AI Science Tracker

UNI: a general-purpose foundation model for computational pathology

Mass General Brigham; Harvard Medical School · 19 Mar 2024 · medicine

Discovery

Mass General Brigham; Harvard Medical School

UNI: a general-purpose foundation model for computational pathology

Archived from discovery counts: this entry documents retrospective method benchmarks rather than a qualifying scientific discovery. UNI was pretrained on more than 100 million image patches from over 100,000 H&E whole-slide images across 20 major tissue types. Across 34 pathology tasks, including cancer classification and transplant-rejection assessment, it outperformed established pathology AI models. Evaluation is retrospective, and the weights are gated under a non-commercial academic licence.

Technology: UNI (self-supervised vision transformer foundation model for pathology)

Publication: Not annotated in this catalog · Test context: Not annotated in this catalog. Catalog categories, not an evidence grade.

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review scope and date are not recorded; source checked does not establish full-text review.

Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Follow-up and relationships

No follow-up recorded; this is not a claim that no follow-up exists.

Follow-up review scope and date are not recorded.

No source-supported relationships recorded.

Browse the current catalog.