Voxel-wise Comparison with a-contrario Analysis for Automated Segmentation of Multiple Sclerosis Lesions from Multimodal MRI - Archive ouverte HAL Access content directly
Conference Papers Year :

Voxel-wise Comparison with a-contrario Analysis for Automated Segmentation of Multiple Sclerosis Lesions from Multimodal MRI

(1) , (1) , (2) , (1)
1
2

Abstract

We introduce a new framework for the automated and un-supervised segmentation of Multiple Sclerosis lesions from multimodal Magnetic Resonance images. It relies on a voxel-wise approach to detect local white matter abnormalities, with an a-contrario analysis, which takes into account local information. First, a voxel-wise comparison of multimodal patient images to a set of controls is performed. Then, region-based probabilities are estimated using an a-contrario approach. Finally, correction for multiple testing is performed. Validation was undertaken on a multi-site clinical dataset of 53 MS patients with various number and volume of lesions. We showed that the proposed framework outperforms the widely used FDR-correction for this type of analysis, particularly for low lesion loads.
Vignette du fichier
Galassi_Miccai2018_thumbnail.png (141.33 Ko) Télécharger le fichier Fichier principal
Vignette du fichier
miccai2018.pdf (1.07 Mo) Télécharger le fichier
Vignette du fichier
GalassiFrancesca_brainLes_Miccai2018.pdf (684.91 Ko) Télécharger le fichier
Format : Figure, Image
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Loading...

Dates and versions

inserm-01888928 , version 1 (05-10-2018)

Identifiers

Cite

Francesca Galassi, Olivier Commowick, Emmanuel Vallee, Christian Barillot. Voxel-wise Comparison with a-contrario Analysis for Automated Segmentation of Multiple Sclerosis Lesions from Multimodal MRI. MICCAI BrainLes 2018 workshop, Alessandro Crimi; Spyridon Bakas, Sep 2018, Granada, Spain. pp.180-188, ⟨10.1007/978-3-030-11723-8_18⟩. ⟨inserm-01888928⟩
298 View
372 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More