Factorised spatial representation learning: application in semi-supervised myocardial segmentation
This addresses the challenge of scanner variability and artifacts in medical image analysis for clinicians, though it is incremental as it builds on existing factorisation ideas in a new domain.
The paper tackles the problem of learning factorized feature representations in medical imaging by separating anatomical from imaging-related information, achieving comparable myocardium segmentation performance to fully supervised networks using only a fraction of labeled images on datasets like ACDC and Edinburgh Imaging Facility QMRI.
The success and generalisation of deep learning algorithms heavily depend on learning good feature representations. In medical imaging this entails representing anatomical information, as well as properties related to the specific imaging setting. Anatomical information is required to perform further analysis, whereas imaging information is key to disentangle scanner variability and potential artefacts. The ability to factorise these would allow for training algorithms only on the relevant information according to the task. To date, such factorisation has not been attempted. In this paper, we propose a methodology of latent space factorisation relying on the cycle-consistency principle. As an example application, we consider cardiac MR segmentation, where we separate information related to the myocardium from other features related to imaging and surrounding substructures. We demonstrate the proposed method's utility in a semi-supervised setting: we use very few labelled images together with many unlabelled images to train a myocardium segmentation neural network. Specifically, we achieve comparable performance to fully supervised networks using a fraction of labelled images in experiments on ACDC and a dataset from Edinburgh Imaging Facility QMRI. Code will be made available at https://github.com/agis85/spatial_factorisation.