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 a 2D approach, 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.
@article{arxiv.2101.10674,
title = {Leveraging 3D Information in Unsupervised Brain MRI Segmentation},
author = {Benjamin Lambert and Maxime Louis and Senan Doyle and Florence Forbes and Michel Dojat and Alan Tucholka},
journal= {arXiv preprint arXiv:2101.10674},
year = {2021}
}
Comments
Accepted for presentation at IEEE International Symposium on Biomedical Imaging 2021