Addressing Bias and Data Scarcity in AI-Based Skin Disease Diagnosis with Non-Dermoscopic Images

AI-based diagnosis of skin diseases holds considerable promise for increasing healthcare accessibility, however, its effectiveness is currently limited by several challenges, including fairness. This study analyzes a real-world dataset collected from an Italian hospital, characterized by limited data availability, leading to poor diversity and representation—particularly evident in the scarcity of data for certain diseases and darker skin tones. Such limitations result in substantial classification biases. Additionally, the dataset includes non-dermoscopic, consumer-grade images that suffer from quality issues like inconsistent lighting and blurriness, complicating the training of fair and efficient AI models. Conventional strategies to mitigate these problems, such as synthesizing images for underrepresented groups, are hindered by the difficulty in accurately identifying skin tones from poor-quality images. Our research introduces a novel pipeline designed to enhance both the accuracy and fairness of skin disease diagnosis by addressing the challenges posed by real-world data. The proposed solution involves a two-stage approach: 1) data pre-processing and augmentation to obtain images that more accurately represent darker skin tones, generated through a state-of-the-art diffusion model; and 2) disease classification employing deep learning models. This methodology addresses data scarcity and improves fairness, with thorough validation of real-world data showing enhanced reliability and fairness in predictions across various skin diseases.