arXiv cs.AI· Vincent Roca, Hakim Daouairi, Sevak Yepremian, Hilde Henon, Nicolas Martinage, Laurent Puy, Gr\'egory Kuchcinski, Martin Bretzner, Renaud Lopes·· 4 小时前AI 评分40
ISLA:集成学习与域自适应实现可泛化的急性缺血性脑卒中病灶分割并获临床验证
ISLA: Ensemble learning and domain adaptation for generalizable acute ischemic stroke lesion segmentation in diffusion MRI with clinical validation
AI 导读
研究者提出基于 nnU-Net 设计原则的急性缺血性脑卒中病灶分割框架 ISLA,结合注意力模块、深监督和跨分辨率、卷积块与损失函数的集成学习,并推出利用无标注目标域数据的半监督变体 ISLA-MT。
正文 · 原文
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 $\mathit{ISLA}$ (Ischemic Stroke Lesion Analyzer), a framework for AIS lesion segmentation built on the design principles of $\mathit{nnU\text{-}Net}$. $\mathit{ISLA}$ combines attention modules, deep supervision, and ensemble learning across different input resolutions, convolutional block types, and loss functions. We also introduce $\mathit{ISLA\text{-}MT}$, 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 $\mathit{nnU\text{-}Net}$ trained on the same data. $\mathit{ISLA}$ outperformed the pre-trained models on the internal validation set, while both $\mathit{ISLA}$ and $\mathit{ISLA\text{-}MT}$ outperformed them on the external cohort. Although $\mathit{nnU\text{-}Net}$ performed slightly better than $\mathit{ISLA}$ internally, both $\mathit{ISLA}$ variants demonstrated better generalization to the external cohort. Furthermore, $\mathit{ISLA\text{-}MT}$ significantly improved performance over $\mathit{ISLA}$ 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 this https URL.
| Comments: | Substantially revised manuscript, including improvements to the methodology, additional experiments, and an expanded discussion |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2601.08732 [cs.CV] |
| (or arXiv:2601.08732v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2601.08732 arXiv-issued DOI via DataCite |
Submission history
From: Vincent Roca [view email]
[v1]
Tue, 13 Jan 2026 17:05:40 UTC (5,023 KB)
[v2]
Fri, 13 Nov 2026 18:29:11 UTC (13,693 KB)
来源:arXiv cs.AI · arxiv.org