English

Localized Perturbations For Weakly-Supervised Segmentation of Glioma Brain Tumours

Image and Video Processing 2021-12-01 v1 Computer Vision and Pattern Recognition

Abstract

Deep convolutional neural networks (CNNs) have become an essential tool in the medical imaging-based computer-aided diagnostic pipeline. However, training accurate and reliable CNNs requires large fine-grain annotated datasets. To alleviate this, weakly-supervised methods can be used to obtain local information from global labels. This work proposes the use of localized perturbations as a weakly-supervised solution to extract segmentation masks of brain tumours from a pretrained 3D classification model. Furthermore, we propose a novel optimal perturbation method that exploits 3D superpixels to find the most relevant area for a given classification using a U-net architecture. Our method achieved a Dice similarity coefficient (DSC) of 0.44 when compared with expert annotations. When compared against Grad-CAM, our method outperformed both in visualization and localization ability of the tumour region, with Grad-CAM only achieving 0.11 average DSC.

Keywords

Cite

@article{arxiv.2111.14953,
  title  = {Localized Perturbations For Weakly-Supervised Segmentation of Glioma Brain Tumours},
  author = {Sajith Rajapaksa and Farzad Khalvati},
  journal= {arXiv preprint arXiv:2111.14953},
  year   = {2021}
}