cs.CVJan 13, 2026

ISLA: Ensemble learning and domain adaptation for generalizable acute ischemic stroke lesion segmentation in diffusion MRI with clinical validation

Authors: Vincent Roca, Hakim Daouairi, Sevak Yepremian, Hilde Henon, Nicolas Martinage, Laurent Puy, Grégory Kuchcinski, Martin Bretzner, 

Organizations: Univ. Lille, CNRS, Inserm, CHU Lille, Institut Pasteur de Lille, US 41 - UAR 2014 - PLBS, F-59000 Lille, France · CHU Lille, Département de Neurologie vasculaire, F-59037 Lille, France · Univ. Lille, Inserm, CHU Lille, U1172 - Lille Neurosciences & Cognition, F-59037 Lille, France · CHU Lille, Département de Neuroradiologie, F-59037 Lille, France · 

Abstract

Accurate segmentation of acute ischemic stroke (AIS) lesions on MRI is essential for clinical decision-making. Deep learning methods offer a promising approach to automating this task. However, they often generalize poorly to unseen clinical sites, and few AIS lesion segmentation methods have been externally validated. In this study, we propose ISLA\mathit{ISLA} (Ischemic Stroke Lesion Analyzer), a framework for AIS lesion segmentation built on the design principles of nnU-Net\mathit{nnU\text{-}Net}. ISLA\mathit{ISLA} combines attention modules, deep supervision, and ensemble learning across different input resolutions, convolutional block types, and loss functions. We also introduce ISLA-MT\mathit{ISLA\text{-}MT}, a variant that leverages unlabeled target-domain images through semi-supervised learning. We trained both approaches on the SOOP and ISLES 2022 datasets and evaluated on a held-out internal validation set of 253 cases, as well as on 590 cases from an independent multicenter clinical cohort. We compared them with three state-of-the-art pre-trained models and with nnU-Net\mathit{nnU\text{-}Net} trained on the same data. ISLA\mathit{ISLA} outperformed the pre-trained models on the internal validation set, while both ISLA\mathit{ISLA} and ISLA-MT\mathit{ISLA\text{-}MT} outperformed them on the external cohort. Although nnU-Net\mathit{nnU\text{-}Net} performed slightly better than ISLA\mathit{ISLA} internally, both ISLA\mathit{ISLA} variants demonstrated better generalization to the external cohort. Furthermore, ISLA-MT\mathit{ISLA\text{-}MT} significantly improved performance over ISLA\mathit{ISLA} on the external cohort. The proposed models performed particularly well on low-contrast lesions, and qualitative error analyses suggested greater robustness to acquisition artifacts. Both models are fast (∼\sim 5 s per case), and their code and weights are publicly available at https://github.com/RocaVincent/isla_segmentation.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 26, 2026

Deep Learning Segmentation of Diffusion-Weighted MRI Acute Ischaemic Stroke: A Pragmatic Evaluation Across Three Datasets

Objective: Diffusion-weighted MRI (DWI-MRI) is the gold standard for visualizing and quantifying acute ischaemic stroke (AIS). Although deep learning methods can accurately segment AIS lesions, the optimal image inputs and model architecture remain uncertain. We evaluated whether accurate AIS lesion segmentation can be achieved using a pragmatic deep learning approach with minimal preprocessing and clinically feasible inference times. Materials and Methods: Self-configured nnU-Net models were trained on 1,744 DWI cases from local, national, and open-access datasets and tested on 436 cases. Four experimental conditions were evaluated using five-fold cross-validation: with or without brain extraction and using either DWI alone or DWI plus apparent diffusion coefficient (ADC) images as inputs. Two architectures were compared: the baseline nnU-Net (base) and a residual encoder nnU-Net (ResEnc). Performance was benchmarked against the DeepISLES ensemble model from the 2022 ISLES challenge. Results: In the test set (n=436), the base model achieved a median (IQR) Dice similarity coefficient (DSC) of 0.84 (0.19). For the base model, only two of six pairwise comparisons between input configurations showed significant differences. ResEnc produced small but significant improvements in DSC compared with the base model for DWI, DWI+brain extraction, and DWI+ADC inputs (all p<0.02), but not for DWI+ADC+brain extraction (p>0.50). The base model significantly outperformed DeepISLES, particularly in patients with smaller infarct volumes (signed-rank test, p<0.01). Conclusions: A baseline nnU-Net trained on DWI alone, without preprocessing, enabled fast and accurate AIS lesion segmentation. This streamlined approach may facilitate clinical research and support acute stroke imaging workflows
Jan 13, 2026

Automated Lesion Segmentation of Stroke MRI Using nnU-Net: A Comprehensive External Validation Across Acute and Chronic Lesions

Accurate and generalisable segmentation of stroke lesions from magnetic resonance imaging (MRI) is essential for advancing clinical research, prognostic modelling, and personalised interventions. Although deep learning has improved automated lesion delineation, many existing models are optimised for narrow imaging contexts and generalise poorly to independent datasets, modalities, and stroke stages. Here, we systematically evaluated stroke lesion segmentation using the nnU-Net framework across multiple heterogeneous, publicly available MRI datasets spanning acute and chronic stroke. Models were trained and tested on diffusion-weighted imaging (DWI), fluid-attenuated inversion recovery (FLAIR), and T1-weighted MRI, and evaluated on independent datasets. Across stroke stages, models showed robust generalisation, with segmentation accuracy approaching reported inter-rater reliability. Performance varied with imaging modality and training data characteristics. In acute stroke, DWI-trained models consistently outperformed FLAIR-based models, with only modest gains from multimodal combinations. In chronic stroke, increasing training set size improved performance, with diminishing returns beyond several hundred cases. Lesion volume was a key determinant of accuracy: smaller lesions were harder to segment, and models trained on restricted volume ranges generalised poorly. MRI image quality further constrained generalisability: models trained on lower-quality scans transferred poorly, whereas those trained on higher-quality data generalised well to noisier images. Discrepancies between predictions and reference masks were often attributable to limitations in manual annotations. Together, these findings show that automated lesion segmentation can approach human-level performance while identifying key factors governing generalisability and informing the development of lesion segmentation tools.
Aug 24, 2026

Native-Space 3D CarveMix for Multi-Site T1w Stroke Segmentation

Segmenting ischemic stroke lesions on T1-weighted (T1w) MRI acquired across different scanners and protocols without intensity standardization is difficult because lesions are subtle and share intensity characteristics with cerebrospinal fluid. Standard deep learning architectures trained across multiple centers plateau around Dice 0.66, with acute lesions (≤7\le 7 days post-stroke) performing substantially worse due to severe sample scarcity. We combine a MedNeXt-L (k=5k=5) backbone with on-the-fly 3D CarveMix augmentation that pastes real lesion patches into healthy brain regions during training. By generating synthetic lesion placements dynamically within each fold with subject-level split isolation, the model sees more diverse lesion patterns without requiring pre-generated copies on disk. We evaluate on 1,453 native T1w scans from 55 clinical centers in the ISLES 2026 challenge. Our method achieves a mean 5-fold cross-validation Dice of 0.648 at 500 epochs, a +0.018 improvement over the MedNeXt-L backbone at a matched training budget (0.630)