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

TL;DR

This paper introduces a superpixel-based pseudo-label refinement framework for semi-supervised brain tumour segmentation in MRI, significantly improving accuracy with minimal annotated data.

Contribution

It proposes a novel superpixel-guided pseudo-label refinement method that enhances semi-supervised brain tumour segmentation performance.

Findings

Achieved DSC=0.824 for whole tumour segmentation.

Improved performance over baseline with only 5 annotated patients.

Effective pseudo-label refinement reduces annotation burden.

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.