Factorised spatial representation learning: application in semi-supervised myocardial segmentation

By Agisilaos Chartsias, Thomas Joyce, G. Papanastasiou, S. Semple, M. Williams, D. Newby, Rohan Dharmakumar, Sotirios A. Tsaftaris. 2018

77 citations recorded by the source corpus.

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 this https URL.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

On the Transfer of Disentangled Representations in Realistic Settings (2020, background): “Despite the growing importance of the ﬁeld and the potential societal impact in the medical domain (Chartsias et al., 2018) or fair decision making (Locatello et al., 2019a), state-of-the-art approaches for learning disentangled representations have so far only been systematically evaluated on…”
On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset (2019, background): “[6] Agisilaos Chartsias, Thomas Joyce, Giorgos Papanastasiou, Scott Semple, Michelle Williams, David Newby, Rohan Dharmakumar, and Sotirios A Tsaftaris.”
Is Independence all you need? On the Generalization of Representations Learned from Correlated Data (2020, background): “Given the potential societal impact in the medical domain (Chartsias et al., 2018) or fair decision making (Lo-catello et al., 2019a; Madras et al., 2018; Creager et al., 2019), the evaluation of the usefulness of disentangled representations trained on correlated data is of critical importance.”
GANs for Medical Image Analysis (2018, methodology): “Since in segmentation, residual (non-RoI) information in addition to RoI features can make segmentation results more realistic, [78] and [79] propose a reconstruction strategy based on both of these features.”
AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020, unknown): “…in the context of cardiac segmentation, the work of Chartsias et al. , showed that when combined with auto-encoding principles and factorised learning, a shape-prior aided with reconstruction objectives offer a compelling solution to semi-supervised learning for myocardial segmentation [112].”
Medical Image Segmentation Using Deep Learning: A Survey (2020, background): “eled images. Thus, the semi-supervised learning framework achieves better segmentation effect in the gland segmentation task for histopathology images.Similarly, some other semi-supervised frameworks [97, 98, 99, 100] are also proposed to optimize medical image segmentation. IV. FUTURE RESEARCH DIRE”
Disentangled representation learning in cardiac image analysis (2019, methodology): “Whilst a decomposition could also be performed with a single neural network with two separate outputs and shared layer components, as done in our previous work (Chartsias et al., 2018), we found that by using two separate networks, as also done in Huang et al.”
Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation (2019, background): “Generative model based semisupervised approaches are also popular in the medical image analysis community [5, 19, 28, 29].”