We build AI systems to predict cancer outcomes and treatment toxicity at scale — integrating clinical, histopathologic, and spatial data across one of the largest melanoma and immunotherapy cohorts globally.
Improving how we predict, prevent, and treat cancer — patient by patient.
We operate at the intersection of clinical oncology, artificial intelligence, and genomics — building tools that improve outcomes for patients with melanoma, skin cancer, immune-mediated disease, and life-threatening immunotherapy toxicities.
Multimodal AI integrating clinical data and digital pathology to predict recurrence and progression in early-stage melanoma — outperforming standard staging, validated across independent cohorts, and designed to guide adjuvant therapy decisions. AUROC 0.845 internal / 0.812 external validation.
Explore melanoma AI research
Multiplex imaging (t-CyCIF, ORION) and spatial transcriptomics reveal tumor–immune interactions, stromal features, and AI-driven spatial biomarkers of treatment response and disease progression.
Learn more
We study immune-related adverse events (irAEs) as both clinical challenges and biological signals — operating one of the largest irAE cohorts globally (24,000+ patients), linking toxicity phenotypes to survival outcomes, and establishing international consensus definitions (JITC 2024, Chen & Semenov et al.).
Learn moreOur work sits at the intersection of artificial intelligence, oncology, and dermatology — translating large-scale computational discoveries into tools that directly improve how patients with melanoma and immunotherapy toxicities are diagnosed, stratified, and treated.
Risk stratification and treatment guidance for melanoma patients — directly integrated into clinical workflows at MGH.
Tens of thousands of patients across multi-institutional datasets, among the largest in the field.
From computational model to clinical trial — our discoveries move from data to bedside.
Moving beyond TNM staging toward individualized, AI-driven prediction for every patient.
Melanoma kills over 8,000 Americans annually, and immunotherapy toxicities affect hundreds of thousands of cancer patients worldwide — yet clinicians still lack reliable tools to predict who is at risk. The Semenov Lab is at the forefront of applying AI at the intersection of dermatology and oncology to change this. Our research has already produced guidelines used globally, machine learning tools that predict melanoma recurrence with greater accuracy than standard staging, large multi-institutional digital pathology cohorts in melanoma, and pharmacovigilance systems that identify drug toxicities at health-system scale.
Dr. Semenov is a dermatologist and clinician-scientist with expertise in applied mathematics, biostatistics, epidemiology, and clinical informatics in melanoma. He is co-Director of the MGH Oncodermatology Program and Assistant Professor of Dermatology at Harvard Medical School, where he has built a nationally and internationally recognized research program at the interface of cutaneous oncology, AI in skin disease, and dermatology precision medicine.
He co-chairs data governance for ASPIRE, a national irAE registry, and serves on the Scientific Advisory Board of the RARE Registry for rare melanoma. He leads a federally funded dermatology informatics and AI in oncology research program and serves as Statistics Editor for JAAD, Associate Editor for the International Journal of Dermatology, and Associate Editor for npj Digital Medicine. He holds active leadership roles including: DataDerm Oversight Committee, American Academy of Dermatology; Co-Chair of Research, Oncodermatology Society; Co-Chair of Data Governance, ASPIRE (Alliance for Support and Prevention of Immune-Related Events); and member of the RARE Registry Oversight Committee through the Melanoma Research Alliance.
From MGH to Harvard Medical School, our work spans the most innovative biomedical research ecosystem in the world.
The lab operates across multiple Harvard-affiliated institutions in the greater Boston area, enabling deep collaboration across clinical care, cancer research, and computational biology.
Dr. Semenov is a board-certified dermatologist and internationally recognized expert in cutaneous oncology and oncodermatology. He provides comprehensive, multidisciplinary care for patients with melanoma and skin cancer across all stages of disease, patients experiencing skin toxicities from checkpoint blockade and other cancer treatments, and patients with complex immune-mediated skin disease and inflammatory skin disease arising from cancer therapy. He has contributed to the development of clinical guidelines for the diagnosis and management of immunotherapy-related skin toxicities and receives referrals from across the United States. Since its launch in 2022, the MGH Oncodermatology Program has grown to 600+ referrals annually and serves as a national model — adopted by institutions across the US and internationally.
