Localized Perturbations For Weakly-Supervised Segmentation of Glioma Brain Tumours
This addresses the need for accurate tumor segmentation in medical imaging with reduced annotation effort, though it is incremental as it builds on existing weakly-supervised and perturbation techniques.
The paper tackled the problem of segmenting glioma brain tumors from medical images without fine-grained annotations by proposing a weakly-supervised method using localized perturbations, achieving a Dice similarity coefficient of 0.44 compared to expert annotations and outperforming Grad-CAM, which scored 0.11.
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.