Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation
Thompson, Bethany H. and Di Caterina, Gaetano and Voisey, Jeremy P.; (2022) Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI). IEEE International Symposium on Biomedical Imaging (ISBI), 978166542 . IEEE, IND, pp. 1-5. ISBN 9781665429238 (https://doi.org/10.1109/ISBI52829.2022.9761681)
Preview |
Text.
Filename: Thompson_etal_ISBI_2022_Pseudo_label_refinement_using_superpixels_for_semi_supervised_brain_tumour_segmentation.pdf
Accepted Author Manuscript License: Strathprints license 1.0 Download (1MB)| Preview |
Abstract
Training neural networks using limited annotations is an important problem in the medical domain. Deep Neural Networks (DNNs) typically require large, annotated datasets to achieve acceptable performance which, in the medical domain, are especially difficult to obtain as they require significant time from expert radiologists. Semi-supervised learning aims to overcome this problem by learning segmentations with very little annotated data, whilst exploiting large amounts of unlabelled data. However, the best-known technique, which utilises inferred pseudo-labels, is vulnerable to inaccurate pseudo-labels degrading the performance. We propose a framework based on superpixels - meaningful clusters of adjacent pixels - to improve the accuracy of the pseudo labels and address this issue. Our framework combines superpixels with semi-supervised learning, refining the pseudo-labels during training using the features and edges of the superpixel maps. This method is evaluated on a multimodal magnetic resonance imaging (MRI) dataset for the task of brain tumour region segmentation. Our method demonstrates improved performance over the standard semi-supervised pseudo-labelling baseline when there is a reduced annotator burden and only 5 annotated patients are available. We report DSC=0.824 and DSC=0.707 for the test set whole tumour and tumour core regions respectively.
ORCID iDs
Thompson, Bethany H., Di Caterina, Gaetano ORCID: https://orcid.org/0000-0002-7256-0897 and Voisey, Jeremy P.;-
-
Item type: Book Section ID code: 81030 Dates: DateEvent26 April 2022Published7 January 2022AcceptedNotes: © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Subjects: Medicine > Internal medicine > Neuroscience. Biological psychiatry. Neuropsychiatry
Technology > Engineering (General). Civil engineering (General) > BioengineeringDepartment: Faculty of Science > Physics
Faculty of Engineering > Electronic and Electrical EngineeringDepositing user: Pure Administrator Date deposited: 10 Jun 2022 11:24 Last modified: 22 Sep 2024 00:39 Related URLs: URI: https://strathprints.strath.ac.uk/id/eprint/81030