DermDiff: Generative Diffusion Model for Mitigating Racial Biases in Dermatology Diagnosis
This addresses a critical fairness issue in healthcare AI for dermatology, though it is an incremental improvement in data augmentation methods.
The paper tackles racial biases in AI models for dermatology diagnosis by proposing DermDiff, a generative diffusion model that creates diverse dermoscopic images to improve dataset representation, resulting in enhanced performance for underrepresented skin tones.
Skin diseases, such as skin cancer, are a significant public health issue, and early diagnosis is crucial for effective treatment. Artificial intelligence (AI) algorithms have the potential to assist in triaging benign vs malignant skin lesions and improve diagnostic accuracy. However, existing AI models for skin disease diagnosis are often developed and tested on limited and biased datasets, leading to poor performance on certain skin tones. To address this problem, we propose a novel generative model, named DermDiff, that can generate diverse and representative dermoscopic image data for skin disease diagnosis. Leveraging text prompting and multimodal image-text learning, DermDiff improves the representation of underrepresented groups (patients, diseases, etc.) in highly imbalanced datasets. Our extensive experimentation showcases the effectiveness of DermDiff in terms of high fidelity and diversity. Furthermore, downstream evaluation suggests the potential of DermDiff in mitigating racial biases for dermatology diagnosis. Our code is available at https://github.com/Munia03/DermDiff