Improving Racial Equity in Skin Cancer Detection: Leveraging Artificial Intelligence Driven Synthetic Image Generation, Cascading Convolutional Neural Networks, and Affordable Diagnostic Hardware for Accurate Cancer Screening Across All Skin Tones

Skin cancer affects millions of people each year, yet both physicians and artificial intelligence systems often perform less accurately on patients with darker skin tones because of limited training data. In this project, I developed an artificial intelligence framework that generates synthetic images of skin lesions in darker skin and uses them to train a more equitable diagnostic model. To improve accessibility, I also designed a low-cost handheld device capable of capturing images and providing rapid skin cancer screening, helping expand access to accurate diagnosis across diverse communities.

• Medicine
• Artificial Intelligence