Label uncertainty-guided multi-stream model for disease screening
This work addresses disease screening in medical imaging by handling label uncertainty, though it is incremental as it builds on existing multi-stream approaches.
The paper tackled the problem of intra-observer variability in medical image annotation by modeling it as label uncertainty and using this to guide a multi-stream network for disease screening, resulting in improved performance, particularly for hard cases, as demonstrated in a glaucoma screening case study.
The annotation of disease severity for medical image datasets often relies on collaborative decisions from multiple human graders. The intra-observer variability derived from individual differences always persists in this process, yet the influence is often underestimated. In this paper, we cast the intra-observer variability as an uncertainty problem and incorporate the label uncertainty information as guidance into the disease screening model to improve the final decision. The main idea is dividing the images into simple and hard cases by uncertainty information, and then developing a multi-stream network to deal with different cases separately. Particularly, for hard cases, we strengthen the network's capacity in capturing the correct disease features and resisting the interference of uncertainty. Experiments on a fundus image-based glaucoma screening case study show that the proposed model outperforms several baselines, especially in screening hard cases.