Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation

Bethany H. Thompson, Gaetano Di Caterina, Jeremy P. Voisey

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

13 Citations (Scopus)
30 Downloads (Pure)


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.

Original languageEnglish
Title of host publication2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)
Place of PublicationPiscataway, NJ
Number of pages5
ISBN (Electronic)9781665429238
Publication statusPublished - 26 Apr 2022
Event19th IEEE International Symposium on Biomedical Imaging - Kolkata, India
Duration: 28 Mar 202231 Mar 2022

Publication series

NameIEEE International Symposium on Biomedical Imaging (ISBI)
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452


Conference19th IEEE International Symposium on Biomedical Imaging
Abbreviated titleIEEE ISBI 2022


  • brain
  • segmentation
  • semi-supervised
  • superpixels
  • tumour


Dive into the research topics of 'Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation'. Together they form a unique fingerprint.

Cite this