ABSTRACT
An estimated 3 billion people lack access to dermatological care globally. Artificial intelligence (AI) may aid in triaging skin diseases and identifying malignancies. However, most AI models have not been assessed on images of diverse skin tones or uncommon diseases. Thus, we created the Diverse Dermatology Images (DDI) dataset-the first publicly available, expertly curated, and pathologically confirmed image dataset with diverse skin tones. We show that state-of-the-art dermatology AI models exhibit substantial limitations on the DDI dataset, particularly on dark skin tones and uncommon diseases. We find that dermatologists, who often label AI datasets, also perform worse on images of dark skin tones and uncommon diseases. Fine-tuning AI models on the DDI images closes the performance gap between light and dark skin tones. These findings identify important weaknesses and biases in dermatology AI that should be addressed for reliable application to diverse patients and diseases.
ABSTRACT
A 60-year-old Japanese man presented with multiple subcutaneous nodules in his left groin. Histologically, the nodules consisted of suppurative granulomas and abscesses not involving the hair follicles. Trichophyton rubrum TWCC57922 was detected by fungal culture and polymerase chain reaction (PCR) sequencing of the rDNA genes. We diagnosed these nodules as deeper dermal dermatophytosis, a rare form of invasive dermatophytosis. He was treated with terbinafine. We compared these findings with previous reports of deep dermal dermatophytosis.