Skip to Main content Skip to Navigation
Conference papers

Detection of abnormal folding patterns with unsupervised deep generative models

Louise Guillon 1 Bastien Cagna 1 Benoit Dufumier 2, 3 Joël Chavas 1 Denis Rivière 1 Jean-François Mangin 1
1 BAOBAB - Unité Baobab
NEUROSPIN - Service NEUROSPIN : DRF/JOLIOT/NEUROSPIN
3 Télécom ParisTech - IP
LTCI - Laboratoire Traitement et Communication de l'Information
Abstract : Although the main structures of cortical folding are present in each human brain, the folding pattern is unique to each individual. Because of this large normal variability, the identification of abnormal patterns associated to developmental disorders is a complex open challenge. In this paper, we tackle this problem as an anomaly detection task and explore the potential of deep generative models using benchmarks made up of synthetic anomalies. To focus learning on the folding geometry, brain MRI are preprocessed first to deal only with a skeleton-based negative cast of the cortex. A variational auto-encoder is trained to get a representation of the regional variability of the folding pattern of the general population. Then several synthetic benchmark datasets of abnormalities are designed. The latent space expressivity is assessed through classification experiments between control's and abnormal's latent codes. Finally, the properties encoded in the latent space are analyzed through perturbation of specific latent dimensions and observation of the resulting modification of the reconstructed images. The results have shown that the latent representation is rich enough to distinguish subtle differences like asymmetries between the right and left hemispheres.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03349112
Contributor : Louise Guillon Connect in order to contact the contributor
Submitted on : Monday, September 20, 2021 - 11:45:26 AM
Last modification on : Thursday, September 23, 2021 - 3:33:25 AM

File

abnormal_folding_patterns_dete...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03349112, version 1

Citation

Louise Guillon, Bastien Cagna, Benoit Dufumier, Joël Chavas, Denis Rivière, et al.. Detection of abnormal folding patterns with unsupervised deep generative models. MLCN workshop, held in conjunction of MICCAI, Sep 2021, Strasbourg, France. ⟨hal-03349112⟩

Share

Metrics

Record views

82

Files downloads

156