Multilabel, multiscale topological transformation for cerebral MRI segmentation post-processing

Abstract : Accurate segmentation of cerebral structures remains, after two decades of research, a complex task. In particular, obtaining satisfactory results in terms of topology, in addition to quantitative and geometrically correct properties is still an ongoing issue. In this paper, we investigate how recent advances in multilabel topology and homotopy-type preserving transformations can be involved in the development of multiscale topological modelling of brain structures, and topology-based post-processing of segmentation maps of brain MR images. In this context, a preliminary study and a proof-of-concept are presented.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01982972
Contributor : Nicolas Passat <>
Submitted on : Saturday, March 23, 2019 - 11:40:30 AM
Last modification on : Saturday, November 16, 2019 - 1:38:38 AM
Long-term archiving on : Monday, June 24, 2019 - 12:22:18 PM

File

Tor-Diez ISMM 2019.pdf
Files produced by the author(s)

Identifiers

Citation

Carlos Tor-Díez, Sylvain Faisan, Loïc Mazo, Nathalie Bednarek, Hélène Meunier, et al.. Multilabel, multiscale topological transformation for cerebral MRI segmentation post-processing. International Symposium on Mathematical Morphology (ISMM), 2019, Saarbrücken, Germany. pp.471-482, ⟨10.1007/978-3-030-20867-7_36⟩. ⟨hal-01982972⟩

Share

Metrics

Record views

133

Files downloads

124