Enjoying Information Dividend: Gaze Track-based Medical Weakly Supervised Segmentation
This work addresses the challenge of sparse annotations in medical image segmentation for clinicians, but it is incremental as it builds on existing gaze-based methods.
The paper tackles the problem of weakly supervised semantic segmentation in medical imaging by proposing GradTrack, a framework that uses physicians' gaze tracks to enhance performance, achieving Dice score improvements of 3.21% and 2.61% on two datasets.
Weakly supervised semantic segmentation (WSSS) in medical imaging struggles with effectively using sparse annotations. One promising direction for WSSS leverages gaze annotations, captured via eye trackers that record regions of interest during diagnostic procedures. However, existing gaze-based methods, such as GazeMedSeg, do not fully exploit the rich information embedded in gaze data. In this paper, we propose GradTrack, a framework that utilizes physicians' gaze track, including fixation points, durations, and temporal order, to enhance WSSS performance. GradTrack comprises two key components: Gaze Track Map Generation and Track Attention, which collaboratively enable progressive feature refinement through multi-level gaze supervision during the decoding process. Experiments on the Kvasir-SEG and NCI-ISBI datasets demonstrate that GradTrack consistently outperforms existing gaze-based methods, achieving Dice score improvements of 3.21\% and 2.61\%, respectively. Moreover, GradTrack significantly narrows the performance gap with fully supervised models such as nnUNet.