FIG 1 - uploaded by Chong Hyun Suh
Content may be subject to copyright.
Source publication
Background:
Accurate diagnosis of high-grade glioma and solitary brain metastasis is clinically important because it affects the patient's outcome and alters patient management.
Purpose:
To evaluate the diagnostic performance of DWI and DTI for differentiating high-grade glioma from solitary brain metastasis.
Data sources:
A literature search...
Contexts in source publication
Context 1
... detailed literature-selection process is illustrated in Fig 1. The literature search identified 215 articles. After we removed 54 du- plicate articles, screening of the titles and abstracts of the remain- ing 161 articles yielded 44 potentially eligible articles. Full-text reviews were performed, and 30 studies were excluded because of the following: 1) twelve studies because the 2 2 table could not be obtained [29][30][31][32][33][34][35][36][37][38][39][40] ; 2) seven studies not in the field of interest 41-47 ; 3) five studies with a partially overlapping patient cohort 48-52 ; 4) four studies with mixed brain tumors 53-56 ; 5) one study with a low-grade glioma 57 ; and 6) one case series. 58 Fourteen studies evaluating the diagnostic performance of DWI and DTI for dif- ferentiating high-grade glioma from solitary brain metastasis, 3-16 covering 1143 patients, were included in the ...
Context 2
... results of the quality assessment are illustrated in On-line Fig 1. In the pa- tient-selection domain, 10 studies re- vealed an unclear risk of bias because of nonconsecutive enrollment. 3,[5][6][7]9,[11][12][13][14][15] In the index test domain, 6 studies re- vealed an unclear risk of bias because it was unclear whether imaging analysis had been conducted blinded to the ref- erence standard. 3,5,7,9,15,16 In the refer- ence standard domain, 2 studies re- vealed a high risk of bias, with 1 study not mentioning the reference standard 6 and 1 study using both histopathology and clinical diagnosis. 14 In the flow and timing domain, 13 studies revealed an unclear risk of bias because the time intervals between MR imaging and the reference standard were not men- tioned. 3,4,6-16 However, there were no concerns regarding the applicability of all 3 ...
Context 3
... study has several limitations. First, only 21.4% (3 of 14) of the included studies were prospective. 5,13,16 However, the in- cluded studies are the only currently available ones. Second, we combined the MR imaging techniques used for diagnostic perfor- mance (ie, DWI and DTI). Third, the included studies used vari- ous parameters. However, we demonstrated the absence of heter- ogeneity across the included studies. In addition, we also performed multiple subgroup analyses. Furthermore, we con- ducted this study using robust methodology (hierarchic logistic regression modeling 23 ) and have reported the results in accor- dance with several guidelines (PRISMA, 21 the Handbook for Di- agnostic Test Accuracy Reviews published by the Cochrane Col- laboration, 62 and the Agency for Healthcare Research and Quality 63 ). Nevertheless, caution is required in applying our re- sults to daily clinical ...
Context 4
... detailed literature-selection process is illustrated in Fig 1. The literature search identified 215 articles. ...
Context 5
... results of the quality assessment are illustrated in On-line Fig 1. In the pa- tient-selection domain, 10 studies re- vealed an unclear risk of bias because of nonconsecutive enrollment. ...
Similar publications
Pediatric glioblastoma multiforme (GBM) involving the spine is an aggressive tumor with a poor quality of life for patients. Despite this, there is only a limited number of reports describing the outcomes of pediatric spinal GBMs, both as primary spinal GBMs and metastases from an intracranial tumor. Here, we performed an individual patient meta-an...
Citations
... 2 Hemodynamic imaging-derived measurements have shown high sensitivity and specificity, particularly those derived from dynamic susceptibility contrast (DSC), dynamic contrast-enhanced (DCE), and arterial spin labeling (ASL) sequences, for differentiating HGGs from BMs, lymphomas, and nonneoplastic lesions. 8,9 Using conventional MRI sequences, HGGs and BMs have similar appearances, both having surrounding edema, necrotic centers, and irregular enhancing margins, 2,10 and conventional MRI is therefore prone to misclassification. 2 Consequently, previous studies have used advanced techniques including perfusion-weighted imaging, 6,7,[11][12][13][14] cerebral blood volume (CBV), cerebral blood flow (CBF), diffusion-weighted imaging (DWI), 13,15 diffusion tensor imaging, [15][16][17] a combination of perfusion and diffusion metrics, 16 MR spectroscopy, 11 texture analysis, 2 quantitative diagnosis, 18 and machine learning 10,19 approaches to differentiate between HGGs and BMs. ...
... 2 Hemodynamic imaging-derived measurements have shown high sensitivity and specificity, particularly those derived from dynamic susceptibility contrast (DSC), dynamic contrast-enhanced (DCE), and arterial spin labeling (ASL) sequences, for differentiating HGGs from BMs, lymphomas, and nonneoplastic lesions. 8,9 Using conventional MRI sequences, HGGs and BMs have similar appearances, both having surrounding edema, necrotic centers, and irregular enhancing margins, 2,10 and conventional MRI is therefore prone to misclassification. 2 Consequently, previous studies have used advanced techniques including perfusion-weighted imaging, 6,7,[11][12][13][14] cerebral blood volume (CBV), cerebral blood flow (CBF), diffusion-weighted imaging (DWI), 13,15 diffusion tensor imaging, [15][16][17] a combination of perfusion and diffusion metrics, 16 MR spectroscopy, 11 texture analysis, 2 quantitative diagnosis, 18 and machine learning 10,19 approaches to differentiate between HGGs and BMs. ...
Background
Distinguishing high-grade gliomas (HGGs) from brain metastases (BMs) using perfusion-weighted imaging (PWI) remains challenging. PWI offers quantitative measurements of cerebral blood flow (CBF) and cerebral blood volume (CBV), but optimal PWI parameters for differentiation are unclear.
Purpose
To compare CBF and CBV derived from PWIs in HGGs and BMs, and to identify the most effective PWI parameters and techniques for differentiation.
Study Type
Systematic review and meta-analysis.
Population
Twenty-four studies compared CBF and CBV between HGGs (n = 704) and BMs (n = 488).
Field Strength/Sequence
Arterial spin labeling (ASL), dynamic susceptibility contrast (DSC), dynamic contrast-enhanced (DCE), and dynamic susceptibility contrast-enhanced (DSCE) sequences at 1.5 T and 3.0 T.
Assessment
Following the PRISMA guidelines, four major databases were searched from 2000 to 2024 for studies evaluating CBF or CBV using PWI in HGGs and BMs.
Statistical Tests
Standardized mean difference (SMD) with 95% CIs was used. Risk of bias (ROB) and publication bias were assessed, and I2 statistic was used to assess statistical heterogeneity. A P-value<0.05 was considered significant.
Results
HGGs showed a significant modest increase in CBF (SMD = 0.37, 95% CI: 0.05–0.69) and CBV (SMD = 0.26, 95% CI: 0.01–0.51) compared with BMs. Subgroup analysis based on region, sequence, ROB, and field strength for CBF (HGGs: 375 and BMs: 222) and CBV (HGGs: 493 and BMs: 378) values were conducted. ASL showed a considerable moderate increase (50% overlapping CI) in CBF for HGGs compared with BMs. However, no significant difference was found between ASL and DSC (P = 0.08).
Data Conclusion
ASL-derived CBF may be more useful than DSC-derived CBF in differentiating HGGs from BMs. This suggests that ASL may be used as an alternative to DSC when contrast medium is contraindicated or when intravenous injection is not feasible.
... First, our results showed that DWI and DTI have limited ability to distinguish Gb and SBM and are considered appropriate as part of a multiparametric MRI protocol rather than as a single sequence to be combined with radiomics. A large meta-analysis also showed that DWI and DTI exhibited broad individual sensitivities and specificities and only a moderate diagnostic accuracy [34]. Unlike traditional diffusion MRI methods that offer limited information, NODDI provides a more nuanced characterization of brain tissue, including the density and orientation of neuronal fibers [16,17,35]. ...
Objectives
To evaluate the performance of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics in distinguishing between glioblastoma (Gb) and solitary brain metastasis (SBM).
Materials and methods
In this retrospective study, NODDI images were curated from 109 patients with Gb ( n = 57) or SBM ( n = 52). Automatically segmented multiple volumes of interest (VOIs) encompassed the main tumor regions, including necrosis, solid tumor, and peritumoral edema. Radiomics features were extracted for each main tumor region, using three NODDI parameter maps. Radiomics models were developed based on these three NODDI parameter maps and their amalgamation to differentiate between Gb and SBM. Additionally, radiomics models were constructed based on morphological magnetic resonance imaging (MRI) and diffusion imaging (diffusion-weighted imaging [DWI]; diffusion tensor imaging [DTI]) for performance comparison.
Results
The validation dataset results revealed that the performance of a single NODDI parameter map model was inferior to that of the combined NODDI model. In the necrotic regions, the combined NODDI radiomics model exhibited less than ideal discriminative capabilities (area under the receiver operating characteristic curve [AUC] = 0.701). For peritumoral edema regions, the combined NODDI radiomics model achieved a moderate level of discrimination (AUC = 0.820). Within the solid tumor regions, the combined NODDI radiomics model demonstrated superior performance (AUC = 0.904), surpassing the models of other VOIs. The comparison results demonstrated that the NODDI model was better than the DWI and DTI models, while those of the morphological MRI and NODDI models were similar.
Conclusion
The NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM.
Clinical relevance statement
The NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM, and radiomics features can be incorporated into the multidimensional phenotypic features that describe tumor heterogeneity.
Key Points
• The neurite orientation dispersion and density imaging (NODDI) radiomics model showed promising performance for preoperative discrimination between glioblastoma and solitary brain metastasis.
• Compared with other tumor volumes of interest, the NODDI radiomics model based on solid tumor regions performed best in distinguishing the two types of tumors.
• The performance of the single-parameter NODDI model was inferior to that of the combined-parameter NODDI model.
... Previous studies have reported progress in the ability of DWI and diffusion tensor imaging (DTI) to differentiate between GBM and SBM [26][27][28] [26]. DWI and DTI are better suited as part of a multiparametric MRI protocol than as single sequences [25]. ...
... Previous studies have reported progress in the ability of DWI and diffusion tensor imaging (DTI) to differentiate between GBM and SBM [26][27][28] [26]. DWI and DTI are better suited as part of a multiparametric MRI protocol than as single sequences [25]. ...
Background
We created discriminative models of different regions of interest (ROIs) using radiomic texture features of neurite orientation dispersion and density imaging (NODDI) and evaluated the feasibility of each model in differentiating glioblastoma multiforme (GBM) from solitary brain metastasis (SBM).
Methods
We conducted a retrospective study of 204 patients with GBM (n = 146) or SBM (n = 58). Radiomic texture features were extracted from five ROIs based on three metric maps (intracellular volume fraction, orientation dispersion index, and isotropic volume fraction of NODDI), including necrosis, solid tumors, peritumoral edema, tumor bulk volume (TBV), and abnormal bulk volume. Four feature selection methods and eight classifiers were used for the radiomic texture feature selection and model construction. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic performance of the models. Routine magnetic resonance imaging (MRI) radiomic texture feature models generated in the same manner were used for the horizontal comparison.
Results
NODDI-radiomic texture analysis based on TBV subregions exhibited the highest accuracy (although nonsignificant) in differentiating GBM from SBM, with area under the ROC curve (AUC) values of 0.918 and 0.882 in the training and test datasets, respectively, compared to necrosis (AUCtraining:0.845, AUCtest:0.714), solid tumor (AUCtraining:0.852, AUCtest:0.821), peritumoral edema (AUCtraining:0.817, AUCtest:0.762), and ABV (AUCtraining:0.834, AUCtest:0.779). The performance of the five ROI radiomic texture models in routine MRI was inferior to that of the NODDI-radiomic texture model.
Conclusion
Preoperative NODDI-radiomic texture analysis based on TBV subregions shows great potential for distinguishing GBM from SBM.
... According to a meta-analysis, however, the results of these studies are not entirely uniform and they report rather widely ranging sensitivity and specificity values (46-96% and 40-100%, respectively). (40). ...
... Fused images with PCA, DCHWT, LRD, and DDcGAN algorithms provided the significant RSCs difference between LGGs and HGGs. There is a consensus among studies that used ADC maps and SWI images for glioma grade classification 4,[9][10][11][12][13]16,17,23 . Interestingly, in fused images, RSCs in LGGs are significantly higher than HGGs with PCA, DCHWT, LRD, and DDcGAN algorithms. ...
Non-invasive glioma grade classification is an exciting area in neuroimaging. The primary purpose of this study is to investigate the performance of different medical image fusion algorithms for glioma grading purposes by fusing advanced Magnetic Resonance Imaging (MRI) images. Ninety-six subjects underwent an Apparent diffusion coefficient (ADC) map and Susceptibility-weighted imaging (SWI) MRI scan. After preprocessing, the different medical image fusion methods used to fuse ADC maps and SWI were Principal Component Analysis (PCA), Structure-Aware, Discrete Cosine Harmonic Wavelet Transform (DCHWT), Deep-Convolutional Neural network (DNN), Dual-Discriminator conditional generative adversarial network (DDcGAN), and Laplacian Re-Decomposition (LRD). The Entropy, standard deviation (STD), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Relative Signal Contrast (RSC) were calculated for qualitative and quantitative analysis. We found high fused image quality with LRD and DDcGAN methods. Further quantitative analysis showed that RSCs in fused images in Low-Grade glioma (LGG) were significantly higher than RSCs in High-Grade glioma (HGG) with PCA, DCHWT, LRD, and DDcGAN. The Receiver Operating Characteristic (ROC) curve test highlighted that LRD and DDcGAN have the highest performance for glioma grade classification. Our work suggests using the DDcGAN and LRD networks for glioma grade classification by fusing ADC maps and SWI images.
... Several attempts have been made to use the magnetic resonance imaging (MRI) modality for glioma grading as a non-invasive and fast method. Many studies have been published on the application of different MRI image weights, such as diffusion-weighted imaging (DWI) [6][7][8][9][10][11][12] , susceptibility-weighted imaging (SWI) 4,13-17 , perfusion-weighted imaging (PWI) [18][19][20] , and magnetic resonance spectroscopy (MRS) [21][22][23] for glioma grade classification. A fundamental problem with much of the literature on using single MRI image weights for glioma grading is the low accuracy of these methods. ...
... Fused images with PCA, DCHWT, LRD, and DDcGAN algorithms provided the significant RSCs difference between LGGs and HGGs. There is a consensus among studies that used ADC maps and SWI images for glioma grade classification 4,[9][10][11][12][13]16,17,23 . Interestingly, in fused images, RSCs in LGGs are significantly higher than HGGs with PCA, DCHWT, LRD, and DDcGAN algorithms. ...
Non-invasive glioma grade classification is an exciting area in neuroimaging. The primary purpose of this study is to investigate the performance of different medical image fusion algorithms for glioma grading purposes by fusing advanced Magnetic Resonance Imaging (MRI) images. Ninety-six subjects underwent an Apparent diffusion coefficient (ADC) map and Susceptibility-weighted imaging (SWI) MRI scan. After preprocessing, the different medical image fusion methods used to fuse ADC maps and SWI were Principal Component Analysis (PCA), Structure-Aware, Discrete Cosine Harmonic Wavelet Transform (DCHWT), Deep-Convolutional Neural network (DNN), Dual-Discriminator conditional generative adversarial network (DDcGAN), and Laplacian Re-Decomposition (LRD). The Entropy, standard deviation (STD), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Relative Signal Contrast (RSC) were calculated for qualitative and quantitative analysis. We found high fused image quality with LRD and DDcGAN methods. Further quantitative analysis showed that RSCs in fused images in Low-Grade glioma (LGG) were significantly higher than RSCs in High-Grade glioma (HGG) with PCA, DCHWT, LRD, and DDcGAN. The Receiver Operating Characteristic (ROC) curve test highlighted that LRD and DDcGAN have the highest performance for glioma grade classification. Our work suggests using the DDcGAN and LRD networks for glioma grade classification by fusing ADC maps and SWI images.
... The differential diagnosis between central nervous system (CNS) solitary-enhancing lesions, including high-grade gliomas (HGG) and brain metastasis, is still a challenge in common radiological practice [1]. Since both lesions may show similar morphological features on conventional MRI related to enhancement, necrosis, or vasogenic edema, the differential between HGG and solitary metastasis usually needs advanced MRI approaches [2]. In the last two decades, hundreds of papers have addressed the capability of advanced MRI sequences such as diffusion-weighted imaging (DWI), perfusion-weighted imaging (PWI), including dynamic susceptibility contrast (DSC) and dynamic contrast-enhanced (DCE), MR spectroscopy, arterial spin labeling (ASL), or amide proton transfer (APT) among others for this task [3][4][5]. ...
Objectives:
The differential between high-grade glioma (HGG) and metastasis remains challenging in common radiological practice. We compare different natural language processing (NLP)-based deep learning models to assist radiologists based on data contained in radiology reports.
Methods:
This retrospective study included 185 MRI reports between 2010 and 2022 from two different institutions. A total of 117 reports were used for the training and 21 were reserved for the validation set, while the rest were used as a test set. A comparison of the performance of different deep learning models for HGG and metastasis classification has been carried out. Specifically, Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), a hybrid version of BiLSTM and CNN, and a radiology-specific Bidirectional Encoder Representations from Transformers (RadBERT) model were used.
Results:
For the classification of MRI reports, the CNN network provided the best results among all tested, showing a macro-avg precision of 87.32%, a sensitivity of 87.45%, and an F1 score of 87.23%. In addition, our NLP algorithm detected keywords such as tumor, temporal, and lobe to positively classify a radiological report as HGG or metastasis group.
Conclusions:
A deep learning model based on CNN enables radiologists to discriminate between HGG and metastasis based on MRI reports with high-precision values. This approach should be considered an additional tool in diagnosing these central nervous system lesions.
Clinical relevance statement:
The use of our NLP model enables radiologists to differentiate between patients with high-grade glioma and metastasis based on their MRI reports and can be used as an additional tool to the conventional image-based approach for this challenging task.
Key points:
• Differential between high-grade glioma and metastasis is still challenging in common radiological practice. • Natural language processing (NLP)-based deep learning models can assist radiologists based on data contained in radiology reports. • We have developed and tested a natural language processing model for discriminating between high-grade glioma and metastasis based on MRI reports that show high precision for this task.
... MRI techniques that help differentiate between BM and HGG represent an active area of research, and significant improvements over conventional MRI techniques have been made in the last few years using spectroscopy, perfusion, and diffusion-weighted imaging techniques [8][9][10][11][12][13][14]. A major drawback of such techniques with respect to conventional MRI is the need for additional special imaging acquisitions that would have a negative impact on the procedural cost, patient convenience, and the time to get a diagnosis. ...
Solitary large brain metastases (LBM) and high-grade gliomas (HGG) are sometimes hard to differentiate on MRI. The management differs significantly between these two entities, and non-invasive methods that help differentiate between them are eagerly needed to avoid potentially morbid biopsies and surgical procedures. We explore herein the performance and interpretability of an MRI-radiomics variational quantum neural network (QNN) using a quantum-annealing mutual-information (MI) feature selection approach. We retrospectively included 423 patients with HGG and LBM (> 2 cm) who had a contrast-enhanced T1-weighted (CE-T1) MRI between 2012 and 2019. After exclusion, 72 HGG and 129 LBM were kept. Tumors were manually segmented, and a 5-mm peri-tumoral ring was created. MRI images were pre-processed, and 1813 radiomic features were extracted. A set of best features based on MI was selected. MI and conditional-MI were embedded into a quadratic unconstrained binary optimization (QUBO) formulation that was mapped to an Ising-model and submitted to D’Wave’s quantum annealer to solve for the best combination of 10 features. The 10 selected features were embedded into a 2-qubits QNN using PennyLane library. The model was evaluated for balanced-accuracy (bACC) and area under the receiver operating characteristic curve (ROC-AUC) on the test set. The model performance was benchmarked against two classical models: dense neural networks (DNN) and extreme gradient boosting (XGB). Shapley values were calculated to interpret sample-wise predictions on the test set. The best 10-feature combination included 6 tumor and 4 ring features. For QNN, DNN, and XGB, respectively, training ROC-AUC was 0.86, 0.95, and 0.94; test ROC-AUC was 0.76, 0.75, and 0.79; and test bACC was 0.74, 0.73, and 0.72. The two most influential features were tumor Laplacian-of-Gaussian-GLRLM-Entropy and sphericity. We developed an accurate interpretable QNN model with quantum-informed feature selection to differentiate between LBM and HGG on CE-T1 brain MRI. The model performance is comparable to state-of-the-art classical models.
... The FA range and FA maximum value can distinguish LGG from HGG, as LGG have a significantly lower value [47]. Distinguishing metastases from HGG is difficult on diffusion-weighted imaging; however, it was found that there is an increased FA peritumorally, and a significant decrease in the mean diffusivity (MD) in HGG compared to brain metastases, while intratumorally, no significant changes were seen [48][49][50]. Similarly, meningiomas showed a significantly higher FA and lower ADC compared to HGG [51]. ...
Alteration in the surrounding brain tissue may occur in the presence of a brain tumor. The present study aims to assess the characteristics and criteria of the pattern of white matter tract microstructure integrity alteration in brain tumor patients. The Scopus, PubMed/Medline, and Web of Science electronic databases were searched for related articles based on the guidelines established by PRISMA. Twenty-five studies were selected on the morphological changes of white matter tract integrity based on the differential classification of white matter tract (WMT) patterns in brain tumor patients through diffusion tensor imaging (DTI). The characterization was based on two criteria: the visualization of the tract—its orientation and position—and the DTI parameters, which were the fractional anisotropy and apparent diffusion coefficient. Individual evaluations revealed no absolute, mutually exclusive type of tumor in relation to morphological WMT microstructure integrity changes. In most cases, different types and grades of tumors have shown displacement or infiltration. Characterizing morphological changes in the integrity of the white matter tract microstructures is vital in the diagnostic and prognostic evaluation of the tumor’s progression and could be a potential assessment for the early detection of possible neurological defects that may affect the patient, as well as aiding in surgery decision-making.
... The movement of water in the extracellular space is also affected by increased cellularity, which is seen as a decline in ADC values (Guzman et al., 2008;Klimas et al., 2013). In some cases, however, even advanced MRI techniques, such as DWI and ADC, fail to differentiate pathologies characterized by perilesional edema that require different therapeutic approaches (Suh et al., 2018). Thus, it is more appropriate to focus on finding other possible methods of ADC map analysis to differentiate these brain pathologies. ...
Differential diagnosis of brain lesion pathologies is complex, but it is nevertheless crucial for appropriate clinical management. Advanced imaging methods, including diffusion-weighted imaging and apparent diffusion coefficient, can help discriminate between brain mass lesions such as glioblastoma, brain metastasis, brain abscesses as well as brain lymphomas. These pathologies are characterized by blood-brain barrier alterations and have been extensively studied. However, the changes in the blood-brain barrier that are observed around brain pathologies and that contribute to the development of vasogenic brain edema are not well described. Some infiltrative brain pathologies such as glioblastoma are characterized by glioma cell infiltration in the brain tissue around the tumor mass and thus affect the nature of the vasogenic edema. Interestingly, a common feature of primary and secondary brain tumors or tumor-like brain lesions characterized by vasogenic brain edema is the formation of various molecules that lead to alterations of tight junctions and result in blood-brain barrier damage. The resulting vasogenic edema, especially blood-brain barrier disruption, can be visualized using advanced magnetic resonance imaging techniques, such as diffusion-weighted imaging and apparent diffusion coefficient. This review presents a comprehensive overview of blood-brain barrier changes contributing to the development of vasogenic brain edema around glioblastoma, brain metastases, lymphomas, and abscesses.
