Multi-Scale Cross Contrastive Learning for Semi-Supervised Medical Image Segmentation

Liu, Q., Gu, X., Henderson, P. and Deligianni, F. (2023) Multi-Scale Cross Contrastive Learning for Semi-Supervised Medical Image Segmentation. In: 34th British Machine Vision Conference (BMVC 2023), Aberdeen, UK, 20-24 Nov 2023,

Abstract

Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data. However, most existing approaches do not explicitly capture high-level semantic relations between distant regions, which limits their performance. In this paper, we focus on representation learning for semi-supervised learning, by developing a novel Multi-Scale Cross Supervised Contrastive Learning (MCSC) framework, to segment structures in medical images. We jointly train CNN and Transformer models, regularising their features to be semantically consistent across different scales. Our approach contrasts multi-scale features based on ground-truth and cross-predicted labels, in order to extract robust feature representations that reflect intra- and inter-slice relationships across the whole dataset. To tackle class imbalance, we take into account the prevalence of each class to guide contrastive learning and ensure that features adequately capture infrequent classes. Extensive experiments on two multi-structure medical segmentation datasets demonstrate the effectiveness of MCSC. It not only outperforms state-of-the-art semi-supervised methods by more than 3.0 % in Dice, but also greatly reduces the performance gap with fully supervised methods. Our code is available at https://github.com/kathyliu579/MCSC.

• Item Type: Conference Proceedings
• Additional Information: The authors acknowledge funding by China Scholarship Council, EPSRC (EP/W01212X/1) and Royal Society (RGS/R2/212199).
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Liu, Qianying and Gu, Mr Xiao and Deligianni, Dr Fani and Henderson, Dr Paul
• Authors: Liu, Q., Gu, X., Henderson, P., and Deligianni, F.
• College/School: College of Science and Engineering; College of Science and Engineering > School of Computing Science
• Copyright Holders: Copyright © 2023 the authors
• First Published: First published in The 34th British Machine Vision Conference Proceedings
• Publisher Policy: Reproduced in accordance with the publisher copyright policy

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
315206		Privacy-Preserved Human Motion Analysis for Healthcare Applications	Fani Deligianni	Engineering and Physical Sciences Research Council (EPSRC)	EP/W01212X/1	Computing Science