CIFoundry

Pathology AI tools

Digital pathology AI analyzes whole-slide images. It detects and grades cancer, quantifies biomarkers and helps pathologists prioritize cases, often alongside a lab moving from glass slides to scanners.

27
tools listed
6
FDA-cleared
5
with named health-system users

Well-documented pathology tools

Not a ranking. Shown A–Z.

How we picked these

Tools are picked automatically from four public signals recorded in each listing: FDA clearance, De Novo or approval; health systems named as users in news reports; a linked published study; and Epic integration. A tool needs at least 2 of the 4 to appear. Tools with more signals, then more reported health-system users, come first, until about 8 are shown. Tools that tie are shown together or not at all (never more than 10), so no tool is picked over another by name. “Well-documented” describes the public record, not clinical quality. This list is based on information recorded in each listing; a tool's absence doesn't mean it lacks these qualities. No one can pay to appear here, and advertising never affects this list.

Evaluating a pathology AI tool? Use our checklist

What physicians and administrators look for, evidence to ask for, how to test it locally, red flags and questions for the vendor. Jump straight to the tool type:

All 27 pathology AI tools

Listed A–Z. Listing is free, and no one can pay to change the order.

Pathology
FDA Breakthrough

PathChat (PathChat DX)

Mahmood Lab (Harvard Medical School / Mass General Brigham); licensed to Modella AI

PathChat is a multimodal generative AI copilot for pathology developed by the Mahmood Lab, combining the UNI vision encoder with a 13B-parameter Llama 2 LLM to answer diagnostic questions, describe morphology, and summarize reports from histology images. Published in Nature in 2024, it demonstrated state-of-the-art performance on pathology multiple-choice questions and was preferred by expert pathologists for open-ended queries. A clinical version, PathChat DX, received FDA Breakthrough Device Designation in January 2025 and is licensed to Modella AI.

  • FDAnot on record
  • Epicnot on record
  • Named usersnot on record
  • Studyon record
generative AIvision-language modelpathology copilot+3
Pathology
Research

UNI (Universal Pathology Foundation Model)

Mahmood Lab (Harvard Medical School / Brigham and Women's Hospital / Mass General Brigham)

UNI is a general-purpose, self-supervised vision foundation model for computational pathology developed by the Mahmood Lab, trained on over 100 million images from 100,000+ diagnostic H&E whole-slide images across 20 tissue types. It serves as a feature extractor for downstream tasks such as ROI classification, slide-level classification, and disease subtyping, achieving state-of-the-art results across 34 clinical benchmarks. UNI is widely used as a research backbone in digital pathology and was followed by the larger UNI 2 model.

  • FDAnot on record
  • Epicnot on record
  • Named usersnot on record
  • Studyon record
foundation modelcomputational pathologyself-supervised learning+3

Get weekly updates for Pathology

Up to 5 new items a week: new tools, FDA decisions and studies. Newest first, never ranked. Confirm by email, unsubscribe any time.

How to evaluate pathology AI

Regulatory status

Check whether the tool is FDA-cleared for the exact use you plan, or is a non-device or research tool. Every listing links to the FDA record where one exists.

Evidence

Look for peer-reviewed validation, ideally in patients and settings like yours, and ask vendors how performance is monitored after go-live.

Integration

Confirm how it fits your EHR and workflow (Epic, PACS, FHIR) and who does the integration work.

Peer adoption

See which health systems already use it and ask peers in the forum about real-world results.

Can't find the right fit? Browse builder firms that build custom pathology AI, or compare tools side by side.

Other specialties