Factorisation-based Image Labelling

TL;DR

This paper introduces a factorisation-based image labelling method for automated brain MRI segmentation that effectively handles various image contrasts and domain shifts, outperforming existing methods in accuracy and versatility.

Contribution

The paper presents a novel generative model with latent variables for patch-based label propagation, enabling fully automated and contrast-invariant brain segmentation.

Findings

Outperforms state-of-the-art methods on MICCAI 2012 data

Handles different MR contrasts effectively

Demonstrates robustness to domain shift

Abstract

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.