Dataset Information

Development and Validation of a Deep Learning-Based Automatic Brain Segmentation and Classification Algorithm for Alzheimer Disease Using 3D T1-Weighted Volumetric Images.

ABSTRACT:

Background and purpose

Limited evidence has suggested that a deep learning automatic brain segmentation and classification method, based on T1-weighted brain MR images, can predict Alzheimer disease. Our aim was to develop and validate a deep learning-based automatic brain segmentation and classification algorithm for the diagnosis of Alzheimer disease using 3D T1-weighted brain MR images.

Materials and methods

A deep learning-based algorithm was developed using a dataset of T1-weighted brain MR images in consecutive patients with Alzheimer disease and mild cognitive impairment. We developed a 2-step algorithm using a convolutional neural network to perform brain parcellation followed by 3 classifier techniques including XGBoost for disease prediction. All classification experiments were performed using 5-fold cross-validation. The diagnostic performance of the XGBoost method was compared with logistic regression and a linear Support Vector Machine by calculating their areas under the curve for differentiating Alzheimer disease from mild cognitive impairment and mild cognitive impairment from healthy controls.

Results

In a total of 4 datasets, 1099, 212, 711, and 705 eligible patients were included. Compared with the linear Support Vector Machine and logistic regression, XGBoost significantly improved the prediction of Alzheimer disease (P < .001). In terms of differentiating Alzheimer disease from mild cognitive impairment, the 3 algorithms resulted in areas under the curve of 0.758-0.825. XGBoost had a sensitivity of 68% and a specificity of 70%. In terms of differentiating mild cognitive impairment from the healthy control group, the 3 algorithms resulted in areas under the curve of 0.668-0.870. XGBoost had a sensitivity of 79% and a specificity of 80%.

Conclusions

The deep learning-based automatic brain segmentation and classification algorithm allowed an accurate diagnosis of Alzheimer disease using T1-weighted brain MR images. The widespread availability of T1-weighted brain MR imaging suggests that this algorithm is a promising and widely applicable method for predicting Alzheimer disease.

SUBMITTER: Suh CH

PROVIDER: S-EPMC7963227 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

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:IntroductionBladder magnetic resonance imaging (MRI) has been recently integrated in the diagnosis pathway of bladder cancer. However, automatic recognition of suspicious lesions is still challenging. Thus, development of a solution for proper delimitation of the tumor and its separation from the healthy tissue is of primordial importance. As a solution to this unmet medical need, we aimed to develop an artificial intelligence-based decision support system, which automatically segments the bladder wall and the tumor as well as any suspect area from the 3D MRI images.MaterialsWe retrospectively assessed all patients diagnosed with bladder cancer, who underwent MRI at our department (n=33). All examinations were performed using a 1.5 Tesla MRI scanner. All images were reviewed by two radiologists, who performed manual segmentation of the bladder wall and all lesions. First, the performance of our fully automated end-to-end segmentation model based on a 3D U-Net architecture (by considering various depths of 4, 5 or 6 blocks) trained in two data augmentation scenarios (on 5 and 10 augmentation datasets per original data, respectively) was tested. Second, two learning setups were analyzed by training the segmentation algorithm with 7 and 14 MRI original volumes, respectively.ResultsWe obtained a Dice-based performance over 0.878 for automatic segmentation of bladder wall and tumors, as compared to manual segmentation. A larger training dataset using 10 augmentations for 7 patients could further improve the results of the U-Net-5 model (0.902 Dice coefficient at image level). This model performed best in terms of automated segmentation of bladder, as compared to U-Net-4 and U-Net-6. However, in this case increased time for learning was needed as compared to U-Net-4. We observed that an extended dataset for training led to significantly improved segmentation of the bladder wall, but not of the tumor.ConclusionWe developed an intelligent system for bladder tumors automated diagnostic, that uses a deep learning model to segment both the bladder wall and the tumor. As a conclusion, low complexity networks, with less than five-layers U-Net architecture are feasible and show good performance for automatic 3D MRI image segmentation in patients with bladder tumors.

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.