 |
Conference papers
Automatic Multiple Sclerosis lesion segmentation from Intensity-Normalized multi-channel MRI
Abstract : In the context of the FLI MICCAI 2016 MSSEG challenge for lesion segmentation, we present a fully automated algorithm for Multiple Sclerosis (MS) lesion segmentation. Our method is composed of three main steps. First, the MS patient images are registered and intensity normalized. Then, the lesion segmentation is done using a voxel-wise comparison of multi-channel Magnetic Resonance Images (MRI) against a set of controls. Finally, the segmentation is refined by applying several lesion appearance rules.
https://www.hal.inserm.fr/inserm-01424802
Contributor : Olivier Commowick <>
Submitted on : Monday, January 2, 2017 - 9:59:02 PM
Last modification on : Friday, January 15, 2021 - 3:34:04 AM
Long-term archiving on: : Tuesday, April 4, 2017 - 1:41:51 AM
Contributor : Olivier Commowick <>
Submitted on : Monday, January 2, 2017 - 9:59:02 PM
Last modification on : Friday, January 15, 2021 - 3:34:04 AM
Long-term archiving on: : Tuesday, April 4, 2017 - 1:41:51 AM
File
MSSEG_Beaumont_2.pdf
Files produced by the author(s)