Robust Skin Disease Classification by Distilling Deep Neural Network Ensemble for the Mobile Diagnosis of Herpes Zoster

Herpes zoster (HZ) is a common cutaneous disease affecting one out of five people; hence, early diagnosis of HZ is crucial as it can progress to chronic pain syndrome if antiviral treatment is not provided within 72 hr. Mobile diagnosis of HZ with the assistance of artificial intelligence can prevent neuropathic pain while reducing clinicians' fatigue and diagnosis cost. However, the clinical images captured from daily mobile devices likely contain visual corruptions, such as motion blur and noise, which can easily mislead the automated system. Hence, this paper aims to train a robust and mobile deep neural network (DNN) that can distinguish HZ from other skin diseases using user-submitted images. To enhance robustness while retaining low computational cost, we propose a knowledge distillation from ensemble via curriculum training (KDE-CT) wherein a student network learns from a stronger teacher network progressively. We established skin diseases dataset for HZ diagnosis and evaluated the robustness against 75 types of corruption. A total of 13 different DNNs was evaluated on both clean and corrupted images. The experiment result shows that the proposed KDE-CT significantly improves corruption robustness when compared with other methods. Our trained MobileNetV3-Small achieved more robust performance (93.5% overall accuracy, 67.6 mean corruption error) than the DNN ensemble with smaller computation (549x fewer multiply-and-accumulate operations), which makes it suitable for mobile skin lesion analysis.

Automated summary

The paper introduces a mobile diagnosis technique using artificial intelligence to assist in early detection of herpes zoster, and proposes a knowledge distillation strategy to train a robust and mobile deep neural network for distinguishing HZ from other skin diseases. Experimental results show that the proposed method significantly improves corruption robustness.