A 3D hierarchical multimodal detection and segmentation method for multiple sclerosis lesions in MRI

Abstract : In this paper, we propose a novel 3D method for multiple sclerosis segmentation on FLAIR Magnetic Resonance images (MRI), based on a lesion context-based criterion performed on a max-tree representation. The detection criterion is refined using prior information from other available MRI acquisitions (T2, T1, T1 enhanced with Gadolinium and DP). The method has been tested on fifteen patients su↵ering from multiple sclerosis. The results show the ability of the method to detect almost all lesions. However, the algorithm also provides false detections.
Complete list of metadatas

Cited literature [4 references]  Display  Hide  Download

https://www.hal.inserm.fr/inserm-01417465
Contributor : Nathalie Duchange <>
Submitted on : Thursday, December 15, 2016 - 4:20:01 PM
Last modification on : Monday, February 10, 2020 - 6:13:46 PM
Long-term archiving on: Thursday, March 16, 2017 - 5:41:53 PM

File

Urien et al, MSSEG Challenge P...
Files produced by the author(s)

Identifiers

  • HAL Id : inserm-01417465, version 1

Citation

Hélène Urien, Irène Buvat, Nicolas Rougon, Isabelle Bloch. A 3D hierarchical multimodal detection and segmentation method for multiple sclerosis lesions in MRI. Proceedings of the 1st MICCAI Challenge on Multiple Sclerosis Lesions Segmentation Challenge Using a Data Management and Processing Infrastructure — MICCAI-MSSEG, pp.69-74, 2016. ⟨inserm-01417465⟩

Share

Metrics

Record views

402

Files downloads

167