An interpretable imbalanced semi-supervised deep learning framework for improving differential diagnosis of skin diseases

TL;DR

This paper introduces an interpretable semi-supervised deep learning framework for skin disease diagnosis that addresses class imbalance, achieves high accuracy, and provides explanations aligned with clinical diagnosis, aiding in rural healthcare.

Contribution

It presents the first interpretable semi-supervised framework for multiclass skin disease diagnosis with class rebalancing and explanation capabilities.

Findings

Achieved 97.9% accuracy in skin disease classification

Effectively handled class imbalance with pseudo-labeling

Provided clinically consistent explanations using SHAP

Abstract

Dermatological diseases are among the most common disorders worldwide. This paper presents the first study of the interpretability and imbalanced semi-supervised learning of the multiclass intelligent skin diagnosis framework (ISDL) using 58,457 skin images with 10,857 unlabeled samples. Pseudo-labelled samples from minority classes have a higher probability at each iteration of class-rebalancing self-training, thereby promoting the utilization of unlabeled samples to solve the class imbalance problem. Our ISDL achieved a promising performance with an accuracy of 0.979, sensitivity of 0.975, specificity of 0.973, macro-F1 score of 0.974 and area under the receiver operating characteristic curve (AUC) of 0.999 for multi-label skin disease classification. The Shapley Additive explanation (SHAP) method is combined with our ISDL to explain how the deep learning model makes predictions. This finding is consistent with the clinical diagnosis. We also proposed a sampling distribution optimisation strategy to select pseudo-labelled samples in a more effective manner using ISDLplus. Furthermore, it has the potential to relieve the pressure placed on professional doctors, as well as help with practical issues associated with a shortage of such doctors in rural areas.