King's College London

Research portal

Quality-aware semi-supervised learning for CMR segmentation

Research output: Chapter in Book/Report/Conference proceedingConference paper

Original languageEnglish
Title of host publication2020 Conference on Medical Image Computing and Computer Assisted Interventions
Subtitle of host publicationWorkshop on Statistical Atlases and Computational Modelling of the Heart
PublisherSpringer
Published26 Aug 2020

Documents

King's Authors

Abstract

One of the challenges in developing deep learning algorithms for medical image segmentation is the scarcity of annotated training data. To overcome this limitation, data augmentation and semi-supervised learning (SSL) methods have been developed. However, these methods have limited effectiveness as they either exploit the existing dataset only (data augmentation) or risk negative impact by adding poor training examples (SSL). Segmentations are rarely the nal product of medical image analysis - they are typically used in downstream tasks to infer higher-order patterns to evaluate diseases. Clinicians take into account a
wealth of prior knowledge on biophysics and physiology when evaluating image analysis results. We have used these clinical assessments in previous works to create robust quality-control (QC) classifiers for automated cardiac magnetic resonance (CMR) analysis.
In this paper, we propose a novel scheme that uses QC of the downstream task to identify high quality outputs of CMR segmentation networks, that are subsequently utilised for further network training. In essence, this provides quality-aware augmentation of training data in a variant of SSL for segmentation networks (semiQCSeg). We evaluate our approach in two CMR segmentation tasks (aortic and short axis cardiac volume segmentation) using UK Biobank data and two commonly used network architectures (U-net and a Fully Convolutional Network) and compare against supervised and SSL strategies. We show that semiQCSeg improves training of the segmentation networks. It decreases the need for labelled data, while outperforming the other methods in terms of Dice and clinical metrics.
SemiQCSeg can be an effcient approach for training segmentation networks for medical image data when labelled datasets are scarce.

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454