Enhancing Safety in Diabetic Retinopathy Detection: Uncertainty-Aware Deep Learning Models with Rejection Capabilities
This work addresses safety risks in clinical diagnosis of diabetic retinopathy by enhancing model reliability, though it is incremental as it builds on existing uncertainty estimation methods.
The paper tackled the problem of uncertainty in deep learning models for diabetic retinopathy detection by introducing an uncertainty-aware model with a rejection mechanism for low-confidence predictions, resulting in improved reliability with trade-offs between accuracy and coverage demonstrated through metrics like Accuracy on accepted predictions and Expected Calibration Error.
Diabetic retinopathy (DR) is a major cause of visual impairment, and effective treatment options depend heavily on timely and accurate diagnosis. Deep learning models have demonstrated great success identifying DR from retinal images. However, relying only on predictions made by models, without any indication of model confidence, creates uncertainty and poses significant risk in clinical settings. This paper investigates an alternative in uncertainty-aware deep learning models, including a rejection mechanism to reject low-confidence predictions, contextualized by deferred decision-making in clinical practice. The results show there is a trade-off between prediction coverage and coverage reliability. The Variational Bayesian model adopted a more conservative strategy when predicting DR, subsequently rejecting the uncertain predictions. The model is evaluated by means of important performance metrics such as Accuracy on accepted predictions, the proportion of accepted cases (coverage), the rejection-ratio, and Expected Calibration Error (ECE). The findings also demonstrate a clear trade-off between accuracy and caution, establishing that the use of uncertainty estimation and selective rejection improves the model's reliability in safety-critical diagnostic use cases.