Strabismus Detection Based on Uncertainty Estimation and Knowledge Distillation

Strabismus significantly impacts human health as a prevalent ophthalmic condition. Early detection of strabismus is crucial for effective treatment and prognosis. Traditional deep learning models for strabismus detection often fail to estimate prediction certainty precisely. This paper employed a Bayesian deep learning algorithm with knowledge distillation, improving the model's performance and uncertainty estimation ability. Trained on 6807 images from two tertiary hospitals, the model showed significantly higher diagnostic accuracy than traditional deep-learning models. Experimental results revealed that knowledge distillation enhanced the Bayesian model’s performance and uncertainty estimation ability. These findings underscore the combined benefits of using Bayesian deep learning algorithms and knowledge distillation, which improve the reliability and accuracy of strabismus diagnostic predictions.