Dual-Encoder Transformer-Based Multimodal Learning for Ischemic Stroke Lesion Segmentation Using Diffusion MRI

TL;DR

This paper introduces a dual-encoder transformer-based model for automated ischemic stroke lesion segmentation using multimodal diffusion MRI, outperforming existing methods and achieving a high Dice score of 85.4% on the ISLES 2022 dataset.

Contribution

It proposes a novel dual-encoder TransUNet architecture that learns modality-specific features from DWI and ADC scans for improved lesion segmentation.

Findings

Transformer-based models outperform convolutional models.

The dual-encoder TransUNet achieves the highest Dice score of 85.4%.

Incorporating adjacent slices improves segmentation accuracy.

Abstract

Accurate segmentation of ischemic stroke lesions from diffusion magnetic resonance imaging (MRI) is essential for clinical decision-making and outcome assessment. Diffusion-Weighted Imaging (DWI) and Apparent Diffusion Coefficient (ADC) scans provide complementary information on acute and sub-acute ischemic changes; however, automated lesion delineation remains challenging due to variability in lesion appearance. In this work, we study ischemic stroke lesion segmentation using multimodal diffusion MRI from the ISLES 2022 dataset. Several state-of-the-art convolutional and transformer-based architectures, including U-Net variants, Swin-UNet, and TransUNet, are benchmarked. Based on performance, a dual-encoder TransUNet architecture is proposed to learn modality-specific representations from DWI and ADC inputs. To incorporate spatial context, adjacent slice information is integrated using a three-slice input configuration. All models are trained under a unified framework and evaluated using the Dice Similarity Coefficient (DSC). Results show that transformer-based models outperform convolutional baselines, and the proposed dual-encoder TransUNet achieves the best performance, reaching a Dice score of 85.4% on the test set. The proposed framework offers a robust solution for automated ischemic stroke lesion segmentation from diffusion MRI.