A Novel Multi-Task Model Imitating Dermatologists for Accurate Differential Diagnosis of Skin Diseases in Clinical Images

TL;DR

This paper introduces DermImitFormer, a multi-task model that mimics dermatologists' diagnostic procedures by predicting body parts, lesion attributes, and diseases, leading to improved accuracy and interpretability in skin disease diagnosis.

Contribution

The paper presents a novel multi-task model with modules that imitate dermatologists' diagnostic strategies, including lesion selection and reasoning between features, and provides a large-scale dataset for evaluation.

Findings

Achieves state-of-the-art recognition performance on three datasets.

Effectively highlights local lesion features from noisy backgrounds.

Enhances diagnosis interpretability through multi-task learning.

Abstract

Skin diseases are among the most prevalent health issues, and accurate computer-aided diagnosis methods are of importance for both dermatologists and patients. However, most of the existing methods overlook the essential domain knowledge required for skin disease diagnosis. A novel multi-task model, namely DermImitFormer, is proposed to fill this gap by imitating dermatologists' diagnostic procedures and strategies. Through multi-task learning, the model simultaneously predicts body parts and lesion attributes in addition to the disease itself, enhancing diagnosis accuracy and improving diagnosis interpretability. The designed lesion selection module mimics dermatologists' zoom-in action, effectively highlighting the local lesion features from noisy backgrounds. Additionally, the presented cross-interaction module explicitly models the complicated diagnostic reasoning between body parts, lesion attributes, and diseases. To provide a more robust evaluation of the proposed method, a large-scale clinical image dataset of skin diseases with significantly more cases than existing datasets has been established. Extensive experiments on three different datasets consistently demonstrate the state-of-the-art recognition performance of the proposed approach.