Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 19, 2025npj Digital MedicineOpen Access

PathOrchestra: a comprehensive foundation model for computational pathology with over 100 diverse clinical-grade tasks

View Full Paper
Ask AI
Bookmark
Share

Authors

FYFang YanJWJianfeng WuJLJiawen Li

Discussion

Loading...

Member takes

Overview

PathOrchestra demonstrates 0.950 accuracy in whole slide images, highlighting advanced biomarker assessment and bladder cancer screening.

Key Points

  • The aim is to present PathOrchestra, a comprehensive foundation model for computational pathology.
  • Trained on 287,424 slides from 21 tissue types across three centers.
  • Evaluated on 112 tasks from private and public datasets.
  • Covered tasks include digital slide preprocessing and multi-cancer subtype classification.
  • Achieved over 0.950 accuracy in 47 tasks.
  • Included evaluations for bladder cancer screening and lymphoma subtyping.
  • First to generate structured reports for colorectal cancer and lymphoma.

Cite This Study

Yan et al. (2025) studied this question.

synapsesocial.com/papers/6924fed1c0ce034ddc350f99https://doi.org/10.1038/s41746-025-02027-w
View Full Paper
Ask AI
Bookmark
Share