{"entity":{"id":"faisal-mahmood","kind":"person","name":"Faisal Mahmood","aka":[],"tldr":"Built UNI and CONCH, the pathology foundation models that let AI read whole-slide images across cancer types.","summary":"Faisal Mahmood's laboratory developed CLAM for weakly supervised whole-slide learning, TOAD for predicting tumour origin, and the UNI and CONCH foundation models trained on more than 100 million pathology images, which set the benchmark for general-purpose computational pathology. His group also builds multimodal models integrating histology with genomics for prognosis and is a leading academic voice on AI in pathology.","asOf":"2026-09-10","links":[{"label":"PubMed","url":"https://pubmed.ncbi.nlm.nih.gov/?term=Mahmood%20F%5BAuthor%5D%20computational%20pathology"}],"tags":["ai","pathology","foundation-models"],"related":[],"cancers":[],"sections":[],"technologies":["pathology-foundation-model","digital-pathology-ai"],"targets":[],"drugs":[],"companies":[],"institutions":["broad-institute"],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":["paper-alphafold2-jumper-nature-2021"],"journals":[],"dependsOn":[],"notes":[],"role":"Associate Professor of Pathology, Harvard Medical School and Brigham and Women's Hospital; Associate Member, Broad Institute","institutionId":"broad-institute","specialisms":["Computational pathology","Pathology foundation models","Multimodal AI","Weakly supervised learning"],"profiles":[{"label":"PubMed","url":"https://pubmed.ncbi.nlm.nih.gov/?term=Mahmood%20F%5BAuthor%5D%20computational%20pathology"}],"papers":[{"title":"Towards a general-purpose foundation model for computational pathology (UNI)","journal":"Nature Medicine","year":2024,"doi":"10.1038/s41591-024-02857-3"},{"title":"AI-based pathology predicts origins for cancers of unknown primary","journal":"Nature","year":2021,"doi":"10.1038/s41586-021-03512-4"},{"title":"Data-efficient and weakly supervised computational pathology on whole-slide images","journal":"Nature Biomedical Engineering","year":2021,"doi":"10.1038/s41551-020-00682-4"},{"title":"AlphaFold 2: predicting protein structures to near-experimental accuracy","journal":"Nature","year":2021,"url":"https://doi.org/10.1038/s41586-021-03819-2","doi":"10.1038/s41586-021-03819-2"}],"orcid":"0000-0001-7587-1562"},"route":"/people/faisal-mahmood/","neighbours":{"technology":[{"id":"digital-pathology-ai","kind":"technology","name":"Digital pathology & AI","route":"/technologies/digital-pathology-ai/"},{"id":"pathology-foundation-model","kind":"technology","name":"Pathology & radiology foundation models","route":"/technologies/pathology-foundation-model/"}],"institution":[{"id":"broad-institute","kind":"institution","name":"Broad Institute of MIT and Harvard","route":"/institutions/broad-institute/"}],"paper":[{"id":"paper-alphafold2-jumper-nature-2021","kind":"paper","name":"AlphaFold 2: predicting protein structures to near-experimental accuracy","route":"/key-papers/paper-alphafold2-jumper-nature-2021/"}]}}