No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Deep learning predicts resistance to neoadjuvant chemotherapy for locally advanced gastric cancer: a multicenter study
Abstract
Background:
Accurate pre-treatment prediction of neoadjuvant chemotherapy (NACT) resistance in patients with locally advanced gastric cancer (LAGC) is essential for timely surgeries and optimized treatments. We aim to evaluate the effectiveness of deep learning (DL) on computed tomography (CT) images in predicting NACT resistance in LAGC patients.
Methods:
A total of 633 LAGC patients receiving NACT from three hospitals were included in this retrospective study. The training and internal validation cohorts were randomly selected from center 1, comprising 242 and 104 patients, respectively. The external validation cohort 1 comprised 128 patients from center 2, and the external validation cohort 2 comprised 159 patients from center 3. First, a DL model was developed using ResNet-50 to predict NACT resistance in LAGC patients, and the gradient-weighted class activation mapping (Grad-CAM) was assessed for visualization. Then, an integrated model was constructed by combing the DL signature and clinical characteristics. Finally, the performance was tested in internal and external validation cohorts using area under the receiver operating characteristic (ROC) curves (AUC).
Results:
The DL model achieved AUCs of 0.808 (95% CI 0.724-0.893), 0.755 (95% CI 0.660-0.850), and 0.752 (95% CI 0.678-0.825) in validation cohorts, respectively, which were higher than those of the clinical model. Furthermore, the integrated model performed significantly better than the clinical model (P < 0.05).
Conclusions:
A CT-based model using DL showed promising performance for predicting NACT resistance in LAGC patients, which could provide valuable information in terms of individualized treatment.
... Previous researchers have successfully utilized deep learning techniques to predict lymph node metastasis, depth of infiltration, and survival outcomes in gastric cancer patients, achieving notable results [18,33]. In the context of predicting response to NAC, researchers previously employed deep learning features extracted from a ResNet-50 network and observed AUC values ranging from 0.752 to 0.808 in the validation sets [34], which aligns closely with the findings of this study. However, that study only extracted features from portal venous phase images, potentially overlooking crucial information present in arterial and delayed phase images. ...
... However, these studies were often single-center, had relatively small sample sizes, and lacked external validation. Some researchers found that tumor T stage was a crucial predictive factor for NAC efficacy [34], similar to what was observed in our study. The rationale behind this may be that T staging reflected tumor burden and invasiveness, with larger or more invasive tumors achieving higher staging before treatment, implying greater resistance or difficulty in treatment. ...
... A recent study discovered that extracting deep learning features from the ResNet50 neural network and combining them with clinicopathological features could more accurately predict the response of LAGC to NAC, with AUCs of 0.755 and 0.752 in the internal and external validation sets, respectively. Its efficacy was slightly lower than the nomogram proposed in this study in the internal validation set, possibly because this model did not include manual features [34]. The user-friendly nomogram in this study can be utilized by both clinicians and patients which aligns with the trend of personalized medicine. ...
Purpose
Developed and validated a deep learning radiomics nomogram using multi-phase contrast-enhanced computed tomography (CECT) images to predict neoadjuvant chemotherapy (NAC) response in locally advanced gastric cancer (LAGC) patients.
Methods
This multi-center study retrospectively included 322 patients diagnosed with gastric cancer from January 2013 to June 2023 at two hospitals. Handcrafted radiomics technique and the EfficientNet V2 neural network were applied to arterial, portal venous, and delayed phase CT images to extract two-dimensional handcrafted and deep learning features. A nomogram model was built by integrating the handcrafted signature, the deep learning signature, with clinical features. Discriminative ability was assessed using the receiver operating characteristics (ROC) curve and the precision-recall (P-R) curve. Model fitting was evaluated using calibration curves, and clinical utility was assessed through decision curve analysis (DCA).
Results
The nomogram exhibited excellent performance. The area under the ROC curve (AUC) was 0.848 [95% confidence interval (CI), 0.793–0.893)], 0.802 (95% CI 0.688–0.889), and 0.751 (95% CI 0.652–0.833) for the training, internal validation, and external validation sets, respectively. The AUCs of the P-R curves were 0.838 (95% CI 0.756–0.895), 0.541 (95% CI 0.329–0.740), and 0.556 (95% CI 0.376–0.722) for the corresponding sets. The nomogram outperformed the clinical model and handcrafted signature across all sets (all P < 0.05). The nomogram model demonstrated good calibration and provided greater net benefit within the relevant threshold range compared to other models.
Conclusion
This study created a deep learning nomogram using CECT images and clinical data to predict NAC response in LAGC patients undergoing surgical resection, offering personalized treatment insights.
Graphical abstract
... With the development of computer-aided medicine, accurate assessment of tumor's pathological features has been achieved by combining radiomics and deep learning to extract and analyze quantitative radiological features, known as 'virtual biopsies, ' which provide a reference standard for conventional biopsies [15][16][17]. Several studies have demonstrated the potential role of deep-learning-based radiomics in predicting lymph node metastasis [18] or response to neoadjuvant chemotherapy [19,20] in GC, so this study explored the non-invasive assessment of GC biomarkers based on such methods using preoperative computed enhanced tomography (CECT) images and clinical data. It was also visualized as a nomogram to evaluate the potential application as a virtual biopsy tool in clinical auxiliary diagnosis. ...
... As an emerging means of quantitative image analysis, deep learning can optimize such limitations and improve the accuracy and reliability of prediction models [16,46,47]. The combination of deep learning and radiomics has shown promising results [18][19][20]48]. In this study, we first attempted to apply deep learning algorithms to the calculation and reconstruction of GC-related MSI radiomic features. ...
Objectives:
This study aims to develop and validate a virtual biopsy model to predict microsatellite instability (MSI) status in preoperative gastric cancer (GC) patients based on clinical information and the radiomics of deep learning algorithms.
Methods:
A total of 223 GC patients with MSI status detected by postoperative immunohistochemical staining (IHC) were retrospectively recruited and randomly assigned to the training (n = 167) and testing (n = 56) sets in a 3:1 ratio. In the training set, 982 high-throughput radiomic features were extracted from preoperative abdominal dynamic contrast-enhanced CT (CECT) and screened. According to the deep learning multilayer perceptron (MLP), 15 optimal features were optimized to establish the radiomic feature score (Rad-score), and LASSO regression was used to screen out clinically independent predictors. Based on logistic regression, the Rad-score and clinically independent predictors were integrated to build the clinical radiomics model and visualized as a nomogram and independently verified in the testing set. The performance and clinical applicability of hybrid model in identifying MSI status were evaluated by the area under the receiver operating characteristic (AUC) curve, calibration curve, and decision curve (DCA).
Results:
The AUCs of the clinical image model in training set and testing set were 0.883 [95% CI: 0.822-0.945] and 0.802 [95% CI: 0.666-0.937], respectively. This hybrid model showed good consistency in the calibration curve and clinical applicability in the DCA curve, respectively.
Conclusions:
Using preoperative imaging and clinical information, we developed a deep-learning-based radiomics model for the non-invasive evaluation of MSI in GC patients. This model maybe can potentially support clinical treatment decision making for GC patients.
... In light of this clinical challenge, it is imperative to identify effective biomarkers for predicting the efficacy of NACT in AGC patients. Currently, predictive markers for the response rate of NACT in AGC encompass various factors, including clinical pathological characteristics [8], genomic biomarkers [9], proteomic biomarkers [9], and radiomics parameters [10][11][12]. Since proteins serve as essential functional molecules in biological processes, this study places particular emphasis on proteomic biomarkers. ...
Background
Neoadjuvant chemotherapy (NACT) is routinely used to treat patients with advanced gastric cancer (AGC). However, the identification of reliable markers to determine which AGC patients would benefit from NACT remains challenging.
Methods
A systematic screening of plasma proteins between NACT-sensitive and NACT-resistant AGC patients was performed by a mass spectrometer (n = 6). The effect of the most differential plasma protein was validated in two independent cohorts with AGC patients undergoing NACT (ELISA cohort: n = 155; Validated cohort: n = 203). The expression of this candidate was examined in a cohort of AGC tissues using immunohistochemistry (n = 34). The mechanism of this candidate on 5-Fluorouracil (5-FU) resistance was explored by cell-biology experiments in vitro and vivo.
Results
A series of differential plasma proteins between NACT-sensitive and NACT-resistant AGC patients was identified. Among them, plasma HIST1H2BK was validated as a significant biomarker for predicting NACT response and prognosis. Moreover, HIST1H2BK was over-expression in NACT-resistant tissues compared to NACT-sensitive tissues in AGC. Mechanistically, HIST1H2BK inhibited 5-FU-induced apoptosis by upregulating A2M transcription and then activating LRP/PI3K/Akt pathway, thereby promoting 5-FU resistance in GC cells. Intriguingly, HIST1H2BK-overexpressing 5-FU-resistant GC cells propagated resistance to 5-FU-sensitive GC cells through the secretion of HIST1H2BK.
Conclusion
This study highlights significant differences in plasma protein profiles between NACT-resistant and NACT-sensitive AGC patients. Plasma HIST1H2BK emerged as an effective biomarker for achieving more accurate NACT in AGC. The mechanism of intracellular and secreted HIST1H2BK on 5-FU resistance provided a novel insight into chemoresistance in AGC.
... After screening the titles and abstracts, 177 studies were selected for full-text reading. Finally, 9 studies, comprising 23 cohorts, were included for assessing the diagnostic accuracy of AI algorithms in predicting the response of GC to neoadjuvant chemotherapy (29)(30)(31)(32)(33)(34)(35)(36)(37). Out of these, 7 head-tohead studies were analyzed to compare the diagnostic accuracy of AI, CM, and IM. ...
Background
Artificial intelligence (AI) models, clinical models (CM), and the integrated model (IM) are utilized to evaluate the response to neoadjuvant chemotherapy (NACT) in patients diagnosed with gastric cancer.
Objective
The objective is to identify the diagnostic test of the AI model and to compare the accuracy of AI, CM, and IM through a comprehensive summary of head-to-head comparative studies.
Methods
PubMed, Web of Science, Cochrane Library, and Embase were systematically searched until September 5, 2023, to compile English language studies without regional restrictions. The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) criteria. Forest plots were utilized to illustrate the findings of diagnostic accuracy, while Hierarchical Summary Receiver Operating Characteristic curves were generated to estimate sensitivity (SEN) and specificity (SPE). Meta-regression was applied to analyze heterogeneity across the studies. To assess the presence of publication bias, Deeks’ funnel plot and an asymmetry test were employed.
Results
A total of 9 studies, comprising 3313 patients, were included for the AI model, with 7 head-to-head comparative studies involving 2699 patients. Across the 9 studies, the pooled SEN for the AI model was 0.75 (95% confidence interval (CI): 0.66, 0.82), and SPE was 0.77 (95% CI: 0.69, 0.84). Meta-regression was conducted, revealing that the cut-off value, approach to predicting response, and gold standard might be sources of heterogeneity. In the head-to-head comparative studies, the pooled SEN for AI was 0.77 (95% CI: 0.69, 0.84) with SPE at 0.79 (95% CI: 0.70, 0.85). For CM, the pooled SEN was 0.67 (95% CI: 0.57, 0.77) with SPE at 0.59 (95% CI: 0.54, 0.64), while for IM, the pooled SEN was 0.83 (95% CI: 0.79, 0.86) with SPE at 0.69 (95% CI: 0.56, 0.79). Notably, there was no statistical difference, except that IM exhibited higher SEN than AI, while maintaining a similar level of SPE in pairwise comparisons. In the Receiver Operating Characteristic analysis subgroup, the CT-based Deep Learning (DL) subgroup, and the National Comprehensive Cancer Network (NCCN) guideline subgroup, the AI model exhibited higher SEN but lower SPE compared to the IM. Conversely, in the training cohort subgroup and the internal validation cohort subgroup, the AI model demonstrated lower SEN but higher SPE than the IM. The subgroup analysis underscored that factors such as the number of cohorts, cohort type, cut-off value, approach to predicting response, and choice of gold standard could impact the reliability and robustness of the results.
Conclusion
AI has demonstrated its viability as a tool for predicting the response of GC patients to NACT Furthermore, CT-based DL model in AI was sensitive to extract tumor features and predict the response. The results of subgroup analysis also supported the above conclusions. Large-scale rigorously designed diagnostic accuracy studies and head-to-head comparative studies are anticipated.
Systematic review registration
PROSPERO, CRD42022377030.
... The accuracy achieved by the addition of these AI systems to standard endoscopy has shown significant improvements over un-assisted endoscopy, even outperforming human experts in some cases. The use of CNNs and other DL architectures has proven to be particularly effective in handling the complexity and variability of GC images [19,[56][57][58]. ...
Background: Gastric cancer (GC), a significant health burden worldwide, is typically diagnosed in the advanced stages due to its non-specific symptoms and complex morphological features. Deep learning (DL) has shown potential for improving and standardizing early GC detection. This systematic review aims to evaluate the current status of DL in pre-malignant, early-stage, and gastric neoplasia analysis. Methods: A comprehensive literature search was conducted in PubMed/MEDLINE for original studies implementing DL algorithms for gastric neoplasia detection using endoscopic images. We adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The focus was on studies providing quantitative diagnostic performance measures and those comparing AI performance with human endoscopists. Results: Our review encompasses 42 studies that utilize a variety of DL techniques. The findings demonstrate the utility of DL in GC classification, detection, tumor invasion depth assessment, cancer margin delineation, lesion segmentation, and detection of early-stage and pre-malignant lesions. Notably, DL models frequently matched or outperformed human endoscopists in diagnostic accuracy. However, heterogeneity in DL algorithms, imaging techniques, and study designs precluded a definitive conclusion about the best algorithmic approach. Conclusions: The promise of artificial intelligence in improving and standardizing gastric neoplasia detection, diagnosis, and segmentation is significant. This review is limited by predominantly single-center studies and undisclosed datasets used in AI training, impacting generalizability and demographic representation. Further, retrospective algorithm training may not reflect actual clinical performance, and a lack of model details hinders replication efforts. More research is needed to substantiate these findings, including larger-scale multi-center studies, prospective clinical trials, and comprehensive technical reporting of DL algorithms and datasets, particularly regarding the heterogeneity in DL algorithms and study designs.
... P < 0.01). Due to the phase-lowering effect of preoperative NACT, most of the bene ts in GC patients receiving NACT came from preoperative treatment, while the effect of postoperative treatment was unknown [34][35][36]. By scoring the high-risk factors that affect patient prognosis and recurrence risk, they were divided into low-, moderate-, and high-risk groups. ...
Background
Neoadjuvant chemotherapy combined with radical gastrectomy is the standard treatment for resectable gastric cancer, but whether these patients can benefit from adjuvant chemotherapy remains unclear.
Methods
A total of 732 patients with initially diagnosed non-metastatic resectable gastric cancer between 2004 and 2016 were screened using the Surveillance, Epidemiology, and Results database of the National Cancer Institute of the United States and retrospectively analyzed. Among them, 366 patients received postoperative chemotherapy and 506 patients did not. The propensity score matching was used to balance the two groups of confounding factors, the Kaplan–Meier method was used for survival analysis, and the logrank test was used to compare the differences between the survival curves. The Cox proportional hazards regression model was used to screen independent prognostic factors and establish a nomogram survival prediction model. The patients were divided into high-, moderate-, and low-risk groups according to the overall survival prediction score generated by X-tile software based on the nomogram.
Results
Multivariate analysis showed that the independent prognostic factors of gastric cancer in the group not receiving chemotherapy were history, ypT stage, ypN stage, and examined lymph node count, which were included in the nomogram prediction model. The C-index for the model was 0.727 (95% confidence interval, 0.65056–0.80344). The patients were divided into three different risk level groups based on the nomogram prediction score. Low- and moderate-risk patients did not benefit from adjuvant chemotherapy, while high-risk patients did.
Conclusion
The nomogram model in the present study can effectively evaluate the prognosis of patients with resectable gastric cancer. In addition, postoperative chemotherapy can be recommended for high-risk patients, but not for low-risk patients.
BACKGROUND
Locally advanced gastric cancer (LAGC) is a common malignant tumor. In recent years, neoadjuvant chemotherapy has gradually become popular for the treatment of LAGC.
AIM
To investigate the efficacy of oxaliplatin combined with a tigio neoadjuvant chemotherapy regimen vs a conventional chemotherapy regimen for LAGC.
METHODS
Ninety patients with LAGC were selected and randomly divided into control and study groups with 45 patients in each group, according to the numerical table method. The control group was treated with conventional chemotherapy, and the study group was treated with oxaliplatin combined with tigio-neoadjuvant chemotherapy. The primary outcome measures were the clinical objective response rate (ORR) and surgical resection rate (SRR), whereas the secondary outcome measures were safety and Karnofsky Performance Status score.
RESULTS
The ORR in the study group was 80.00%, which was significantly higher than that of the control group (57.78%). In the study group, SRR was 75.56%, which was significantly higher than that of the control group (57.78%). There were 15.56% adverse reactions in the study group and 35.56% in the control group. These differences were statistically significant between the two groups.
CONCLUSION
The combination of oxaliplatin and tigio before surgery as neoadjuvant chemotherapy for patients with LAGC can effectively improve the ORR and SRR and is safe.
Effective neoadjuvant chemotherapy (NAC) can improve the survival of patients with locally progressive gastric cancer, but chemotherapeutics do not always exhibit good efficacy in all patients. Therefore, accurate preoperative evaluation of the effect of neoadjuvant therapy and the appropriate selection of surgery time to minimize toxicity and complications while prolonging patient survival are key issues that need to be addressed. This paper reviews the role of three imaging methods, morphological, functional, radiomics, and artificial intelligence (AI)-based imaging, in evaluating NAC pathological reactions for gastric cancer. In addition, the advantages and disadvantages of each method and the future application prospects are discussed.
Graphical abstract
Gastric cancer is a leading contributor to cancer incidence and mortality globally. Recently, artificial intelligence approaches, particularly machine learning and deep learning, are rapidly reshaping the full spectrum of clinical management for gastric cancer. Machine learning is formed from computers running repeated iterative models for progressively improving performance on a particular task. Deep learning is a subtype of machine learning on the basis of multilayered neural networks inspired by the human brain. This review summarizes the application of artificial intelligence algorithms to multi-dimensional data including clinical and follow-up information, conventional images (endoscope, histopathology, and computed tomography (CT)), molecular biomarkers, etc. to improve the risk surveillance of gastric cancer with established risk factors; the accuracy of diagnosis, and survival prediction among established gastric cancer patients; and the prediction of treatment outcomes for assisting clinical decision making. Therefore, artificial intelligence makes a profound impact on almost all aspects of gastric cancer from improving diagnosis to precision medicine. Despite this, most established artificial intelligence-based models are in a research-based format and often have limited value in real-world clinical practice. With the increasing adoption of artificial intelligence in clinical use, we anticipate the arrival of artificial intelligence-powered gastric cancer care.
Objectives
An accurate and rapid diagnosis is crucial for the appropriate treatment of pulmonary tuberculosis (TB). This study aims to develop an artificial intelligence (AI)–based fully automated CT image analysis system for detection, diagnosis, and burden quantification of pulmonary TB.Methods
From December 2007 to September 2020, 892 chest CT scans from pathogen-confirmed TB patients were retrospectively included. A deep learning–based cascading framework was connected to create a processing pipeline. For training and validation of the model, 1921 lesions were manually labeled, classified according to six categories of critical imaging features, and visually scored regarding lesion involvement as the ground truth. A “TB score” was calculated based on a network-activation map to quantitively assess the disease burden. Independent testing datasets from two additional hospitals (dataset 2, n = 99; dataset 3, n = 86) and the NIH TB Portals (n = 171) were used to externally validate the performance of the AI model.ResultsCT scans of 526 participants (mean age, 48.5 ± 16.5 years; 206 women) were analyzed. The lung lesion detection subsystem yielded a mean average precision of the validation cohort of 0.68. The overall classification accuracy of six pulmonary critical imaging findings indicative of TB of the independent datasets was 81.08–91.05%. A moderate to strong correlation was demonstrated between the AI model–quantified TB score and the radiologist-estimated CT score.Conclusions
The proposed end-to-end AI system based on chest CT can achieve human-level diagnostic performance for early detection and optimal clinical management of patients with pulmonary TB.Key Points• Deep learning allows automatic detection, diagnosis, and evaluation of pulmonary tuberculosis.• Artificial intelligence helps clinicians to assess patients with tuberculosis.• Pulmonary tuberculosis disease activity and treatment management can be improved.
Importance
Neoadjuvant therapies have been shown to decrease tumor burden, increase resection rate, and improve the outcomes among patients with locally advanced gastric cancer (GC). However, not all patients are equally responsive; therefore, differentiating potential respondents from nonrespondents is clinically important.
Objective
To use pretreatment computed tomography (CT)–pixelated feature-difference extraction techniques to identify diagnostically relevant features that could predict patients’ response to neoadjuvant chemotherapy at diagnosis.
Design, Setting, and Participants
This multicenter cohort study included patients with locally advanced GC who were treated from January 2010 to July 2017 at 2 hospitals in southern China (training cohort) and 1 hospital in northern China (external validation cohort). Their clinicopathological data, pretreatment CT images, and pathological reports were retrieved and analyzed. Data analysis was conducted from December 2017 to May 2021.
Exposures
All patients underwent 2 to 4 cycles of fluorouracil in combination with a platinum-based neoadjuvant chemotherapy regimen. All gastrectomies were performed according to the Japanese Classification of Gastric Carcinoma (14th edition) guidelines.
Main Outcomes and Measures
Reliability of clinicopathological and radiomics-based features were assessed with area under receiver operating characteristic curve (AUC) and Mann-Whitney U test.
Results
A total of 323 patients (242 [74.9%] men; median [range] age, 58 [24-82] years) were included in the study, with 250 patients (77.4%) in the training cohort and 73 (22.6%) in the validation cohort. The baseline pretreatment characteristics of the training and validation cohorts were well-balanced. The number of respondents in the training and validation cohort was 122 (48.8%) and 40 (54.8%), respectively, and the number of nonrespondents was 128 (51.2%) and 33 (45.2%), respectively. No clinicopathological variables were significantly associated with treatment response. Using radiomics, 20 low-intercorrelated features from a total of 7477 features were used to construct a radiomics signature that demonstrated significant association with treatment response. Good discrimination performance of the radiomics signature for predicting treatment response in the training (AUC, 0.736; 95% CI, 0.675-0.798) and external validation (AUC, 0.679; 95% CI, 0.554-0.803) cohorts was observed. Decision curve analysis confirmed the clinical utility of the radiomics signature.
Conclusions and Relevance
In this study, the proposed radiomics signature showed potential as a clinical aid for predicting the response of patients with locally advanced GC before treatment, thereby allowing timely planning for effective treatments for potential nonrespondents.
Objectives
To develop and evaluate machine learning models using baseline and restaging computed tomography (CT) for predicting and early detecting pathological downstaging (pDS) with neoadjuvant chemotherapy in advanced gastric cancer (AGC).
Methods
We collected 292 AGC patients who received neoadjuvant chemotherapy. They were classified into (a) primary cohort (206 patients with 3–4 cycles chemotherapy) for model development and internal validation, (b) testing cohort I (46 patients with 3–4 cycles chemotherapy) for evaluating models’ predictive ability before and after the complete course, and (c) testing cohort II ( n = 40) for model evaluation on its performance at early treatment. We extracted 1,231 radiomics features from venous phase CT at baseline and restaging. We selected radiomics models based on 28 cross-combination models and measured the areas under the curve (AUC). Our prediction radiomics (PR) model is designed to predict pDS outcomes using baseline CT. Detection radiomics (DR) model is applied to restaging CT for early pDS detection.
Results
PR model achieved promising outcomes in two testing cohorts (AUC 0.750, p = .009 and AUC 0.889, p = .000). DR model also showed a good predictive ability (AUC 0.922, p = .000 and AUC 0.850, p = .000), outperforming the commonly used RECIST method (NRI 39.5% and NRI 35.4%). Furthermore, the improved DR model with averaging outcome scores of PR and DR models showed boosted results in two testing cohorts (AUC 0.961, p = .000 and AUC 0.921, p = .000).
Conclusions
CT-based radiomics models perform well on prediction and early detection tasks of pDS and can potentially assist surgical decision-making in AGC patients.
Key Points
• Baseline contrast-enhanced computed tomography (CECT)-based radiomics features were predictive of pathological downstaging, allowing accurate identification of non-responders before therapy.
• Restaging CECT-based radiomics features were predictive to achieve pDS after and even at an early stage of neoadjuvant chemotherapy.
• Combination of baseline and restaging CECT-based radiomics features was promising for early detection and preoperative evaluation of pathological downstaging of AGC.
Importance
Occult peritoneal metastasis frequently occurs in patients with advanced gastric cancer and is poorly diagnosed with currently available tools. Because the presence of peritoneal metastasis precludes the possibility of curative surgery, there is an unmet need for a noninvasive approach to reliably identify patients with occult peritoneal metastasis.
Objective
To assess the use of a deep learning model for predicting occult peritoneal metastasis based on preoperative computed tomography images.
Design, Setting, and Participants
In this multicenter, retrospective cohort study, a deep convolutional neural network, the Peritoneal Metastasis Network (PMetNet), was trained to predict occult peritoneal metastasis based on preoperative computed tomography images. Data from a cohort of 1225 patients with gastric cancer who underwent surgery at Sun Yat-sen University Cancer Center (Guangzhou, China) were used for training purposes. To externally validate the model, data were collected from 2 independent cohorts comprising a total of 753 patients with gastric cancer who underwent surgery at Nanfang Hospital (Guangzhou, China) or the Third Affiliated Hospital of Southern Medical University (Guangzhou, China). The status of peritoneal metastasis for all patients was confirmed by pathological examination of pleural specimens obtained during surgery. Detailed clinicopathological data were collected for each patient. Data analysis was performed between September 1, 2019, and January 31, 2020.
Main Outcomes and Measures
The area under the receiver operating characteristic curve (AUC) and decision curve were analyzed to evaluate performance in predicting occult peritoneal metastasis.
Results
A total of 1978 patients (mean [SD] age, 56.0 [12.2] years; 1350 [68.3%] male) were included in the study. The PMetNet model achieved an AUC of 0.946 (95% CI, 0.927-0.965), with a sensitivity of 75.4% and a specificity of 92.9% in external validation cohort 1. In external validation cohort 2, the AUC was 0.920 (95% CI, 0.848-0.992), with a sensitivity of 87.5% and a specificity of 98.2%. The discrimination performance of PMetNet was substantially higher than conventional clinicopathological factors (AUC range, 0.51-0.63). In multivariable logistic regression analysis, PMetNet was an independent predictor of occult peritoneal metastasis.
Conclusions and Relevance
The findings of this cohort study suggest that the PMetNet model can serve as a reliable noninvasive tool for early identification of patients with clinically occult peritoneal metastasis, which will inform individualized preoperative treatment decision-making and may avoid unnecessary surgery and complications. These results warrant further validation in prospective studies.
Background:
Lymph node metastasis (LNM) in gastric cancer is a prognostic factor and has implications for the extent of lymph node dissection. The lymphatic drainage of the stomach involves multiple nodal stations with different risks of metastases. The aim of this study was to develop a deep learning system for predicting LNMs in multiple nodal stations based on preoperative CT images in patients with gastric cancer.
Methods:
Preoperative CT images from patients who underwent gastrectomy with lymph node dissection at two medical centres were analysed retrospectively. Using a discovery patient cohort, a system of deep convolutional neural networks was developed to predict pathologically confirmed LNMs at 11 regional nodal stations. To gain understanding about the networks' prediction ability, gradient-weighted class activation mapping for visualization was assessed. The performance was tested in an external cohort of patients by analysis of area under the receiver operating characteristic (ROC) curves (AUC), sensitivity and specificity.
Results:
The discovery and external cohorts included 1172 and 527 patients respectively. The deep learning system demonstrated excellent prediction accuracy in the external validation cohort, with a median AUC of 0·876 (range 0·856-0·893), sensitivity of 0·743 (0·551-0·859) and specificity of 0·936 (0·672-0·966) for 11 nodal stations. The imaging models substantially outperformed clinicopathological variables for predicting LNMs (median AUC 0·652, range 0·571-0·763). By visualizing nearly 19 000 subnetworks, imaging features related to intratumoral heterogeneity and the invasive front were found to be most useful for predicting LNMs.
Conclusion:
A deep learning system for the prediction of LNMs was developed based on preoperative CT images of gastric cancer. The models require further validation but may be used to inform prognosis and guide individualized surgical treatment.
PurposeThe increased risk of colorectal cancer (CRC) associated with long-term use of proton pump inhibitors (PPIs) has attracted considerable attention; however, the conclusions of studies evaluating this correlation are inconsistent or even controversial. Therefore, we conducted a systematic review and meta-analysis to determine the association of PPI use with the risk of CRC.MethodsA systematic literature search was conducted in PubMed, EMBASE, and the Cochrane Central Register of Controlled Trials to identify relevant studies. Pooled odds ratios (ORs) with 95% confidence intervals (CIs) for the associations between PPI use and the risk of CRC were estimated with a fixed-effects or random-effects model.ResultsWe identified and included 9 observational studies (3 cohort studies and 6 case-control studies) comprising 1,036,438 participants. Overall, there was no statistically significant association between PPI use and the risk of CRC (pooled OR 1.26, 95% CI: 0.90–1.73; p = 0.166) when PPI exposure was assessed as a binary variable. However, a weak association between long-term use of PPIs and CRC was demonstrated (pooled OR 1.19, 95% CI: 1.09–1.31; p < 0.001) when the cumulative duration of PPI exposure was confined to > 5 years.Conclusions
Although the present meta-analysis suggests a weak association between long-term use (> 5 years) of PPIs and CRC, there is not enough statistical power to refute or confirm an association between the use of PPIs and CRC. More high-quality prospective cohort studies are needed to assess this correlation.
Background:
Neoadjuvant chemotherapy is a promising treatment option for potential resectable gastric cancer, but patients' responses vary. We aimed to develop and validate a radiomics score (rad_score) to predict treatment response to neoadjuvant chemotherapy and to investigate its efficacy in survival stratification.
Methods:
A total of 106 patients with neoadjuvant chemotherapy before gastrectomy were included (training cohort: n = 74; validation cohort: n = 32). Radiomics features were extracted from the pre-treatment portal venous-phase CT. After feature reduction, a rad_score was established by Randomised Tree algorithm. A rad_clinical_score was constructed by integrating the rad_score with clinical variables, so was a clinical score by clinical variables only. The three scores were validated regarding their discrimination and clinical usefulness. The patients were stratified into two groups according to the score thresholds (updated with post-operative clinical variables), and their survivals were compared.
Results:
In the validation cohort, the rad_score demonstrated a good predicting performance in treatment response to the neoadjuvant chemotherapy (AUC [95% CI] =0.82 [0.67, 0.98]), which was better than the clinical score (based on pre-operative clinical variables) without significant difference (0.62 [0.42, 0.83], P = 0.09). The rad_clinical_score could not further improve the performance of the rad_score (0.70 [0.51, 0.88], P = 0.16). Based on the thresholds of these scores, the high-score groups all achieved better survivals than the low-score groups in the whole cohort (all P < 0.001).
Conclusion:
The rad_score that we developed was effective in predicting treatment response to neoadjuvant chemotherapy and in stratifying patients with gastric cancer into different survival groups. Our proposed strategy is useful for individualised treatment planning.
Gastric cancer is one of the most common digestive system tumors in China, and locally advanced gastric cancer (LAGC) accounts for a high proportion of newly diagnosed cases. Although surgery is the main treatment for gastric cancer, surgical excision alone cannot achieve satisfactory outcomes in LAGC patients. Neoadjuvant therapy (NAT) has gradually become the standard treatment for patients with LAGC, and this treatment can not only achieve tumor downstaging and improve surgical rate and the R0 resection rate, but it also significantly improves the long-term prognosis of patients. Peri/preoperative neoadjuvant chemotherapy and preoperative chemoradiotherapy are both recommended according to a large number of studies, and the regimens have also been evolved in the past decades. Since the NCCN guidelines for gastric cancer are one of the most authoritative evidence-based guidelines worldwide, here, we demonstrate the development course and major breakthroughs of NAT for gastric cancer based on the vicissitudes of the NCCN guidelines from 2007 to 2019, and also discuss the future of NAT.
Objective:
We aimed to develop a deep learning-based signature to predict prognosis and benefit from adjuvant chemotherapy using preoperative computed tomography (CT) images.
Background:
Current staging methods do not accurately predict the risk of disease relapse for patients with gastric cancer.
Methods:
We proposed a novel deep neural network (S-net) to construct a CT signature for predicting disease-free survival (DFS) and overall survival in a training cohort of 457 patients, and independently tested it in an external validation cohort of 1158 patients. An integrated nomogram was constructed to demonstrate the added value of the imaging signature to established clinicopathologic factors for individualized survival prediction. Prediction performance was assessed with respect to discrimination, calibration, and clinical usefulness.
Results:
The DeLIS was associated with DFS and overall survival in the overall validation cohort and among subgroups defined by clinicopathologic variables, and remained an independent prognostic factor in multivariable analysis (P< 0.001). Integrating the imaging signature and clinicopathologic factors improved prediction performance, with C-indices: 0.792-0.802 versus 0.719-0.724, and net reclassification improvement 10.1%-28.3%. Adjuvant chemotherapy was associated with improved DFS in stage II patients with high-DeLIS [hazard ratio = 0.362 (95% confidence interval 0.149-0.882)] and stage III patients with high- and intermediate-DeLIS [hazard ratio = 0.611 (0.442-0.843); 0.633 (0.433-0.925)]. On the other hand, adjuvant chemotherapy did not affect survival for patients with low-DeLIS, suggesting a predictive effect (Pinteraction = 0.048, 0.016 for DFS in stage II and III disease).
Conclusions:
The proposed imaging signature improved prognostic prediction and could help identify patients most likely to benefit from adjuvant chemotherapy in gastric cancer.
Objective:
To develop a predicting model for tumor resistance to neoadjuvant chemoradiotherapy (NCRT) in locally advanced rectal cancer (LARC) by using pre-treatment apparent diffusion coefficient (ADC) image-derived radiomics features.
Method:
A total of 89 patients with LARC were randomly assigned into training (N = 66) and testing cohorts (N = 23) at the ratio of 3:1. Radiomics features were derived from manually determined tumor region of pre-treatment ADC images. Random forest algorithm was used to determine the most relevant features and then to construct a predicting model for identifying resistant tumor. Stability and diagnostic performance of the random forest model was evaluated with the testing cohort.
Results:
The top 10 most relevant features (entropymean, inverse variance, energymean, small area emphasis, ADCmin, ADCmean, sdGa02, small gradient emphasis, age, and size) were determined from clinical characteristics and 133 radiomics features. In the prediction of resistant tumor of the testing cohort, the random forest model constructed based on these most relevant features achieved an area under the receiver operating characteristic curve of 0.83, with the highest accuracy of 91.3%, a sensitivity of 88.9%, and a specificity of 92.8%.
Conclusion:
The random forest classifier based on radiomics features derived from pre-treatment ADC images have the potential to predict tumor resistance to NCRT in patients with LARC, and the use of predicting model may facilitate individualized management of rectal cancer.
Objective
The aim of this study was to investigate whether pretherapeutic, multiparametric magnetic resonance imaging (MRI) radiomic features can be used for predicting non-response to neoadjuvant therapy in patients with locally advanced rectal cancer (LARC).
Methods
We retrospectively enrolled 425 patients with LARC [allocated in a 3:1 ratio to a primary (n = 318) or validation (n = 107) cohort] who received neoadjuvant therapy before surgery. All patients underwent T1-weighted, T2-weighted, diffusion-weighted, and contrast-enhanced T1-weighted MRI scans before receiving neoadjuvant therapy. We extracted 2424 radiomic features from the pretherapeutic, multiparametric MR images of each patient. The Wilcoxon rank-sum test, Spearman correlation analysis, and least absolute shrinkage and selection operator regression were successively performed for feature selection, whereupon a multiparametric MRI-based radiomic model was established by means of multivariate logistic regression analysis. This feature selection and multivariate logistic regression analysis was also performed on all single-modality MRI data to establish four single-modality radiomic models. The performance of the five radiomic models was evaluated by receiver operating characteristic (ROC) curve analysis in both cohorts.
Results
The multiparametric, MRI-based radiomic model based on 16 features showed good predictive performance in both the primary (p < 0.01) and validation (p < 0.05) cohorts, and performed better than all single-modality models. The area under the ROC curve of this multiparametric MRI-based radiomic model achieved a score of 0.822 (95% CI 0.752–0.891).
Conclusions
We demonstrated that pretherapeutic, multiparametric MRI radiomic features have potential in predicting non-response to neoadjuvant therapy in patients with LARC.
Background
For virtually every patient with colorectal cancer (CRC), hematoxylin–eosin (HE)–stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can extract prognosticators directly from these widely available images.
Methods and findings
We hand-delineated single-tissue regions in 86 CRC tissue slides, yielding more than 100,000 HE image patches, and used these to train a CNN by transfer learning, reaching a nine-class accuracy of >94% in an independent data set of 7,180 images from 25 CRC patients. With this tool, we performed automated tissue decomposition of representative multitissue HE images from 862 HE slides in 500 stage I–IV CRC patients in the The Cancer Genome Atlas (TCGA) cohort, a large international multicenter collection of CRC tissue. Based on the output neuron activations in the CNN, we calculated a “deep stroma score,” which was an independent prognostic factor for overall survival (OS) in a multivariable Cox proportional hazard model (hazard ratio [HR] with 95% confidence interval [CI]: 1.99 [1.27–3.12], p = 0.0028), while in the same cohort, manual quantification of stromal areas and a gene expression signature of cancer-associated fibroblasts (CAFs) were only prognostic in specific tumor stages. We validated these findings in an independent cohort of 409 stage I–IV CRC patients from the “Darmkrebs: Chancen der Verhütung durch Screening” (DACHS) study who were recruited between 2003 and 2007 in multiple institutions in Germany. Again, the score was an independent prognostic factor for OS (HR 1.63 [1.14–2.33], p = 0.008), CRC-specific OS (HR 2.29 [1.5–3.48], p = 0.0004), and relapse-free survival (RFS; HR 1.92 [1.34–2.76], p = 0.0004). A prospective validation is required before this biomarker can be implemented in clinical workflows.
Conclusions
In our retrospective study, we show that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images.
Objective
The standard treatment for patients with locally advanced gastric cancer has relied on perioperative radio-chemotherapy or chemotherapy and surgery. The aim of this study was to investigate the wealth of radiomics for pre-treatment computed tomography (CT) in the prediction of the pathological response of locally advanced gastric cancer with preoperative chemotherapy.
Methods
Thirty consecutive patients with CT-staged II/III gastric cancer receiving neoadjuvant chemotherapy were enrolled in this study between December 2014 and March 2017. All patients underwent upper abdominal CT during the unenhanced, late arterial phase (AP) and portal venous phase (PP) before the administration of neoadjuvant chemotherapy. In total, 19,985 radiomics features were extracted in the AP and PP for each patient. Four methods were adopted during feature selection and eight methods were used in the process of building the classifier model. Thirty-two combinations of feature selection and classification methods were examined. Receiver operating characteristic (ROC) curves were used to evaluate the capability of each combination of feature selection and classification method to predict a non-good response (non-GR) based on tumor regression grade (TRG).
Results
The mean area under the curve (AUC) ranged from 0.194 to 0.621 in the AP, and from 0.455 to 0.722 in the PP, according to different combinations of feature selection and the classification methods. There was only one cross-combination machine-learning method indicating a relatively higher AUC (>0.600) in the AP, while 12 cross-combination machine-learning methods presented relatively higher AUCs (all >0.600) in the PP. The feature selection method adopted by a filter based on linear discriminant analysis + classifier of random forest achieved a significantly prognostic performance in the PP (AUC, 0.722±0.108; accuracy, 0.793; sensitivity, 0.636; specificity, 0.889; Z=2.039; P=0.041).
Conclusions
It is possible to predict non-GR after neoadjuvant chemotherapy in locally advanced gastric cancers based on the radiomics of CT.
Significance
Predicting the expected outcome of patients diagnosed with cancer is a critical step in treatment. Advances in genomic and imaging technologies provide physicians with vast amounts of data, yet prognostication remains largely subjective, leading to suboptimal clinical management. We developed a computational approach based on deep learning to predict the overall survival of patients diagnosed with brain tumors from microscopic images of tissue biopsies and genomic biomarkers. This method uses adaptive feedback to simultaneously learn the visual patterns and molecular biomarkers associated with patient outcomes. Our approach surpasses the prognostic accuracy of human experts using the current clinical standard for classifying brain tumors and presents an innovative approach for objective, accurate, and integrated prediction of patient outcomes.
Background
The diagnostic and prognostic significance of carcinoembryonic antigen (CEA), carbohydrate associated antigen 19–9 (CA19–9), alpha-fetoprotein (AFP) and cancer antigen 125 (CA125) in early gastric cancer have not been investigated yet. Thus, the present study aimed to explore the diagnostic and prognostic significance of the four tumor markers for early gastric cancer.
Methods
From September 2008 to March 2015, 587 early gastric cancer patients were given radical gastrectomy in our center. The clinicopathological characteristics were recorded. The association between levels of CEA and CA19–9 and clinicopathological characteristics and prognosis of patients were analyzed.
Results
There were 444 men (75.6%) and 143 women (24.4%). The median age was 57 years (ranged 21–85). The 1-, 3- and 5-year overall survival rate was 99.1%, 96.8% and 93.1%, respectively. The positive rate of CEA, CA19–9, AFP and CA125 was 4.3%, 4.8%, 1.5% and 1.9%, respectively. The positive rate of all markers combined was 10.4%. The associations between the clinicopathological features and levels of CEA and CA19–9 were analyzed. No significant association was found between CEA level and clinicopathological features. However, elevated CA19–9 level was correlated with female gender and presence of lymph node metastasis. Age > 60 years old, presence of lymph node metastasis and elevation of CEA level were independent risk factors for poor prognosis of early gastric cancer.
Conclusions
The positive rates of CEA, CA19–9, APF and CA125 were relatively low for early gastric cancer. Elevation of CA19–9 level was associated with female gender and presence of lymph node metastasis. Elevation of CEA level was an independent risk factor for the poor prognosis of early gastric cancer.
Purpose To identify the molecular basis of quantitative imaging characteristics of tumor-adjacent parenchyma at dynamic contrast material-enhanced magnetic resonance (MR) imaging and to evaluate their prognostic value in breast cancer. Materials and Methods In this institutional review board-approved, HIPAA-compliant study, 10 quantitative imaging features depicting tumor-adjacent parenchymal enhancement patterns were extracted and screened for prognostic features in a discovery cohort of 60 patients. By using data from The Cancer Genome Atlas (TCGA), a radiogenomic map for the tumor-adjacent parenchymal tissue was created and molecular pathways associated with prognostic parenchymal imaging features were identified. Furthermore, a multigene signature of the parenchymal imaging feature was built in a training cohort (n = 126), and its prognostic relevance was evaluated in two independent cohorts (n = 879 and 159). Results One image feature measuring heterogeneity (ie, information measure of correlation) was significantly associated with prognosis (false-discovery rate < 0.1), and at a cutoff of 0.57 stratified patients into two groups with different recurrence-free survival rates (log-rank P = .024). The tumor necrosis factor signaling pathway was identified as the top enriched pathway (hypergeometric P < .0001) among genes associated with the image feature. A 73-gene signature based on the tumor profiles in TCGA achieved good association with the tumor-adjacent parenchymal image feature (R(2) = 0.873), which stratified patients into groups regarding recurrence-free survival (log-rank P = .029) and overall survival (log-rank P = .042) in an independent TCGA cohort. The prognostic value was confirmed in another independent cohort (Gene Expression Omnibus GSE 1456), with log-rank P = .00058 for recurrence-free survival and log-rank P = .0026 for overall survival. Conclusion Heterogeneous enhancement patterns of tumor-adjacent parenchyma at MR imaging are associated with the tumor necrosis signaling pathway and poor survival in breast cancer. (©) RSNA, 2017 Online supplemental material is available for this article.
In the clinical practice of neoadjuvant chemotherapy, response markers are very important. We aimed o investigate whether tumor markers CEA(carcino-embryonic antigen), CA19-9(carbohydrate antigen 19-9), CA72-4(carbohydrate antigen 72-4), and CA125(carbohydrate antigen 125) can be used to evaluate the response to neoadjuvant chemotherapy, and to evaluate the diagnosis and prognosis value of four tumor markers in the patients of gastric cancer.
A retrospective review was performed of 184 gastric cancer patients who underwent a 5-Fu, leucovorin, and oxaliplatin (FOLFOX) neoadjuvant chemotherapy regimen, followed by surgical treatment. Blood samples for CEA, CA19-9, CA72-4, and CA125 levels were taken from patients upon admission to the hospital and after neoadjuvant chemotherapy. Statistical analysis was performed to identify the clinical value of these tumor markers in predicting the survival and the response to neoadjuvant chemotherapy.
Median overall survival times of pretreatment CA19-9-positive and CA72-4-positive patients (14.0 +/-2.8 months and 14.8 +/-4.0 months, respectively) were significantly less than negative patients (32.5 +/-8.9 months and 34.0 +/-10.1 months, respectively) (P = 0.000 and P = 0.002, respectively). Pretreatment status of CA19-9 and CA72-4 were independent prognostic factors in gastric cancer patients (P = 0.029 and P = 0.008, respectively). Pretreatment CEA >50 ng/ml had a positive prediction value for clinical disease progression after neoadjuvant chemotherapy according to the ROC curve (AUC: 0.694, 95% CI: 0.517 to 0.871, P = 0.017). The decrease of tumor markers CEA, CA72-4, and CA125 was significant after neoadjuvant chemotherapy (P = 0.030, P = 0.010, and P = 0.009, respectively), especially in patients with disease control (including complete, partial clinical response, and stable disease) (P = 0.012, P = 0.020, and P = 0.025, respectively). A decrease in CA72-4 by more than 70% had a positive prediction value for pathologic response to neoadjuvant chemotherapy according to the ROC curve (AUC: 0.764, 95% CI: 0.584 to 0.945, P = 0.020).
Our results suggest that high preoperative serum levels of CA72-4 and CA19-9 are associated with higher risk of death, high pretreatment CEA levels (>50 ng/ml) may predict clinical disease progression after neoadjuvant chemotherapy, and a decrease (>70%) of CA72-4 may predict pathologic response to neoadjuvant chemotherapy.
Objectives
To evaluate whether early reductions in CT perfusion parameters predict response to pre-operative chemotherapy prior to surgery for gastroesophageal junction (GEJ) and gastric cancer.
Materials and Methods
Twenty-eight patients with adenocarcinoma of the gastro-esophageal junction (GEJ) and stomach were included. Patients received three series of chemotherapy before surgery, each consisting of a 3-week cycle of intravenous epirubicin, cisplatin or oxaliplatin, concomitant with capecitabine peroral. The patients were evaluated with a CT perfusion scan prior to, after the first series of, and after three series of chemotherapy. The CT perfusion scans were performed using a 320-detector row scanner. Tumour volume and perfusion parameters (arterial flow, blood volume and permeability) were computed on a dedicated workstation with a consensus between two radiologists. Response to chemotherapy was evaluated by two measures. Clinical response was defined as a tumour size reduction of more than 50%. Histological response was evaluated based on residual tumour cells in the surgical specimen using the standardized Mandard Score 1 to 5, in which values of 1 and 2 were classified as responders, and 3 to 5 were classified as nonresponders.
Results
A decrease in tumour permeability after one series of chemotherapy was positively correlated with clinical response after three series of chemotherapy. Significant changes in permeability and tumour volume were apparent after three series of chemotherapy in both clinical and histological responders. A cut-off value of more than 25% reduction in tumour permeability yielded a sensitivity of 69% and a specificity of 58% for predicting clinical response.
Conclusion
Early decrease in permeability is correlated with the likelihood of clinical response to pre-operative chemotherapy in GEJ and gastric cancer. As a single diagnostic test, CT Perfusion only has moderate sensitivity and specificity in response assessment of pre-operative chemotherapy making it insufficient for clinical decision purposes.
To quantitatively assess the ability of double contrast-enhanced ultrasound (DCUS) to detect tumor early response to pre-operative chemotherapy.
Forty-three patients with gastric cancer treated with neoadjuvant chemotherapy followed by curative resection between September 2011 and February 2012 were analyzed. Pre-operative chemotherapy regimens of fluorouracil + oxaliplatin or S-1 + oxaliplatin were administered in 2-4 cycles over 6-12 wk periods. All patients underwent contrast-enhanced computed tomography (CT) scan and DCUS before and after two courses of pre-operative chemotherapy. The therapeutic response was assessed by CT using the response evaluation criteria in solid tumors (RECIST 1.1) criteria. Tumor area was assessed by DCUS as enhanced appearance of gastric carcinoma due to tumor vascularity during the contrast phase as compared to the normal gastric wall. Histopathologic analysis was carried out according to the Mandard tumor regression grade criteria and used as the reference standard. Receiver operating characteristic (ROC) analysis was used to evaluate the efficacy of DCUS parameters in differentiating histopathological responders from non-responders.
The study population consisted of 32 men and 11 women, with mean age of 59.7 ± 11.4 years. Neither age, sex, histologic type, tumor site, T stage, nor N stage was associated with pathological response. The responders had significantly smaller mean tumor size than the non-responders (15.7 ± 7.4 cm vs 33.3 ± 14.1 cm, P < 0.01). According to Mandard's criteria, 27 patients were classified as responders, with 11 (40.7%) showing decreased tumor size by DCUS. In contrast, only three (18.8%) of the 16 non-responders showed decreased tumor size by DCUS (P < 0.01). The area under the ROC curve was 0.64, with a 95%CI of 0.46-0.81. The effects of several cut-off points on diagnostic parameters were calculated in the ROC curve analysis. By maximizing Youden's index (sensitivity + specificity - 1), the best cut-off point for distinguishing responders from non-responders was determined, which had optimal sensitivity of 62.9% and specificity of 56.3%. Using this cut-off point, the positive and negative predictive values of DCUS for distinguishing responders from non-responders were 70.8% and 47.4%, respectively. The overall accuracy of DCUS for therapeutic response assessment was 60.5%, slightly higher than the 53.5% for CT response assessment with RECIST criteria (P = 0.663). Although the advantage was not statistically significant, likely due to the small number of cases assessed. DCUS was able to identify decreased perfusion in responders who showed no morphological change by CT imaging, which can be occluded by such treatment effects as fibrosis and edema.
DCUS may represent an innovative tool for more accurately predicting histopathological response to neoadjuvant chemotherapy before surgical resection in patients with locally-advanced gastric cancer.
A representation and interpretation of the area under a receiver operating characteristic (ROC) curve obtained by the "rating" method, or by mathematical predictions based on patient characteristics, is presented. It is shown that in such a setting the area represents the probability that a randomly chosen diseased subject is (correctly) rated or ranked with greater suspicion than a randomly chosen non-diseased subject. Moreover, this probability of a correct ranking is the same quantity that is estimated by the already well-studied nonparametric Wilcoxon statistic. These two relationships are exploited to (a) provide rapid closed-form expressions for the approximate magnitude of the sampling variability, i.e., standard error that one uses to accompany the area under a smoothed ROC curve, (b) guide in determining the size of the sample required to provide a sufficiently reliable estimate of this area, and (c) determine how large sample sizes should be to ensure that one can statistically detect differences in the accuracy of diagnostic techniques.
Purpose
To investigate whether computed tomography (CT) could be used for screening and surveillance of small gastric gastrointestinal stromal tumors (gGISTs).
Method
A total of 162 pathologically confirmed small gGISTs (≤2 cm) between September 2007 and November 2019 were retrospectively enrolled. Thirty-six lesions received contrast-enhanced CT after they were identified by endoscopy and EUS, and forty-three lesions received CT alone before surgery. The detection rate of CT for ≤1 cm gGISTs (micro-gGISTs) and 1–2 cm gGISTs (mini-gGISTs) was investigated, and the detection rate of CT alone was compared with that of CT following endoscopy and EUS. The relationship between EUS- and CT-detected high-risk features were assessed.
Results
CT demonstrated a favorable detection rate for mini-gGISTs previously identified by EUS and endoscopy, whereas CT alone showed an inferior detection rate (100 % vs. 75 %, p = 0.02). CT showed a poor detection rate for micro-gGISTs, both for lesions received CT after identified by EUS and endoscopy, and those received CT alone (33.3 % vs. 14.8 %, p = 0.372). CT-detected heterogeneous enhancement pattern and presence of calcification were strongly correlated with heterogeneous echotexture (Spearman’s ρ=0.66, p < 0.001) and echogenic foci (Spearman’s ρ=0.79, p < 0.001) on EUS, respectively. CT-detected necrosis was moderately correlated with cystic spaces on EUS (Spearman’s ρ=0.42, p = 0.02). No correlation was found between EUS- and CT- assessed irregular border.
Conclusions
CT could potentially be considered as a surrogate of EUS for surveillance of mini-gGISTs instead of micro-gGISTs, whereas couldn’t be used as a screening modality for either micro- or mini-gGISTs.
Purpose
To assess the efficacy of diffusion kurtosis imaging (DKI) in the prediction of the treatment response to neoadjuvant chemotherapy in patients with locally advanced gastric cancer (LAGC).
Methods
A total of 31 LAGC patients were enrolled in this prospective study. All patients underwent diffusion-weighted MRI examination (with b = 01, 2001, 5001, 8002, 10004, 15004, 20006 s/mm², the subscript denotes the number of signal averages) before and after chemotherapy. DKI and mono-exponential (b = 0, 800 s/mm²) models were built. Apparent diffusion coefficient (ADC), mean diffusivity (MD) and mean kurtosis (MK) of the LAGC tumors were measured. The absolute change values (ΔX) and percentage change values (%ΔX) of the above parameters post neoadjuvant chemotherapy (NACT) were calculated. The response was evaluated according to the pathological tumor regression grade scores (effective response group: TRG 0-2, poor response group: TRG 3). Mann-Whitney U test and receiver operating characteristic (ROC) curves were applicated for statistical analysis.
Results
There were 17 patients in the effective response group (ERG), and 14 patients in the poor response group (PRG). The MKpre and MKpost values in PRG were significantly higher than those in ERG [(0.671 ± 0.026) and (0.641 ± 0.019) vs. (0.584 ± 0.023) and (0.519 ± 0.018), p < 0.001]. ADCpost and MDpost in PRG were significantly lower than those in ERG (p = 0.003, p < 0.001). Significant differences were also observed for % ΔMK, ΔMD and ΔMK between the two groups (p < 0.05). The area under the curve (AUC) for the prediction of PRG was highest for MKpost (AUC = 0.958, cutoff value = 0.614). The MKpre and MKpost had the highest sensitivity (91.7%) and specificity (93.8%) in the prediction of PRG, respectively.
Conclusion
Both DKI and ADC values show potential for the prediction of the PRG in LAGC patients. The DKI parameters, especially MKpost displayed the best performance.
Background:
The aim of the present work is to develop and validate accurate preoperative nomograms to predict microvascular invasion (MVI) and lymph node metastasis (LNM) in hepatocellular carcinoma.
Patients and methods:
A total of 268 patients with resected hepatocellular carcinoma (HCC) were divided into a training set (n = 180), in an earlier period, and a validation set (n = 88), thereafter. Risk factors for MVI and LNM were assessed based on logistic regression. Blood signatures were established using the least absolute shrinkage and selection operator algorithm. Nomograms were constructed by combining risk factors and blood signatures. Performance was evaluated using the training set and validated using the validation set. The clinical values of the nomograms were measured by decision curve analysis.
Results:
The risk factors for MVI were hepatitis B virus (HBV) DNA loading, portal hypertension, Barcelona liver clinic (BCLC) stage, and three computerized tomography (CT) imaging features, namely tumor number, size, and encapsulation, while only BCLC stage, Child-Pugh classification, and tumor encapsulation were associated with LNM. The nomogram incorporating both risk factors and blood signatures achieved better performance in predicting MVI in the training and validation sets (C-indexes of 0.828 and 0.804) than the LNM nomogram (C-indexes of 0.765 and 0.717). Calibration curves also demonstrated a good fit. The decision curves indicate significant clinical usefulness.
Conclusions:
The novel validated nomograms for HCC patients presented herein are noninvasive preoperative tools that can effectively predict the individualized risk of MVI and LNM, and this predictive power can aid doctors in explaining the illness for patient counseling.
Background:
Artificial intelligence-assisted image recognition technology is currently able to detect the target area of an image and fetch information to make classifications according to target features. This study aimed to use deep neural networks for computed tomography (CT) diagnosis of perigastric metastatic lymph nodes (PGMLNs) to simulate the recognition of lymph nodes by radiologists, and to acquire more accurate identification results.
Methods:
A total of 1371 images of suspected lymph node metastasis from enhanced abdominal CT scans were identified and labeled by radiologists and were used with 18,780 original images for faster region-based convolutional neural networks (FR-CNN) deep learning. The identification results of 6000 random CT images from 100 gastric cancer patients by the FR-CNN were compared with results obtained from radiologists in terms of their identification accuracy. Similarly, 1004 CT images with metastatic lymph nodes that had been post-operatively confirmed by pathological examination and 11,340 original images were used in the identification and learning processes described above. The same 6000 gastric cancer CT images were used for the verification, according to which the diagnosis results were analyzed.
Results:
In the initial group, precision-recall curves were generated based on the precision rates, the recall rates of nodule classes of the training set and the validation set; the mean average precision (mAP) value was 0.5019. To verify the results of the initial learning group, the receiver operating characteristic curves was generated, and the corresponding area under the curve (AUC) value was calculated as 0.8995. After the second phase of precise learning, all the indicators were improved, and the mAP and AUC values were 0.7801 and 0.9541, respectively.
Conclusion:
Through deep learning, FR-CNN achieved high judgment effectiveness and recognition accuracy for CT diagnosis of PGMLNs.
Trial registration:
Chinese Clinical Trial Registry, No. ChiCTR1800016787; http://www.chictr.org.cn/showproj.aspx?proj=28515.
Objective:
The aim of this study was to compare stage II/III rectal cancers with or without high-risk factors, and evaluate the effect of neoadjuvant radiotherapy (NRT) in these 2 cohorts.
Background:
NRT is often used in stage II/III rectal cancers to improve local control, while not affecting overall survival. However, good-quality surgery without NRT may also achieve good local control in selected patients.
Methods:
According to risk-stratification criteria and clinical staging, consecutive eligible participants of stage II/III rectal cancer were preoperatively classified into patients with (high-risk) or without (low-risk) high-risk factors. Both groups were respectively randomized to receive either short-course radiotherapy (SCRT) + total mesorectal excision (TME) or TME alone, forming the following 4 groups: high-risk patients with (HiR) or without (HiS) radiation, and low-risk patients with (LoR) or without (LoS) radiation. The primary endpoint was local recurrence. The secondary endpoints included overall survival, disease-free survival, distant recurrence, quality of surgery, and safety (NCT01437514).
Results:
In total, 401 patients were analyzed. With a median 54 months' follow-up, low-risk patients obtained better 3-year cumulative incidence of local recurrence (2.2% vs 11.0%, P = 0.006), overall survival rate (86.9%vs 76.5%, P = 0.002), disease-free survival rate (87.0% vs 67.9%, P < 0.001), and cumulative incidence of distant recurrence (12.5% vs 29.4%, P < 0.001) than high-risk patients. With regard to 3-year cumulative incidence of local recurrence, no differences were observed between the LoR and LoS groups (1.2% vs 3.0%, P = 0.983) or the HiR and HiS groups (12.9% vs 8.9%, P = 0.483).
Conclusions and relevance:
Stratification of stage II/III rectal cancers according to risk factors to more precise subclassifications may result in noteworthy differences in survivals and local pelvic control. An extremely low cumulative incidence of local recurrence and survivals in low-risk patients can be achieved with upfront good quality of surgery alone. This trial, owing to the insufficient power, could not prove the noninferiority of surgery alone, but suggest a discriminative use of NRT according to clinical risk stratification in stage II/III rectal cancer.
urpose: We aimed to evaluate the value of deep learning on positron emission tomography with computed tomography (ET/CT)–based radiomics for individual induction chemotherapy (IC) in advanced nasopharyngeal carcinoma (NC).
Experimental Design: We constructed radiomics signatures and nomogram for predicting disease-free survival (DFS) based on the extracted features from ET and CT images in a training set (n = 470), and then validated it on a test set (n = 237). Harrell's concordance indices (C-index) and time-independent receiver operating characteristic (ROC) analysis were applied to evaluate the discriminatory ability of radiomics nomogram, and compare radiomics signatures with plasma Epstein–Barr virus (EBV) DNA.
Results: A total of 18 features were selected to construct CT-based and ET-based signatures, which were significantly associated with DFS ( < 0.001). Using these signatures, we proposed a radiomics nomogram with a C-index of 0.754 [95% confidence interval (95% CI), 0.709–0.800] in the training set and 0.722 (95% CI, 0.652–0.792) in the test set. Consequently, 206 (29.1%) patients were stratified as high-risk group and the other 501 (70.9%) as low-risk group by the radiomics nomogram, and the corresponding 5-year DFS rates were 50.1% and 87.6%, respectively ( < 0.0001). High-risk patients could benefit from IC while the low-risk could not. Moreover, radiomics nomogram performed significantly better than the EBV DNA-based model (C-index: 0.754 vs. 0.675 in the training set and 0.722 vs. 0.671 in the test set) in risk stratification and guiding IC.
Conclusions: Deep learning ET/CT-based radiomics could serve as a reliable and powerful tool for prognosis prediction and may act as a potential indicator for individual IC in advanced NC.
This article provides a status report on the global burden of cancer worldwide using the GLOBOCAN 2018 estimates of cancer incidence and mortality produced by the International Agency for Research on Cancer, with a focus on geographic variability across 20 world regions. There will be an estimated 18.1 million new cancer cases (17.0 million excluding nonmelanoma skin cancer) and 9.6 million cancer deaths (9.5 million excluding nonmelanoma skin cancer) in 2018. In both sexes combined, lung cancer is the most commonly diagnosed cancer (11.6% of the total cases) and the leading cause of cancer death (18.4% of the total cancer deaths), closely followed by female breast cancer (11.6%), prostate cancer (7.1%), and colorectal cancer (6.1%) for incidence and colorectal cancer (9.2%), stomach cancer (8.2%), and liver cancer (8.2%) for mortality. Lung cancer is the most frequent cancer and the leading cause of cancer death among males, followed by prostate and colorectal cancer (for incidence) and liver and stomach cancer (for mortality). Among females, breast cancer is the most commonly diagnosed cancer and the leading cause of cancer death, followed by colorectal and lung cancer (for incidence), and vice versa (for mortality); cervical cancer ranks fourth for both incidence and mortality. The most frequently diagnosed cancer and the leading cause of cancer death, however, substantially vary across countries and within each country depending on the degree of economic development and associated social and life style factors. It is noteworthy that high‐quality cancer registry data, the basis for planning and implementing evidence‐based cancer control programs, are not available in most low‐ and middle‐income countries. The Global Initiative for Cancer Registry Development is an international partnership that supports better estimation, as well as the collection and use of local data, to prioritize and evaluate national cancer control efforts. CA: A Cancer Journal for Clinicians 2018;0:1‐31. © 2018 American Cancer Society
Purpose To characterize intratumoral spatial heterogeneity at perfusion magnetic resonance (MR) imaging and investigate intratumoral heterogeneity as a predictor of recurrence-free survival (RFS) in breast cancer. Materials and Methods In this retrospective study, a discovery cohort (n = 60) and a multicenter validation cohort (n = 186) were analyzed. Each tumor was divided into multiple spatially segregated, phenotypically consistent subregions on the basis of perfusion MR imaging parameters. The authors first defined a multiregional spatial interaction (MSI) matrix and then, based on this matrix, calculated 22 image features. A network strategy was used to integrate all image features and classify patients into different risk groups. The prognostic value of imaging-based stratification was evaluated in relation to clinical-pathologic factors with multivariable Cox regression. Results Three intratumoral subregions with high, intermediate, and low MR perfusion were identified and showed high consistency between the two cohorts. Patients in both cohorts were stratified according to network analysis of multiregional image features regarding RFS (log-rank test, P = .002 for both). Aggressive tumors were associated with a larger volume of the poorly perfused subregion as well as interaction between poorly and moderately perfused subregions and surrounding parenchyma. At multivariable analysis, the proposed MSI-based marker was independently associated with RFS (hazard ratio: 3.42; 95% confidence interval: 1.55, 7.57; P = .002) adjusting for age, estrogen receptor (ER) status, progesterone receptor status, human epidermal growth factor receptor type 2 (HER2) status, tumor volume, and pathologic complete response (pCR). Furthermore, imaging helped stratify patients for RFS within the ER-positive and HER2-positive subgroups (log-rank test, P = .007 and .004) and among patients without pCR after neoadjuvant chemotherapy (log-rank test, P = .003). Conclusion Breast cancer consists of multiple spatially distinct subregions. Imaging heterogeneity is an independent prognostic factor beyond traditional risk predictors.
Background:
Adjuvant chemotherapy after surgery improves survival of patients with stage II-III, resectable gastric cancer. However, the overall survival benefit observed after adjuvant chemotherapy is moderate, suggesting that not all patients with resectable gastric cancer treated with adjuvant chemotherapy benefit from it. We aimed to develop and validate a predictive test for adjuvant chemotherapy response in patients with resectable, stage II-III gastric cancer.
Methods:
In this multi-cohort, retrospective study, we developed through a multi-step strategy a predictive test consisting of two rule-based classifier algorithms with predictive value for adjuvant chemotherapy response and prognosis. Exploratory bioinformatics analyses identified biologically relevant candidate genes in gastric cancer transcriptome datasets. In the discovery analysis, a four-gene, real-time RT-PCR assay was developed and analytically validated in formalin-fixed, paraffin-embedded (FFPE) tumour tissues from an internal cohort of 307 patients with stage II-III gastric cancer treated at the Yonsei Cancer Center with D2 gastrectomy plus adjuvant fluorouracil-based chemotherapy (n=193) or surgery alone (n=114). The same internal cohort was used to evaluate the prognostic and chemotherapy response predictive value of the single patient classifier genes using associations with 5-year overall survival. The results were validated with a subset (n=625) of FFPE tumour samples from an independent cohort of patients treated in the CLASSIC trial (NCT00411229), who received D2 gastrectomy plus capecitabine and oxaliplatin chemotherapy (n=323) or surgery alone (n=302). The primary endpoint was 5-year overall survival.
Findings:
We identified four classifier genes related to relevant gastric cancer features (GZMB, WARS, SFRP4, and CDX1) that formed the single patient classifier assay. In the validation cohort, the prognostic single patient classifier (based on the expression of GZMB, WARS, and SFRP4) identified 79 (13%) of 625 patients as low risk, 296 (47%) as intermediate risk, and 250 (40%) as high risk, and 5-year overall survival for these groups was 83·2% (95% CI 75·2-92·0), 74·8% (69·9-80·1), and 66·0% (60·1-72·4), respectively (p=0·012). The predictive single patient classifier (based on the expression of GZMB, WARS, and CDX1) assigned 281 (45%) of 625 patients in the validation cohort to the chemotherapy-benefit group and 344 (55%) to the no-benefit group. In the predicted chemotherapy-benefit group, 5-year overall survival was significantly improved in those patients who had received adjuvant chemotherapy after surgery compared with those who received surgery only (80% [95% CI 73·5-87·1] vs 64·5% [56·8-73·3]; univariate hazard ratio 0·47 [95% CI 0·30-0·75], p=0·0015), whereas no such improvement in 5-year overall survival was observed in the no-benefit group (72·9% [66·5-79·9] in patients who received chemotherapy plus surgery vs 72·5% [65·8-79·9] in patients who only had surgery; 0·93 [0·62-1·38], p=0·71). The predictive single patient classifier groups (chemotherapy benefit vs no-benefit) could predict adjuvant chemotherapy benefit in terms of 5-year overall survival in the validation cohort (pinteraction=0·036 in univariate analysis). Similar results were obtained in the internal evaluation cohort.
Interpretation:
The single patient classifiers validated in this study provide clinically important prognostic information independent of standard risk-stratification methods and predicted chemotherapy response after surgery in two independent cohorts of patients with resectable, stage II-III gastric cancer. The single patient classifiers could complement TNM staging to optimise decision making in patients with resectable gastric cancer who are eligible for adjuvant chemotherapy after surgery. Further validation of these results in prospective studies is warranted.
Funding:
Ministry of ICT and Future Planning; Ministry of Trade, Industry, and Energy; and Ministry of Health and Welfare.
Data augmentation, a technique in which a training set is expanded with class-preserving transformations, is ubiquitous in modern machine learning pipelines. In this paper, we seek to establish a theoretical framework for understanding modern data augmentation techniques. We start by showing that for kernel classifiers, data augmentation can be approximated by first-order feature averaging and second-order variance regularization components. We connect this general approximation framework to prior work in invariant kernels, tangent propagation, and robust optimization. Next, we explicitly tackle the compositional aspect of modern data augmentation techniques, proposing a novel model of data augmentation as a Markov process. Under this model, we show that performing $k$-nearest neighbors with data augmentation is asymptotically equivalent to a kernel classifier. Finally, we illustrate ways in which our theoretical framework can be leveraged to accelerate machine learning workflows in practice, including reducing the amount of computation needed to train on augmented data, and predicting the utility of a transformation prior to training.
In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels. While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that can be applied to a variety of tasks. Despite the apparent simplicity of global average pooling, we are able to achieve 37.1% top-5 error for object localization on ILSVRC 2014, which is remarkably close to the 34.2% top-5 error achieved by a fully supervised CNN approach. We demonstrate that our network is able to localize the discriminative image regions on a variety of tasks despite not being trained for them
In this work, we revisit the global average pooling layer proposed in [13],
and shed light on how it explicitly enables the convolutional neural network to
have remarkable localization ability despite being trained on image-level
labels. While this technique was previously proposed as a means for
regularizing training, we find that it actually builds a generic localizable
deep representation that can be applied to a variety of tasks. Despite the
apparent simplicity of global average pooling, we are able to achieve 37.1%
top-5 error for object localization on ILSVRC 2014, which is remarkably close
to the 34.2% top-5 error achieved by a fully supervised CNN approach. We
demonstrate that our network is able to localize the discriminative image
regions on a variety of tasks despite not being trained for them
Deeper neural networks are more difficult to train. We present a residual
learning framework to ease the training of networks that are substantially
deeper than those used previously. We explicitly reformulate the layers as
learning residual functions with reference to the layer inputs, instead of
learning unreferenced functions. We provide comprehensive empirical evidence
showing that these residual networks are easier to optimize, and can gain
accuracy from considerably increased depth. On the ImageNet dataset we evaluate
residual nets with a depth of up to 152 layers---8x deeper than VGG nets but
still having lower complexity. An ensemble of these residual nets achieves
3.57% error on the ImageNet test set. This result won the 1st place on the
ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100
and 1000 layers.
The depth of representations is of central importance for many visual
recognition tasks. Solely due to our extremely deep representations, we obtain
a 28% relative improvement on the COCO object detection dataset. Deep residual
nets are foundations of our submissions to ILSVRC & COCO 2015 competitions,
where we also won the 1st places on the tasks of ImageNet detection, ImageNet
localization, COCO detection, and COCO segmentation.
Interferon-γ (IFN-γ), the sole member in type II IFN predominantly secreted by macrophages and T cells, is a critical regulator of immune function and provides a robust first line of defense against invading pathogens. Binding of IFN-γ to its receptor complex can activate a variety of downstream signaling pathways, particularly the Janus kinase (JAK)/signal transducer and activator of transcription (STAT), to induce gene transcription within the target cells. This pro-inflammatory mediator is highly expressed in atherosclerotic lesions and promotes foam cell formation, but its effects on the atherogenesis are complex, with both pro- and anti-atherogenic properties. IFN-γ also contributes to the development of myocardial infarction and stroke, the two main atherosclerotic diseases. Inhibition of IFN-γ signaling may prevent the development of atherosclerosis and help treat atherosclerotic diseases. Since IFN-γ may also exert anti-atherogenic effects, the safety and efficacy of anti-IFN-γ treatment still require careful evaluation in the clinical setting. In the current review, we summarize recent progression on regulation and signaling pathways of IFN-γ, and highlight its roles in foam cell formation, atherosclerosis, myocardial infarction as well as stroke. An increased understanding of these processes will help to develop novel IFN-γ-centered therapies for atherosclerotic diseases.
Copyright © 2014. Published by Elsevier B.V.
Background/aims:
To determine whether the combination of tumor markers (CA72-4, CA125, CA19-9 and CEA) could increase the sensitivity and accuracy for in the diagnosis of gastric cancer (GC).
Methods:
This study is a retrospective analysis. A total of 426 patients, including 106 patients with GC, 149 patients with benign gastric diseases and 171 healthy people, who visited Zhejiang Xiaoshan Hospital from January 2011 to December 2013, were measured by serum markers, including CA72-4, CA125, CA19-9 and CEA. Statistical analyses including area under curve (AUC) of receiver operating characteristic (ROC) curve, and logistic regression analysis, were performed to evaluate the diagnostic value of these markers on GC.
Results:
Serum levels of CA72-4, CEA, CA125 and CA19-9 were higher in the GC group than those in the benign gastric disease group and the healthy control group (P<0.005). The sensitivities of CA72-4, CEA, CA125 and CA19-9 at the recommended cut-off level for all patients were 33.0%, 25.5%, 31.1% and 38.7%, respectively. However, when all four markers were used in combination the sensitivity increased to 66.0%. But by using an optimal cut-off value, the sensitivities of all four markers for the diagnosis of GC were improved. Especially the sensitivity of CEA increased to 73.6% and the sensitivity of the combination of the tumor markers increased to 75.5%. The age and gender had no effects on the diagnostic value of these markers.
Conclusions:
With the help of optimal cut-off values based on ROC curve and logistic regression analysis, the combination of these markers could improve the sensitivity for the diagnosis of GC based on common serum tumor markers.
"Radiomics" refers to the extraction and analysis of large amounts of advanced quantitative imaging features with high throughput from medical images obtained with computed tomography, positron emission tomography or magnetic resonance imaging. Importantly, these data are designed to be extracted from standard-of-care images, leading to a very large potential subject pool. Radiomics data are in a mineable form that can be used to build descriptive and predictive models relating image features to phenotypes or gene-protein signatures. The core hypothesis of radiomics is that these models, which can include biological or medical data, can provide valuable diagnostic, prognostic or predictive information. The radiomics enterprise can be divided into distinct processes, each with its own challenges that need to be overcome: (a) image acquisition and reconstruction, (b) image segmentation and rendering, (c) feature extraction and feature qualification and (d) databases and data sharing for eventual (e) ad hoc informatics analyses. Each of these individual processes poses unique challenges. For example, optimum protocols for image acquisition and reconstruction have to be identified and harmonized. Also, segmentations have to be robust and involve minimal operator input. Features have to be generated that robustly reflect the complexity of the individual volumes, but cannot be overly complex or redundant. Furthermore, informatics databases that allow incorporation of image features and image annotations, along with medical and genetic data, have to be generated. Finally, the statistical approaches to analyze these data have to be optimized, as radiomics is not a mature field of study. Each of these processes will be discussed in turn, as well as some of their unique challenges and proposed approaches to solve them. The focus of this article will be on images of non-small-cell lung cancer.
Serum tumor biomarker carbohydrate antigen 724 (CA724) is noticeable for gastric cancer. Correlation between CA724 and gastric cancer was investigated based on Chinese population. Chinese Biomedical Database, Chinese Journal Full-text Database and PubMed were searched. Gastric cancer patients were proven by biopsy, and control included health volunteers or benign gastric diseases. Participants received at least one test of CA724, CA125, CA153, CA199, CA242 or CEA. Meta-analysis, summary ROC (SROC) and post hoc analysis were performed by RevMan 5.0 and SPSS 11.5. Totally, 33 eligible studies were analyzed. Meta-analysis showed CA724 had the highest odds ratio 32.86 compared to control, orderly followed by CA242, CA199, CEA, CA125 and CA153. Accumulated accuracy rate of CA724 was 77 %, superior to others. In SROC analysis, specificity of all studies was above 0.70, but sensitivity of few studies was above 0.70; CA724 was selected as the preferable single test, followed by CA242, CA199, CEA, CA125 and CA153. If threshold of both specificity and sensitivity up to 0.70, CA153 was unacceptable; if up to 0.80, only CA724 and CA242 were considerable. In CA724-combined patterns, CA724+CEA+CA199 combination performed best by increasing sensitivity to 0.74 without impairing specificity, while CA724 + CA199 pattern was not a proper combination. CA724 was the most correlative serum tumor biomarker for gastric cancer in Chinese population. Sensitivity of serum CA724 is limited, but CA724+CEA+CA199 combination is considerable to improve sensitivity without impairing specificity.
A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data-labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This survey focuses on categorizing and reviewing the current progress on transfer learning for classification, regression, and clustering problems. In this survey, we discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift. We also explore some potential future issues in transfer learning research.
Multivariable regression models can link a potentially large number of variables to various kinds of outcomes, such as continuous, binary, or time-to-event endpoints. Selection of important variables and selection of the functional form for continuous covariates are key parts of building such models but are notoriously difficult due to several reasons. Caused by multicollinearity between predictors and a limited amount of information in the data, (in)stability can be a serious issue of models selected. For applications with a moderate number of variables, resampling-based techniques have been developed for diagnosing and improving multivariable regression models. Deriving models for high-dimensional molecular data has led to the need for adapting these techniques to settings where the number of variables is much larger than the number of observations. Three studies with a time-to-event outcome, of which one has high-dimensional data, are used to illustrate several techniques. Investigations at the covariate level and at the predictor level are seen to provide considerable insight into model stability and performance. While some areas are indicated where resampling techniques for model building still need further refinement, our case studies illustrate that these techniques can already be recommended for wider use.
Methods of evaluating and comparing the performance of diagnostic tests are of increasing importance as new tests are developed and marketed. When a test is based on an observed variable that lies on a continuous or graded scale, an assessment of the overall value of the test can be made through the use of a receiver operating characteristic (ROC) curve. The curve is constructed by varying the cutpoint used to determine which values of the observed variable will be considered abnormal and then plotting the resulting sensitivities against the corresponding false positive rates. When two or more empirical curves are constructed based on tests performed on the same individuals, statistical analysis on differences between curves must take into account the correlated nature of the data. This paper presents a nonparametric approach to the analysis of areas under correlated ROC curves, by using the theory on generalized U-statistics to generate an estimated covariance matrix.
To evaluate whether tumor markers can be used to assess response to systemic chemotherapy, we analyzed preliminarily the relationship between the response to chemotherapy based on serial imaging and on change in serum tumor marker level of CEA, CA19-9 and CA125.
We analyzed 26 patients with advanced gastric cancer in whom at least one of the tumor markers CEA, CA19-9 and CA125 was elevated before systemic chemotherapy with regard to the relationship between the change in serum tumor marker level and response assessment by imaging studies throughout the treatment course. A responder was defined as showing a > or = 50% drop in tumor marker level for more than 4 weeks.
The sensitivity and negative predictive value of falling tumor marker level after chemotherapy for a partial response in imaging was 100%. When patients were categorized as responders or non-responders, a significant correlation was observed between the assessment of response by tumor markers and by imaging studies. The survival time of responders assessed by tumor markers was significantly longer than that of non-responders.
The measurement of tumor markers might be useful in monitoring response and in predicting the prognosis of patients with advanced gastric cancer treated with systemic chemotherapy. Tumor markers may be used as a means of monitoring treatment in patients when in an imaging study it is difficult to assess response to chemotherapy in clinical practice. Further studies are required to confirm these findings.
Gastric cancer is still a major health problem and a leading cause of cancer mortality despite a worldwide decline in incidence. Environmental and Helicobacter pylori (Hp) acting early in life in a multistep and multifactorial process may cause intestinal type carcinomas, whereas genetic abnormalities are related more to the diffuse type of disease. Primarily due to early detection of the disease, the results of treatment for gastric cancer have improved in Japan, Korea and several specialized Western centres. Surgery offers excellent long-term survival results for early gastric cancer (EGC). Advances in diagnostic and treatment technology have contributed to a trend towards minimal invasive surgery such as endoscopic mucosal resection (EMR) and laparoscopic surgery for selected mucosal cancers.
Computed Tomography (CT) Perfusion as an early prognostic marker for treatment response to neoadjuvant chemotherapy in gastroesophageal junction cancer and gastric cancer-a prospective study
- C A Lauridsen
- E Falletin
- M L Hansen
- I Law
- B Federspiel
- L Bæksgaard
- L B Svendsen
- M B Nielsen
- CA Lauridsen
Diffusion kurtosis imaging in the prediction of poor responses of locally advanced gastric cancer to neoadjuvant chemotherapy-ScienceDirect
- F Jia
- T A Lei
- C Zyl
- A Xtl
- B Hfz
- A Yss
- C Jfj
AJCC Cancer Staging Manual
- Mbes Amin
- F Greene
PyTorch: an imperative style, high-performance deep learning library. Neural information processing systems
- B Steiner
- Z Devito
- S Chintala
- S Gross
- A Paszke
- F Massa
- A Lerer
- G Chanan
- Z Lin
Steiner B, Devito Z, Chintala S, Gross S, Paszke A, Massa F,
Lerer A, Chanan G, Lin Z, Yang E. PyTorch: an imperative style,
high-performance deep learning library. Neural information processing systems; 2019. p. 8026-37.
Prognostic value of deep learning PET/ CT-based radiomics: potential role for future individual induction chemotherapy in advanced nasopharyngeal carcinoma
- H Peng
- D Dong
- M-J Fang
- L Li
- L-L Tang
- Chen L Li
- W-F Mao
- Fan W Liu
Peng H, Dong D, Fang M-J, Li L, Tang L-L, Chen L, Li W-F,
Mao Y-P, Fan W, Liu L-Z. Prognostic value of deep learning PET/
CT-based radiomics: potential role for future individual induction chemotherapy in advanced nasopharyngeal carcinoma. Clin
Cancer Res. 2019;25(14):4271-9.
Predicting cancer outcomes from histology and genomics using convolutional networks
- P Mobadersany
- S Yousefi
- M Amgad
- D A Gutman
- J S Barnholtz-Sloan
- Jev Vega
- D J Brat
- L A Cooper
Mobadersany P, Yousefi S, Amgad M, Gutman DA, Barnholtz-Sloan JS, Vega JEV, Brat DJ, Cooper LA. Predicting cancer
outcomes from histology and genomics using convolutional networks. Proc Natl Acad Sci. 2018;115(13):E2970-9.