Lab

Mahmood Lab

Part of Harvard Medical School

A computational pathology lab at Harvard Medical School and Brigham and Women's Hospital, building open models for cancer diagnosis and prognosis.

Website
9 models(8 Pathology, 2 Spatial omics, 1 Language model, 1 Imaging)

Models (9)

SEAL

Mahmood Lab / University of Cambridge / Télécom Paris

Released February 15, 2026

448

Vision-omics finetuning that aligns pathology foundation models with spatial transcriptomics so morphology features predict local gene expression.

PathologySpatial omics

ABMIL

Mahmood Lab / Brigham and Women's Hospital

Released July 15, 2025

2.7K40153

Attention-based multiple instance learning heads for whole-slide pathology, pretrained on a 108-way pan-cancer slide classification task.

Pathology

KRONOS

Mahmood Lab / Brigham and Women's Hospital / Harvard Medical School / Broad Institute / Dana-Farber Cancer Institute / Beth Israel Deaconess Medical Center / Stanford University / The Ohio State University / University of Tübingen

Released June 3, 2025

32584204

Spatial proteomics foundation model, marker-aware and panel-agnostic, pretrained on 47 million multiplexed tissue-imaging patches from 175 markers.

Spatial omicsPathology

TITAN

Mahmood Lab / Brigham and Women's Hospital / Helmholtz Munich / University of Tokyo

Released November 29, 2024

218124.5K357

Slide-level pathology foundation model turning whole-slide images into reusable embeddings for classification, retrieval, and report generation.

Pathology

MADELEINE

Mahmood Lab / Brigham and Women's Hospital

Released August 5, 2024

4567

Slide-level pathology foundation model that learns whole-slide embeddings by aligning multiple stains of the same tissue during pretraining.

Pathology

PathChat

Mahmood Lab / Brigham and Women's Hospital / Harvard Medical School / Massachusetts General Hospital / The Ohio State University

Released July 10, 2024

476

Multimodal vision-language copilot for pathology that answers open-ended questions about histology images and reasons about differential diagnoses.

PathologyLanguage model

HEST Tissue Segmentation

Mahmood Lab

Released June 23, 2024

161422

DeepLabV3 segmentation model that separates tissue from glass background in H&E and IHC whole-slide images, as used by the HEST-Library.

Pathology

UNI

Mahmood Lab

Released March 22, 2024

1.6K59.6K761

Computational pathology foundation model (ViT-L/16, DINOv2) pretrained on over 100 million H&E tiles from more than 100,000 whole-slide images.

Pathology

CONCH

Mahmood Lab / Brigham and Women's Hospital

Released March 19, 2024

1K69.8K518

Histopathology vision-language foundation model pretrained on 1.17 million image-caption pairs with contrastive and captioning objectives.

Imaging