Unsupervised Detection of Post-Stroke Brain Abnormalities

Youwan Mahé, Elise Bannier, Stéphanie Leplaideur, Elisa Fromont, Francesca Galassi
10/28/2025
cs.CV

No official code found. Best implementation: youwanM/Post-Stroke-UAD (0 stars, AGPL-3.0, last commit 2026-04-17).

Abstract

Post-stroke MRI not only delineates focal lesions but also reveals secondary structural changes, such as atrophy and ventricular enlargement. These abnormalities, increasingly recognised as imaging biomarkers of recovery and outcome, remain poorly captured by supervised segmentation methods. We evaluate REFLECT, a flow-based generative model, for unsupervised detection of both focal and non-lesional abnormalities in post-stroke patients. Using dual-expert central-slice annotations on ATLAS data, performance was assessed at the object level with Free-Response ROC analysis for anomaly maps. Two models were trained on lesion-free slices from stroke patients (ATLAS) and on healthy controls (IXI) to test the effect of training data. On ATLAS test subjects, the IXI-trained model achieved higher lesion segmentation (Dice = 0.37 vs 0.27) and improved sensitivity to non-lesional abnormalities (FROC = 0.62 vs 0.43). Training on fully healthy anatomy improves the modelling of normal variability, enabling broader and more reliable detection of structural abnormalities.

View on arXivView PDF

Code Implementations(1)

youwanM/Post-Stroke-UADCommunity58%
AGPL-3.0

This repository supports the ISBI 2026 Paper : Unsupervised Detection of Post-Stroke Brain Abnormalities

00PythonJan 22, 20266 months agoAGPL-3.0

Similar Papers

Stroke Lesion Segmentation using Multi-Stage Cross-Scale Attention

88% match1 repo42025

How We Won the ISLES'24 Challenge by Preprocessing

86% match1 repo12025

Deep Learning-Driven Segmentation of Ischemic Stroke Lesions Using Multi-Channel MRI

86% match2025

Clinically-Informed Preprocessing Improves Stroke Segmentation in Low-Resource Settings

85% match2025

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

85% match2026

Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review

84% match2025

Cite this paper

@article{mah2025unsupervised,
  title  = {Unsupervised Detection of Post-Stroke Brain Abnormalities},
  author = {Youwan Mahé and Elise Bannier and Stéphanie Leplaideur and Elisa Fromont and Francesca Galassi},
  year   = {2025},
  eprint = {2510.24398},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.24398v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.24398.svg)](https://codeofpaper.com/paper/2510.24398)

Discussion