Automatic Post-Stroke Lesion Segmentation on MR Images using 3D Residual Convolutional Neural Network

TL;DR

This study demonstrates that deep residual 3D convolutional neural networks can effectively segment chronic stroke lesions in MRI scans, achieving the highest performance on a public dataset.

Contribution

The paper introduces a novel 3D residual CNN model with a zoom-in&out strategy for stroke lesion segmentation, achieving state-of-the-art results.

Findings

Average DSC of 0.64 indicating high segmentation accuracy

Achieved the highest performance on the public dataset to date

Effective application of latest deep learning techniques for 3D MRI segmentation

Abstract

In this paper, we demonstrate the feasibility and performance of deep residual neural networks for volumetric segmentation of irreversibly damaged brain tissue lesions on T1-weighted MRI scans for chronic stroke patients. A total of 239 T1-weighted MRI scans of chronic ischemic stroke patients from a public dataset were retrospectively analyzed by 3D deep convolutional segmentation models with residual learning, using a novel zoom-in&out strategy. Dice similarity coefficient (DSC), Average symmetric surface distance (ASSD), and Hausdorff distance (HD) of the identified lesions were measured by using the manual tracing of lesions as the reference standard. Bootstrapping was employed for all metrics to estimate 95% confidence intervals. The models were assessed on the test set of 31 scans. The average DSC was 0.64 (0.51-0.76) with a median of 0.78. ASSD and HD were 3.6 mm (1.7-6.2 mm) and 20.4 mm (10.0-33.3 mm), respectively. To the best of our knowledge, this performance is the highest achieved on this public dataset. The latest deep learning architecture and techniques were applied for 3D segmentation on MRI scans and demonstrated to be effective for volumetric segmentation of chronic ischemic stroke lesions.