Dataset Information

Development of a Machine Learning Classifier Based on Radiomic Features Extracted From Post-Contrast 3D T1-Weighted MR Images to Distinguish Glioblastoma From Solitary Brain Metastasis.

ABSTRACT:

Objectives

To differentiate Glioblastomas (GBM) and Brain Metastases (BM) using a radiomic features-based Machine Learning (ML) classifier trained from post-contrast three-dimensional T1-weighted (post-contrast 3DT1) MR imaging, and compare its performance in medical diagnosis versus human experts, on a testing cohort.

Methods

We enrolled 143 patients (71 GBM and 72 BM) in a retrospective bicentric study from January 2010 to May 2019 to train the classifier. Post-contrast 3DT1 MR images were performed on a 3-Tesla MR unit and 100 radiomic features were extracted. Selection and optimization of the Machine Learning (ML) classifier was performed using a nested cross-validation. Sensitivity, specificity, balanced accuracy, and area under the receiver operating characteristic curve (AUC) were calculated as performance metrics. The model final performance was cross-validated, then evaluated on a test set of 37 patients, and compared to human blind reading using a McNemar's test.

Results

The ML classifier had a mean [95% confidence interval] sensitivity of 85% [77; 94], a specificity of 87% [78; 97], a balanced accuracy of 86% [80; 92], and an AUC of 92% [87; 97] with cross-validation. Sensitivity, specificity, balanced accuracy and AUC were equal to 75, 86, 80 and 85% on the test set. Sphericity 3D radiomic index highlighted the highest coefficient in the logistic regression model. There were no statistical significant differences observed between the performance of the classifier and the experts' blinded examination.

Conclusions

The proposed diagnostic support system based on radiomic features extracted from post-contrast 3DT1 MR images helps in differentiating solitary BM from GBM with high diagnosis performance and generalizability.

SUBMITTER: de Causans A

PROVIDER: S-EPMC8315001 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:We conducted a feasibility study to predict malignant glioma grades via radiomic analysis using contrast-enhanced T1-weighted magnetic resonance images (CE-T1WIs) and T2-weighted magnetic resonance images (T2WIs). We proposed a framework and applied it to CE-T1WIs and T2WIs (with tumor region data) acquired preoperatively from 157 patients with malignant glioma (grade III: 55, grade IV: 102) as the primary dataset and 67 patients with malignant glioma (grade III: 22, grade IV: 45) as the validation dataset. Radiomic features such as size/shape, intensity, histogram, and texture features were extracted from the tumor regions on the CE-T1WIs and T2WIs. The Wilcoxon-Mann-Whitney (WMW) test and least absolute shrinkage and selection operator logistic regression (LASSO-LR) were employed to select the radiomic features. Various machine learning (ML) algorithms were used to construct prediction models for the malignant glioma grades using the selected radiomic features. Leave-one-out cross-validation (LOOCV) was implemented to evaluate the performance of the prediction models in the primary dataset. The selected radiomic features for all folds in the LOOCV of the primary dataset were used to perform an independent validation. As evaluation indices, accuracies, sensitivities, specificities, and values for the area under receiver operating characteristic curve (or simply the area under the curve (AUC)) for all prediction models were calculated. The mean AUC value for all prediction models constructed by the ML algorithms in the LOOCV of the primary dataset was 0.902 ± 0.024 (95% CI (confidence interval), 0.873-0.932). In the independent validation, the mean AUC value for all prediction models was 0.747 ± 0.034 (95% CI, 0.705-0.790). The results of this study suggest that the malignant glioma grades could be sufficiently and easily predicted by preparing the CE-T1WIs, T2WIs, and tumor delineations for each patient. Our proposed framework may be an effective tool for preoperatively grading malignant gliomas.

Project description:IntroductionTo compare the diagnostic accuracy of contrast-enhanced 3D(dimensional) T1-weighted sampling perfection with application-optimized contrasts by using different flip angle evolutions (T1-SPACE), 2D fluid attenuated inversion recovery (FLAIR) images and 2D contrast-enhanced T1-weighted image in detection of leptomeningeal metastasis except for invasive procedures such as a CSF tapping.Materials and methodsThree groups of patients were included retrospectively for 9 months (from 2013-04-01 to 2013-12-31). Group 1 patients with positive malignant cells in CSF cytology (n = 22); group 2, stroke patients with steno-occlusion in ICA or MCA (n = 16); and group 3, patients with negative results on MRI, whose symptom were dizziness or headache (n = 25). A total of 63 sets of MR images are separately collected and randomly arranged: (1) CE 3D T1-SPACE; (2) 2D FLAIR; and (3) CE T1-GRE using a 3-Tesla MR system. A faculty neuroradiologist with 8-year-experience and another 2nd grade trainee in radiology reviewed each MR image- blinded by the results of CSF cytology and coded their observations as positives or negatives of leptomeningeal metastasis. The CSF cytology result was considered as a gold standard. Sensitivity and specificity of each MR images were calculated. Diagnostic accuracy was compared using a McNemar's test. A Cohen's kappa analysis was performed to assess inter-observer agreements.ResultsDiagnostic accuracy was not different between 3D T1-SPACE and CSF cytology by both raters. However, the accuracy test of 2D FLAIR and 2D contrast-enhanced T1-weighted GRE was inconsistent by the two raters. The Kappa statistic results were 0.657 (3D T1-SPACE), 0.420 (2D FLAIR), and 0.160 (2D contrast-enhanced T1-weighted GRE). The 3D T1-SPACE images showed the highest inter-observer agreements between the raters.ConclusionsCompared to 2D FLAIR and 2D contrast-enhanced T1-weighted GRE, contrast-enhanced 3D T1 SPACE showed a better detection rate of leptomeningeal metastasis.

Project description:Purpose: To examine the feasibility and potential difficulties of automatically generating radiologic reports (RRs) to articulate the clinically important features of brain magnetic resonance (MR) images. Materials and Methods: We focused on examining brain atrophy by using magnetization-prepared rapid gradient-echo (MPRAGE) images. The technology was based on multi-atlas whole-brain segmentation that identified 283 structures, from which larger superstructures were created to represent the anatomic units most frequently used in RRs. Through two layers of data-reduction filters, based on anatomic and clinical knowledge, raw images (~10 MB) were converted to a few kilobytes of human-readable sentences. The tool was applied to images from 92 patients with memory problems, and the results were compared to RRs independently produced by three experienced radiologists. The mechanisms of disagreement were investigated to understand where machine-human interface succeeded or failed. Results: The automatically generated sentences had low sensitivity (mean: 24.5%) and precision (mean: 24.9%) values; these were significantly lower than the inter-rater sensitivity (mean: 32.7%) and precision (mean: 32.2%) of the radiologists. The causes of disagreement were divided into six error categories: mismatch of anatomic definitions (7.2 ± 9.3%), data-reduction errors (11.4 ± 3.9%), translator errors (3.1 ± 3.1%), difference in the spatial extent of used anatomic terms (8.3 ± 6.7%), segmentation quality (9.8 ± 2.0%), and threshold for sentence-triggering (60.2 ± 16.3%). Conclusion: These error mechanisms raise interesting questions about the potential of automated report generation and the quality of image reading by humans. The most significant discrepancy between the human and automatically generated RRs was caused by the sentence-triggering threshold (the degree of abnormality), which was fixed to z-score >2.0 for the automated generation, while the thresholds by radiologists varied among different anatomical structures.

Project description:BackgroundThis study aimed to establish a dedicated deep-learning model (DLM) on routine magnetic resonance imaging (MRI) data to investigate DLM performance in automated detection and segmentation of meningiomas in comparison to manual segmentations. Another purpose of our work was to develop a radiomics model based on the radiomics features extracted from automatic segmentation to differentiate low- and high-grade meningiomas before surgery.MaterialsA total of 326 patients with pathologically confirmed meningiomas were enrolled. Samples were randomly split with a 6:2:2 ratio to the training set, validation set, and test set. Volumetric regions of interest (VOIs) were manually drawn on each slice using the ITK-SNAP software. An automatic segmentation model based on SegResNet was developed for the meningioma segmentation. Segmentation performance was evaluated by dice coefficient and 95% Hausdorff distance. Intra class correlation (ICC) analysis was applied to assess the agreement between radiomic features from manual and automatic segmentations. Radiomics features derived from automatic segmentation were extracted by pyradiomics. After feature selection, a model for meningiomas grading was built.ResultsThe DLM detected meningiomas in all cases. For automatic segmentation, the mean dice coefficient and 95% Hausdorff distance were 0.881 (95% CI: 0.851-0.981) and 2.016 (95% CI:1.439-3.158) in the test set, respectively. Features extracted on manual and automatic segmentation are comparable: the average ICC value was 0.804 (range, 0.636-0.933). Features extracted on manual and automatic segmentation are comparable: the average ICC value was 0.804 (range, 0.636-0.933). For meningioma classification, the radiomics model based on automatic segmentation performed well in grading meningiomas, yielding a sensitivity, specificity, accuracy, and area under the curve (AUC) of 0.778 (95% CI: 0.701-0.856), 0.860 (95% CI: 0.722-0.908), 0.848 (95% CI: 0.715-0.903) and 0.842 (95% CI: 0.807-0.895) in the test set, respectively.ConclusionsThe DLM yielded favorable automated detection and segmentation of meningioma and can help deploy radiomics for preoperative meningioma differentiation in clinical practice.

Project description:IntroductionTrigeminal ganglion contrast enhancement (TGCE) is reported to be a normal and a common finding on magnetic resonance imaging studies of dogs, cats and humans. The intent of the present study was to describe the anatomical characteristics of the trigeminal ganglion, its surrounding structures, and histological features that are relevant to explain or hypothesize on the reason for TGCE on T1-weighted post-contrast MRI studies of the brain in dogs.MethodsEight dog cadavers were dissected to study the anatomy of the trigeminal ganglion. The presence and anatomy of vessels was studied by dissection and by histological techniques. Two trigeminal ganglia were isolated and stained with hematoxylin-eosin (HE). Two other trigeminal ganglia included in the trigeminal canal and trigeminal cavity were decalcified with formic acid/formalin for 12 weeks and stained with HE to study the related vessels. Additionally, a corrosion cast was obtained from a separate canine specimen.ResultsLeptomeninges and a subarachnoid space were identified at the level of the trigeminal nerve roots and the trigeminal ganglion. No subarachnoid space was identified and leptomeninges were no longer present at the level of the three trigeminal nerve branches. Small arterial vessels ran to and supplied the trigeminal ganglion, passing through the dura mater. No venous plexus was visualized at the level of the trigeminal ganglion in the dissections. A complex arterial vascular network was identified within the leptomeningeal covering of the trigeminal ganglion and was best appreciated in the corrosion cast. Histological examination revealed small-to moderate-sized blood vessels located in the epineurium around the ganglion; from there a multitude of arterioles penetrated into the perineurium. Small endoneurial branches and capillaries penetrated the ganglion and the trigeminal nerve branches.DiscussionLimitations to this study include the limited number of canine specimens included and the lack of electron microscopy to further support current hypotheses included in our discussion. In conclusion, this study provides further support to the theory that TGCE in dogs may be due an incomplete blood-nerve barrier or blood-ganglion barrier at the interface between the central nervous system and the peripheral nervous system.