Factorisation-based Image Labelling
This work addresses the need for a general-purpose, automated brain segmentation tool to reduce time and cost in neuroimaging, though it appears incremental compared to existing methods.
The paper tackles automated brain MRI segmentation by proposing a patch-based label propagation approach using a generative model with latent variables, achieving competitive results on the MICCAI 2012 dataset and demonstrating robustness to domain shifts across different MR contrasts.
Segmentation of brain magnetic resonance images (MRI) into anatomical regions is a useful task in neuroimaging. Manual annotation is time consuming and expensive, so having a fully automated and general purpose brain segmentation algorithm is highly desirable. To this end, we propose a patched-based label propagation approach based on a generative model with latent variables. Once trained, our Factorisation-based Image Labelling (FIL) model is able to label target images with a variety of image contrasts. We compare the effectiveness of our proposed model against the state-of-the-art using data from the MICCAI 2012 Grand Challenge and Workshop on Multi-Atlas Labeling. As our approach is intended to be general purpose, we also assess how well it can handle domain shift by labelling images of the same subjects acquired with different MR contrasts.