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

arXiv: https://arxiv.org/abs/2512.20436 · HTML: https://mlsanity.com/paper/2512.20436/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 10 of 10)

- [Cross Lingual Speech Emotion Recognition: Urdu vs. Western Languages](https://mlsanity.com/paper/1812.10411/) (2018)
- [Phonocardiographic Sensing using Deep Learning for Abnormal Heartbeat Detection](https://mlsanity.com/paper/1801.08322/) (2018)
- [Motion Corrected Multishot MRI Reconstruction Using Generative Networks with Sensitivity Encoding](https://mlsanity.com/paper/1902.07430/) (2019)
- [Volumetric Lung Nodule Segmentation using Adaptive ROI with Multi-View Residual Learning](https://mlsanity.com/paper/1912.13335/) (2019)
- [Using Deep Autoencoders for Facial Expression Recognition](https://mlsanity.com/paper/1801.08329/) (2018)
- [Automating Motion Correction in Multishot MRI Using Generative Adversarial Networks](https://mlsanity.com/paper/1811.09750/) (2018)
- [Dual-Stage Deeply Supervised Attention-based Convolutional Neural Networks for Mandibular Canal Segmentation in CBCT Scans](https://mlsanity.com/paper/2210.03739/) (2022)
- [Biological Brain Age Estimation using Sex-Aware Adversarial Variational Autoencoder with Multimodal Neuroimages](https://mlsanity.com/paper/2412.05632/) (2024)
- [Anatomy-Guided Representation Learning Using a Transformer-Based Network for Thyroid Nodule Segmentation in Ultrasound Images](https://mlsanity.com/paper/2512.12662/) (2025)
- [Complex Swin Transformer for Accelerating Enhanced SMWI Reconstruction](https://mlsanity.com/paper/2512.22202/) (2025)

## Abstract (arXiv)

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.