Prov-GigaPath: a whole-slide foundation model for digital pathology
Archived from discovery counts: this paper introduces a foundation model and evaluates retrospective prediction benchmarks rather than reporting a separate biological finding or clinical field-study result. Prov-GigaPath was pretrained on 1.3 billion image tiles from 171,189 whole-slide images of more than 30,000 patients across 31 tissue types. It led on 25 of 26 evaluated tasks using both Providence and TCGA data, so evaluation was not confined to one health network. The historical entry is retained as method-development context, consistently with the archived UNI entry.
Technology: Prov-GigaPath (GigaPath vision transformer with LongNet dilated attention)
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.