Leveraging 3D Information in Unsupervised Brain MRI Segmentation
This work addresses the challenge of anatomical variability in brain abnormalities for medical imaging, offering an incremental improvement over existing unsupervised methods.
The paper tackled the problem of unsupervised brain MRI segmentation by proposing a 3D approach using Variational Autoencoders, which outperformed 2D methods in segmenting white-matter hyperintensities and tumor lesions.
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.