Deep Bayesian Active-Learning-to-Rank for Endoscopic Image Data
This work addresses the problem of reducing annotation effort for medical image analysis, specifically for gastroenterologists, but it is incremental as it builds on existing learning-to-rank and active learning techniques.
The paper tackles the challenge of annotating disease severity in endoscopic images by proposing a deep Bayesian active-learning-to-rank method that selects appropriate image pairs for relative annotation, achieving efficient training and handling class imbalance in ulcerative colitis datasets.
Automatic image-based disease severity estimation generally uses discrete (i.e., quantized) severity labels. Annotating discrete labels is often difficult due to the images with ambiguous severity. An easier alternative is to use relative annotation, which compares the severity level between image pairs. By using a learning-to-rank framework with relative annotation, we can train a neural network that estimates rank scores that are relative to severity levels. However, the relative annotation for all possible pairs is prohibitive, and therefore, appropriate sample pair selection is mandatory. This paper proposes a deep Bayesian active-learning-to-rank, which trains a Bayesian convolutional neural network while automatically selecting appropriate pairs for relative annotation. We confirmed the efficiency of the proposed method through experiments on endoscopic images of ulcerative colitis. In addition, we confirmed that our method is useful even with the severe class imbalance because of its ability to select samples from minor classes automatically.