← 研踪 PaperTrailarXiv:2601.08732 · v2
ISLA: Ensemble learning and domain adaptation for generalizable acute ischemic stroke lesion segmentation in diffusion MRI with clinical validation
首次提交 2026-01-14 01:05
版本更新 2026-11-14 02:29
雷达观测 2026-11-16 13:44
摘要
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 (Ischemic Stroke Lesion Analyzer), a framework for AIS lesion segmentation built on the design principles of . combines attention modules, deep supervision, and ensemble learning across different input resolutions, convolutional block types, and loss functions. We also introduce , 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 trained on the same data. outperformed the pre-trained models on the internal validation set, while both and outperformed them on the external cohort. Although performed slightly better than internally, both variants demonstrated better generalization to the external cohort. Furthermore, significantly improved performance over 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 ( 5 s per case), and their code and weights are publicly available at https://github.com/RocaVincent/isla_segmentation.
作者备注:Substantially revised manuscript, including improvements to the methodology, additional experiments, and an expanded discussion
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-14 02:29 · 最新观测版本
ISLA: Ensemble learning and domain adaptation for generalizable acute ischemic stroke lesion segmentation in diffusion MRI with clinical validation
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 (Ischemic Stroke Lesion Analyzer), a framework for AIS lesion segmentation built on the design principles of . combines attention modules, deep supervision, and ensemble learning across different input resolutions, convolutional block types, and loss functions. We also introduce , 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 trained on the same data. outperformed the pre-trained models on the internal validation set, while both and outperformed them on the external cohort. Although performed slightly better than internally, both variants demonstrated better generalization to the external cohort. Furthermore, significantly improved performance over 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 ( 5 s per case), and their code and weights are publicly available at https://github.com/RocaVincent/isla_segmentation.
查看此版本解读 →查看此版本原文 ↗