Weakly Supervised Fine Tuning Approach for Brain Tumor Segmentation Problem
This work addresses the problem of high annotation costs in medical imaging for researchers and clinicians, but it is incremental as it builds on existing weakly supervised techniques.
The paper tackles brain tumor segmentation in MRI by proposing a weakly supervised fine-tuning approach that uses both pixel-level and image-level annotations to reduce reliance on costly pixel-level data, achieving competitive segmentation quality compared to fully supervised methods.
Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain. In contrast, image-level annotations, where only the presence of lesion is marked, are generally cheap, generated in far larger volumes compared to pixel-level labels, and contain less labeling noise. In the context of brain tumor segmentation, both pixel-level and image-level annotations are commonly available; thus, a natural question arises whether a segmentation procedure could take advantage of both. In the present work we: 1) propose a learning-based framework that allows simultaneous usage of both pixel- and image-level annotations in MRI images to learn a segmentation model for brain tumor; 2) study the influence of comparative amounts of pixel- and image-level annotations on the quality of brain tumor segmentation; 3) compare our approach to the traditional fully-supervised approach and show that the performance of our method in terms of segmentation quality may be competitive.