Anatomy of the cervix. Sagittal T2 Fat-sat shows the MRI anatomy of the...

Gene Expression Analysis for Uterine Cervix and Corpus Cancer Characterization

Article

Full-text available

Feb 2024

The analysis of gene expression quantification data is a powerful and widely used approach in cancer research. This work provides new insights into the transcriptomic changes that occur in healthy uterine tissue compared to those in cancerous tissues and explores the differences associated with uterine cancer localizations and histological subtypes. To achieve this, RNA-Seq data from the TCGA database were preprocessed and analyzed using the KnowSeq package. Firstly, a kNN model was applied to classify uterine cervix cancer, uterine corpus cancer, and healthy uterine samples. Through variable selection, a three-gene signature was identified (VWCE, CLDN15, ADCYAP1R1), achieving consistent 100% test accuracy across 20 repetitions of a 5-fold cross-validation. A supplementary similar analysis using miRNA-Seq data from the same samples identified an optimal two-gene miRNA-coding signature potentially regulating the three-gene signature previously mentioned, which attained optimal classification performance with an 82% F1-macro score. Subsequently, a kNN model was implemented for the classification of cervical cancer samples into their two main histological subtypes (adenocarcinoma and squamous cell carcinoma). A uni-gene signature (ICA1L) was identified, achieving 100% test accuracy through 20 repetitions of a 5-fold cross-validation and externally validated through the CGCI program. Finally, an examination of six cervical adenosquamous carcinoma (mixed) samples revealed a pattern where the gene expression value in the mixed class aligned closer to the histological subtype with lower expression, prompting a reconsideration of the diagnosis for these mixed samples. In summary, this study provides valuable insights into the molecular mechanisms of uterine cervix and corpus cancers. The newly identified gene signatures demonstrate robust predictive capabilities, guiding future research in cancer diagnosis and treatment methodologies.

Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study

Article

Full-text available

Feb 2024

Objectives To develop and validate a magnetic resonance imaging-based (MRI) deep multiple instance learning (D-MIL) model and combine it with clinical parameters for preoperative prediction of lymph node metastasis (LNM) in operable cervical cancer. Methods A total of 392 patients with cervical cancer were retrospectively enrolled. Clinical parameters were analysed by logistical regression to construct a clinical model (M1). A ResNet50 structure is applied to extract features at the instance level without using manual annotations about the tumour region and then construct a D-MIL model (M2). A hybrid model (M3) was constructed by M1 and M2 scores. The diagnostic performance of each model was evaluated by the area under the receiver operating characteristic curve (AUC) and compared using the Delong method. Disease-free survival (DFS) was evaluated by the Kaplan‒Meier method. Results SCC-Ag, maximum lymph node short diameter (LN max ), and tumour volume were found to be independent predictors of M1 model. For the diagnosis of LNM, the AUC of the training/internal/external cohort of M1 was 0.736/0.690/0.732, the AUC of the training/internal/external cohort of M2 was 0.757/0.714/0.765, and the AUC of the training/internal/external cohort of M3 was 0.838/0.764/0.835. M3 showed better performance than M1 and M2. Through the survival analysis, patients with higher hybrid model scores had a shorter time to reach DFS. Conclusion The proposed hybrid model could be used as a personalised non-invasive tool, which is helpful for predicting LNM in operable cervical cancer. The score of the hybrid model could also reflect the DFS of operable cervical cancer. Critical relevance statement Lymph node metastasis is an important factor affecting the prognosis of cervical cancer. Preoperative prediction of lymph node status is helpful to make treatment decisions, improve prognosis, and prolong survival time. Key points • The MRI-based deep-learning model can predict the LNM in operable cervical cancer. • The hybrid model has the highest diagnostic efficiency for the LNM prediction. • The score of the hybrid model can reflect the DFS of operable cervical cancer. Graphical Abstract

Automated Prediction of Neoadjuvant Chemoradiotherapy Response in Locally Advanced Cervical Cancer Using Hybrid Model-Based MRI Radiomics

Article

Full-text available

Dec 2023

Background: This study aimed to develop a model that automatically predicts the neoadjuvant chemoradiotherapy (nCRT) response for patients with locally advanced cervical cancer (LACC) based on T2-weighted MR images and clinical parameters. Methods: A total of 138 patients were enrolled, and T2-weighted MR images and clinical information of the patients before treatment were collected. Clinical information included age, stage, pathological type, squamous cell carcinoma (SCC) level, and lymph node status. A hybrid model extracted the domain-specific features from the computational radiomics system, the abstract features from the deep learning network, and the clinical parameters. Then, it employed an ensemble learning classifier weighted by logistic regression (LR) classifier, support vector machine (SVM) classifier, K-Nearest Neighbor (KNN) classifier, and Bayesian classifier to predict the pathologic complete response (pCR). The area under the receiver operating characteristics curve (AUC), accuracy (ACC), true positive rate (TPR), true negative rate (TNR), and precision were used as evaluation metrics. Results: Among the 138 LACC patients, 74 were in the pCR group, and 64 were in the non-pCR group. There was no significant difference between the two cohorts in terms of tumor diameter (p = 0.787), lymph node (p = 0.068), and stage before radiotherapy (p = 0.846), respectively. The 109-dimension domain features and 1472-dimension abstract features from MRI images were used to form a hybrid model. The average AUC, ACC, TPR, TNR, and precision of the proposed hybrid model were about 0.80, 0.71, 0.75, 0.66, and 0.71, while the AUC values of using clinical parameters, domain-specific features, and abstract features alone were 0.61, 0.67 and 0.76, respectively. The AUC value of the model without an ensemble learning classifier was 0.76. Conclusions: The proposed hybrid model can predict the radiotherapy response of patients with LACC, which might help radiation oncologists create personalized treatment plans for patients.

Application of Machine Learning for Prognostic Prediction in early-stage Cervical Cancer, Based on radiomics from ultrasound and MRI

Preprint

Full-text available

Dec 2023

Purpose: We aimed to develop a model for an early-stage cervical cancer for disease free survival (DFS) prediction using machine learning methods based on the combination of clinicopathological and radiomic features which is extracted from magnetic resonance imaging (MRI) and ultrasonography (US). Methods: This retrospectively study included 144 patients who were randomly divided into training and testing cohort at a ratio of 6:4.Radiomic features were extracted from MRI and US images, and in total, 1180 radiomic features and 9 clinicopathological factors were obtained. Six supervised machine learning classifiers were used to assess the prediction performance based on all variables. Next, we established models based on various combinations of clinicopathological characteristic and radiomic features to get the best prediction model using LightGBM. The model’s performance was evaluated by accuracy (ACC) and area under the curve (AUC). Furthermore, unsupervised clustering analysis was performed to identify CC patient subgroups related to DFS prognosis based on the all variables. Results: LightGBM was superior to any other classifiers in CC DFS prediction. The model that combined clinicopathological factors with radiomic features from MRI and US showed the best performance, and the corresponding values were 0.92 of ACC and 0.86 of AUC. Unsupervised clustering analysis identified a strong tendency toward the formation of two distinct groups in DFS rate among CC patients. Conclusion: MRI and US based radiomics has the potential of DFS prediction in early-stage CC with the LightGBM classifier, and the use of predictive algorithms may facilitate the personalized treatment options.

Comparison of the diagnostic value of [68 Ga]Ga-FAPI-04 PET/MR and [18F]FDG PET/CT in patients with T stage ≤ 2a2 uterine cervical cancer: a prospective study

Article

Full-text available

Nov 2023
EUR J NUCL MED MOL I

To compare the diagnostic value of [68 Ga]Ga-FAPI-04 PET/MR and [18F]FDG PET/CT in patients with T stage ≤ 2a2 uterine cervical cancer patients. Patients pathologically diagnosed with cervical cancer and with a T stage ≤ T2a2 were prospectively enrolled. All patients underwent whole-body [68 Ga]Ga-FAPI-04 PET/MR and [18F]FDG PET/CT within 2 weeks, and surgical treatment was performed within 10 days after PET. Twenty-five patients were enrolled. Twenty patients underwent radical hysterectomy, among which all of them underwent pelvic lymphadenectomy, and 10 patients underwent para-aortic lymphadenectomy. Three patients received merely laparoscopic lymphadenectomy without hysterectomy. Two patients with both [18F]FDG and [68 Ga]Ga-FAPI-04 lymph node high metabolism were staged as FIGO IIIC1r, and concurrent chemoradiation therapy (CCRT) was performed. [18F]FDG and [68 Ga]Ga-FAPI-04 had equivalent detection ability on primary tumors, with a positive detection rate of 96.0%. The accuracy of T staging using [18F]FDG and [68 Ga]Ga-FAPI-04 was relatively 50% and 55.0%. Elevated and underrated staging was due to misdiagnosis of either vaginal infiltration or tumor size. In terms of lymph node metastasis detection, the specificity of [68 Ga]Ga-FAPI-04 was 100% (95% CI, 84.6% ~ 100.0%), which was significantly higher than [18F]FDG (59.1% (95% CI, 36.4% ~ 79.3%)) (p = 0.004). [68 Ga]Ga-FAPI-04 PET/MR and [18F]FDG PET/CT demonstrated an equivalent detection ability on cervical cancer primary tumors. However, [68 Ga]Ga-FAPI-04 PET/MR’s diagnostic value in lymph node metastasis was significantly higher than [18F]FDG PET/CT. [68 Ga]Ga-FAPI-04 PET/MR has the potential for more accurate treatment planning, thus clarifying fertility preservation indications for early-stage young patients.

An MRI radiomics-based model for the prediction of invasion of the lymphovascular space in patients with cervical cancer

Preprint

Full-text available

Nov 2023

Background Cervical cancer (CC) remains the second deadliest cancer-associated cause of mortality among women, and the ability to adequately predict the presence or absence of lymphovascular space invasion (LVSI) is vital to ensuring optimal patient outcomes. The objective of this study was to establish and verify an MRI radiomics-based model for the purpose of predicting the status of LVSI in patients with CC. Methods The present study conducted a retrospective analysis, wherein a total of 86 patients were included in the training cohort, and 38 patients were involved in the testing group, specifically focusing on patients with CC. The radiomics feature extraction process involved the utilization of ADC, T2WI-SPAIR, and T2WI sequences. Training group data were utilized for initial radionics-based model development, and model predictive performance was then validated based on data for patients enrolled in the experimental group. Results Radiomics scoring model construction was performed using 17 selected features. The study identified several risk variables associated with LVSI. These risk factors included elevated combined sequence-based radiomics scores (P < 0.001), more advanced FIGO staging (P = 0.03), cervical stromal invasion depth of a minimum of 1/2 (P = 0.02), and poorer tumor differentiation (P < 0.001). Radiomics scores based on combined sequences, ADC, T2WI-SPAIR, and T2WI exhibited AUCs of 0.931, 0.839, 0.815, 0.698, and 0.739 in the training cohort, respectively, with corresponding testing cohort values of 0.725, 0.692, 0.683, 0.833, and 0.854. The calibration curve analyses demonstrated an enhanced level of agreement between the actual and predicted LVSI status, indicating excellent consistency. Furthermore, the results of the decision curve study provided evidence for the clinical utility of this prediction model. Conclusions An MRI radiomics model was successfully developed and validated as a tool capable of predicting CC patient LVSI status, achieving high levels of overall diagnostic accuracy.

Prognostic value of F-FDG PET in uterine cervical cancer patients with stage IIICr allocated by imaging

Article

Full-text available

Nov 2023

The effect on survival of radiographic lymph node metastasis in uterine cervical cancer patients is more important than before, even though its prognostic value not been well investigated. The aim of our study is to evaluate the prognostic potential of ¹⁸F-fluorodeoxyglucose Positron Emission Tomography (¹⁸F-FDG PET) compared with Computed Tomography (CT) in uterine cervical cancer patients with stage IIICr allocated by imaging. Fifty-five patients with biopsy-proven primary cervical cancer underwent definitive radiation therapy for stages IIB–IVB of The International Federation of Gynecology and Obstetrics (FIGO) 2018 classifications. The prognostic performance of pretreatment ¹⁸F-FDG PET and CT for assessing lymph node metastasis was evaluated by two experienced readers. The PET and CT findings were correlated with the risk of progression-free survival (PFS) and overall survival (OS). Kaplan–Meier survival curves showed that PFS was significantly worse in patients with positive lymph nodes on ¹⁸F-FDG PET than in those patients with negative lymph nodes on ¹⁸F-FDG PET (p = 0.003), whereas there was no significant difference in PFS between patients with lymph nodes sized ≥ 1 cm and those sized < 1 cm (p = 0.140). Univariate analysis showed that positive lymph nodes on ¹⁸F-FDG PET was significantly associated with poor PFS (p = 0.006), whereas lymph node size was not significantly associated with poor PFS (p = 0.145). In multivariate analysis, positive lymph nodes on ¹⁸F-FDG PET was significantly associated with poor PFS (p = 0.006) and was an independent prognostic factor for PFS. ¹⁸F-FDG PET offers high prognostic value for patients with stage IIICr allocated by imaging compared with CT, suggesting that ¹⁸F-FDG PET might be useful in clinical staging decisions and thus promote optimal diagnostic and therapeutic strategies.

Gynecologic oncology tumor board: the central role of the radiologist

Article

Full-text available

Jun 2023

This manuscript is a collaborative, multi-institutional effort by members of the Society of Abdominal Radiology Uterine and Ovarian Cancer Disease Focus Panel and the European Society of Urogenital Radiology Women Pelvic Imaging working group. The manuscript reviews the key role radiologists play at tumor board and highlights key imaging findings that guide management decisions in patients with the most common gynecologic malignancies including ovarian cancer, cervical cancer, and endometrial cancer.

Automated Prediction of Radiotherapy Sensitivity Using Hybrid Model-Based MRI Radiomics in Locally Advanced Cervical Cancer

Preprint

Full-text available

Jun 2023

Background To develop a model that could automatically predict radiotherapy sensitivity for patients with locally advanced cervical cancer (LACC) based on T2-weighted MR images and clinical parameters. Methods: A total of 138 patients were enrolled, T2-weighted MR images and clinical information of the patients before treatment were collected. Clinical information includes age, stage, pathological type, squamous cell carcinoma (SCC) level, and lymph node status. A hybrid model extracted the domain specific features from computational radiomics system, the abstract features from deep learning network and the clinical parameters, and employed an ensemble learning classifier weighted by logistic regression (LR) classifier, support vector machine (SVM) classifier, K-Nearest Neighbor (KNN) classifier and Bayesian classifier to predict pathologic complete response (pCR).The area under the receiver operating characteristics curve (AUC), accuracy (ACC), true positive rate (TPR), true negative rate (TNR) and precision were used as evaluation metrics. Results: Among 138 LACC patients, 74 were in the pCR group and 64 were in the non-pCR group. There was no significant difference between the two cohorts in terms of tumor diameter, lymph node and stage before radiotherapy, p = 0.787, 0.068, 0.846, respectively. The 109-dimension domain features and 1472-dimension abstract features from MRI image were selected to use for forming hybrid model. The average AUC, ACC, TPR, TNR and precision of the proposed hybrid model was about 0.80, 0.71, 0.75, 0.66 and 0.71, while The AUC values of using clinical parameters, domain specific features, abstract features alone were 0.61, 0.67 and 0.76, respectively. The AUC value of model without ensemble learning classifier was 0.76. Conclusions: The proposed hybrid model could predict well radiotherapy sensitivity of patients with LACC, which might help radiation oncologist to make personalized treatment plans for patients.

Construction of refined staging classification systems integrating FIGO/T-categories and corpus uterine invasion for non-metastatic cervical cancer

Article

Full-text available

Jun 2023

Background: To investigate the prognostic value of corpus uterine invasion (CUI) in cervical cancer (CC), and determine the necessity to incorporate it for staging. Methods: A total of 809 cases of biopsy-proven, non-metastatic CC were identified from an academic cancer center. Recursive partitioning analysis (RPA) method was used to develop the refined staging systems with respect to overall survival (OS). Internal validation was performed by using calibration curve with 1000 bootstrap resampling. Performances of the RPA-refined stages were compared against the conventional FIGO 2018 and 9th edition TNM-stage classifications by the receiver operating characteristic curve (ROC) and decision curve analysis (DCA). Results: We identified that CUI was independently prognostic for death and relapse in our cohort. RPA modeling using a two-tiered stratification by CUI (positive and negative) and FIGO/T-categories divided CC into three risk groupings (FIGO I'-III'/T1'-3'), with 5-year OS of 90.8%, 82.1%, and 68.5% for proposed FIGO stage I'-III', respectively (p ≤ 0.003 for all pairwise comparisons), and 89.7%, 78.8%, and 68.0% for proposed T1'-3', respectively (p < 0.001 for all pairwise comparisons). The RPA-refined staging systems were well validated with RPA-predicted OS rates showed optimal agreement with actual observed survivals. Additionally, the RPA-refined stages outperformed the conventional FIGO/TNM-stage with significantly higher accuracy of survival prediction (AUC: RPA-FIGO vs. FIGO, 0.663 [95% CI 0.629-0.695] vs. 0.638 [0.604-0.671], p = 0.047; RPA-T vs. T, 0.661 [0.627-0.694] vs. 0.627 [0.592-0.660], p = 0.036). Conclusion: CUI affects the survival outcomes in patients with CC. Disease extended to corpus uterine should be classified as stage III/T3.

Citations