Self-supervised Mean Teacher for Semi-supervised Chest X-Ray Classification

Simple item page
dc.contributor.authorLiu, F.
dc.contributor.authorTian, Y.
dc.contributor.authorCordeiro, F.R.
dc.contributor.authorBelagiannis, V.
dc.contributor.authorReid, I.
dc.contributor.authorCarneiro, G.
dc.contributor.conference12th International Workshop, Machine Learning in Medical Imaging (MLMI) (27 Sep 2021 - 27 Sep 2021 : Strasbourg, France)
dc.contributor.editorLian, C.
dc.contributor.editorCao, X.
dc.contributor.editorRekik, I.
dc.contributor.editorXu, X.
dc.contributor.editorYan, P.
dc.date.issued2021
dc.descriptionThis is the 12th in a series of workshops on this topic in conjunction with the 24th International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI 2021)
dc.description.abstractThe training of deep learning models generally requires a large amount of annotated data for effective convergence and generalisation. However, obtaining high-quality annotations is a laboursome and expensive process due to the need of expert radiologists for the labelling task. The study of semi-supervised learning in medical image analysis is then of crucial importance given that it is much less expensive to obtain unlabelled images than to acquire images labelled by expert radiologists. Essentially, semi-supervised methods leverage large sets of unlabelled data to enable better training convergence and generalisation than using only the small set of labelled images. In this paper, we propose Selfsupervised Mean Teacher for Semi-supervised (S2MTS2) learning that combines self-supervised mean-teacher pre-training with semi-supervised fine-tuning. The main innovation of S2MTS2 is the self-supervised meanteacher pre-training based on the joint contrastive learning, which uses an infinite number of pairs of positive query and key features to improve the mean-teacher representation. The model is then fine-tuned using the exponential moving average teacher framework trained with semisupervised learning. We validate S2MTS2 on the multi-label classification problems from Chest X-ray14 and CheXpert, and the multi-class classification from ISIC2018, where we show that it outperforms the previous SOTA semi-supervised learning methods by a large margin. Our code will be available upon paper acceptance.
dc.description.statementofresponsibilityFengbei Liu, Yu Tian, Filipe R. Cordeiro, Vasileios Belagiannis, Ian Reid, and Gustavo Carneiro
dc.identifier.citationLecture Notes in Artificial Intelligence, 2021 / Lian, C., Cao, X., Rekik, I., Xu, X., Yan, P. (ed./s), vol.12966 LNIP, pp.426-436
dc.identifier.doi10.1007/978-3-030-87589-3_44
dc.identifier.isbn9783030875886
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.orcidLiu, F. [0000-0003-0355-2006]
dc.identifier.orcidReid, I. [0000-0001-7790-6423]
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]
dc.identifier.urihttps://hdl.handle.net/2440/137568
dc.language.isoen
dc.publisherSpringer International Publishing
dc.publisher.placeSwitzerland
dc.relation.granthttp://purl.org/au-research/grants/arc/DP180103232
dc.relation.granthttp://purl.org/au-research/grants/arc/FT190100525
dc.relation.ispartofseriesLecture Notes in Computer Science; 12966
dc.rights© Springer Nature Switzerland AG 2021
dc.source.urihttps://link.springer.com/book/10.1007/978-3-030-87589-3
dc.subjectSemi-supervised learning; Chest X-ray; Self-supervised learning; Multi-label classification
dc.titleSelf-supervised Mean Teacher for Semi-supervised Chest X-Ray Classification
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Australian Institute for Machine Learning publications
Computer Science publications