ArXiv Preprint
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.
Benjamin Lambert, Maxime Louis, Senan Doyle, Florence Forbes, Michel Dojat, Alan Tucholka
2021-01-26
