LesionTABE: Equitable AI for Skin Lesion Detection
By: Rocio Mexia Diaz, Yasmin Greenway, Petru Manescu
Potential Business Impact:
Helps AI see skin problems on all skin colors.
Bias remains a major barrier to the clinical adoption of AI in dermatology, as diagnostic models underperform on darker skin tones. We present LesionTABE, a fairness-centric framework that couples adversarial debiasing with dermatology-specific foundation model embeddings. Evaluated across multiple datasets covering both malignant and inflammatory conditions, LesionTABE achieves over a 25\% improvement in fairness metrics compared to a ResNet-152 baseline, outperforming existing debiasing methods while simultaneously enhancing overall diagnostic accuracy. These results highlight the potential of foundation model debiasing as a step towards equitable clinical AI adoption.
Similar Papers
A Deep Learning Approach for Automated Skin Lesion Diagnosis with Explainable AI
CV and Pattern Recognition
Helps doctors spot skin cancer faster and better.
Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learning
CV and Pattern Recognition
Helps doctors spot skin problems fairly on all skin.
The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective
Machine Learning (CS)
Makes medical predictions fair for everyone.