Guardado en:
Detalles Bibliográficos
Autores principales: Mahé, Youwan, Bannier, Elise, Leplaideur, Stéphanie, Fromont, Elisa, Galassi, Francesca
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.24398
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917048022466560
author Mahé, Youwan
Bannier, Elise
Leplaideur, Stéphanie
Fromont, Elisa
Galassi, Francesca
author_facet Mahé, Youwan
Bannier, Elise
Leplaideur, Stéphanie
Fromont, Elisa
Galassi, Francesca
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24398
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unsupervised Detection of Post-Stroke Brain Abnormalities
Mahé, Youwan
Bannier, Elise
Leplaideur, Stéphanie
Fromont, Elisa
Galassi, Francesca
Computer Vision and Pattern Recognition
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.
title Unsupervised Detection of Post-Stroke Brain Abnormalities
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.24398