DermX: an end-to-end framework for explainable automated dermatological diagnosis

TL;DR

DermX and DermX+ are explainable deep learning frameworks for dermatological diagnosis that achieve near-expert accuracy while providing transparent explanations aligned with dermatologist reasoning.

Contribution

The paper introduces DermX and DermX+, novel end-to-end explainable dermatology diagnosis models trained on a dermatologist-annotated dataset, bridging the gap between accuracy and explainability in clinical AI.

Findings

DermX and DermX+ achieve F1 scores of 0.79, close to dermatologist performance.

Explainability metrics show high alignment with dermatologist explanations.

Models maintain high diagnostic accuracy without sacrificing interpretability.

Abstract

Dermatological diagnosis automation is essential in addressing the high prevalence of skin diseases and critical shortage of dermatologists. Despite approaching expert-level diagnosis performance, convolutional neural network (ConvNet) adoption in clinical practice is impeded by their limited explainability, and by subjective, expensive explainability validations. We introduce DermX and DermX+, an end-to-end framework for explainable automated dermatological diagnosis. DermX is a clinically-inspired explainable dermatological diagnosis ConvNet, trained using DermXDB, a 554 image dataset annotated by eight dermatologists with diagnoses, supporting explanations, and explanation attention maps. DermX+ extends DermX with guided attention training for explanation attention maps. Both methods achieve near-expert diagnosis performance, with DermX, DermX+, and dermatologist F1 scores of 0.79, 0.79, and 0.87, respectively. We assess the explanation performance in terms of identification and localization by comparing model-selected with dermatologist-selected explanations, and gradient-weighted class-activation maps with dermatologist explanation maps, respectively. DermX obtained an identification F1 score of 0.77, while DermX+ obtained 0.79. The localization F1 score is 0.39 for DermX and 0.35 for DermX+. These results show that explainability does not necessarily come at the expense of predictive power, as our high-performance models provide expert-inspired explanations for their diagnoses without lowering their diagnosis performance.