Dermatology Imaging Informatics & AI: Data, Context and Clinical Reality | Dr. Veronica Rotemberg

Description

Artificial intelligence is rapidly entering dermatology — but what does it actually take to make AI work in real clinical practice?In this episode of Imaging Informatics Unplugged, Jason Nagels sits down with Dr. Veronica Rotemberg, Director of Dermatology Informatics and Research at Memorial Sloan Kettering Cancer Center, to explore how dermatology is navigating AI, data quality, and real-world implementation challenges.Dermatology is one of the most image-driven specialties in medicine, yet its imaging workflows have evolved very differently from those in radiology and pathology. As AI models promise improved diagnostic performance, new questions emerge around benchmarking, overfitting, clinical context, and bias.In this conversation, we cover:• Why AI became a forcing function for dermatology informatics• The limits of single-image benchmarking and reader studies• The “ugly duckling” concept in melanoma detection• Overfitting risks from lighting, markers, camera differences, and workflow artifacts• Skin tone bias in AI models and why labelling is harder than it sounds• Why testing AI in its intended clinical use setting is critical⸻⏱ Chapters00:00 – Introduction: Dermatology & Imaging Informatics02:33 – Dr. Rotemberg’s Journey into Dermatology Informatics05:26 – The AI Inflection Point (2017) and the Data Wake-Up Call07:58 – The “Wild West” of Dermatology Image Capture09:42 – AI Hype vs. Clinical Reality11:17 – Where AI Actually Fits in Dermatology Today12:45 – Single-Image Benchmarking and Reader Studies15:23 – The “Ugly Duckling” Concept Explained17:58 – Overfitting: Lighting, Cameras, and Workflow Artifacts18:42 – Augmentation Strategies and Hidden Bias Signals21:22 – Skin Tone Bias in Dermatology AI24:47 – Testing AI in the Intended Clinical Use Setting26:09 – The Future of Dermatology Informatics27:38 – “You’re an Informaticist. You Just Don’t Know It Yet.”⸻Dr. Rotemberg holds a PhD in Biomedical Engineering, leads an NIH-funded AI and informatics research lab, chairs the Augmented Intelligence Committee