ISLA: A U-Net for MRI-based acute ischemic stroke lesion segmentation with deep supervision, attention, domain adaptation, and ensemble learning

2026-01-13

AI Summary

Accurate MRI segmentation of acute ischemic stroke lesions is crucial for clinical diagnosis and treatment, yet existing methods still face challenges in generalizability and reproducibility. This work proposes a unified U-Net–based framework that, for the first time, systematically integrates deep supervision, attention mechanisms, unsupervised domain adaptation, and ensemble learning to jointly optimize both network architecture and loss functions. Evaluated on large-scale, multi-center diffusion MRI data, the proposed method significantly outperforms two current state-of-the-art models on external test sets, demonstrating markedly improved generalization and clinical applicability. The code and trained models will be publicly released to facilitate reproducibility and further application.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Unsupervised & Self-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate delineation of acute ischemic stroke lesions in MRI is a key component of stroke diagnosis and management. In recent years, deep learning models have been successfully applied to the automatic segmentation of such lesions. While most proposed architectures are based on the U-Net framework, they primarily differ in their choice of loss functions and in the use of deep supervision, residual connections, and attention mechanisms. Moreover, many implementations are not publicly available, and the optimal configuration for acute ischemic stroke (AIS) lesion segmentation remains unclear. In this work, we introduce ISLA (Ischemic Stroke Lesion Analyzer), a new deep learning model for AIS lesion segmentation from diffusion MRI, trained on three multicenter databases totaling more than 1500 AIS participants. Through systematic optimization of the loss function, convolutional architecture, deep supervision, and attention mechanisms, we developed a robust segmentation framework. We further investigated unsupervised domain adaptation to improve generalization to an external clinical dataset. ISLA outperformed two state-of-the-art approaches for AIS lesion segmentation on an external test set. Codes and trained models will be made publicly available to facilitate reuse and reproducibility.

Problem

• acute ischemic stroke
• MRI
• lesion segmentation
• deep learning
• domain adaptation

Innovation

• deep supervision
• attention mechanism
• domain adaptation
• ensemble learning
• U-Net