Leveraging 3D information in unsupervised brain MRI segmentation - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Leveraging 3D information in unsupervised brain MRI segmentation

Abstract

Automatic segmentation of brain abnormalities is challenging, as they vary considerably from one pathology to another. Current methods are supervised and require numerous annotated images for each pathology, a strenuous task. To tackle anatomical variability, Unsupervised Anomaly Detection (UAD) methods are proposed, detecting anomalies as outliers of a healthy model learned using a Variational Autoencoder (VAE). Previous work on UAD adopted 2D approaches, meaning that MRIs are processed as a collection of independent slices. Yet, it does not fully exploit the spatial information contained in MRI. Here, we propose to perform UAD in a 3D fashion and compare 2D and 3D VAEs. As a side contribution, we present a new loss function guarantying a robust training. Learning is performed using a multicentric dataset of healthy brain MRIs, and segmentation performances are estimated on White-Matter Hyperintensities and tumors lesions. Experiments demonstrate the interest of 3D methods which outperform their 2D counterparts.
Fichier principal
Vignette du fichier
B_lambert.pdf (232.37 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03273953 , version 1 (29-06-2021)

Identifiers

  • HAL Id : hal-03273953 , version 1

Cite

Benjamin Lambert, Maxime Louis, Senan Doyle, Florence Forbes, Michel Dojat, et al.. Leveraging 3D information in unsupervised brain MRI segmentation. ISBI 2021 - 18th International Symposium on Biomedical Imaging, Apr 2021, Nice / Virtual, France. pp.1-4. ⟨hal-03273953⟩
47 View
138 Download

Share

Gmail Facebook X LinkedIn More