Pré-Publication, Document De Travail Année : 2025

Unsupervised Detection of Post-Stroke Brain Abnormalities

Résumé

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.

Fichier principal
Vignette du fichier
ISBI_2026_MAHE.pdf (785.08 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05335158 , version 1 (28-10-2025)
hal-05335158 , version 2 (23-01-2026)

Licence

Identifiants

  • HAL Id : hal-05335158 , version 1

Citer

Youwan Mahé, Elise Bannier, Stéphanie Leplaideur, Elisa Fromont, Francesca Galassi. Unsupervised Detection of Post-Stroke Brain Abnormalities. 2025. ⟨hal-05335158v1⟩
1202 Consultations
481 Téléchargements

Partager

  • More