Uncertainty-aware ensemble of foundation models differentiates glioblastoma from its mimics

Junhan Zhao, Shih-Yen Lin, Raphaël Attias, Liza Mathews, Christian Engel, Guillaume Larghero, Dmytro Vremenko, Ting-Wan Kao, Tsung-Hua Lee, Yu-Hsuan Wang, Cheng Che Tsai, Eliana Marostica, Ying-Chun Lo, David Meredith, Keith L. Ligon, Omar Arnaout, Thomas Roetzer-Pejrimovsky, Shih-Chieh Lin, Natalie NC Shih, Nipon Chaisuriya, David J. Cook, Jung-Hsien Chiang, Chia-Jen Liu, Adelheid Woehrer, Jeffrey A. Golden, MacLean P. Nasrallah and Kun-Hsing Yu ()
Additional contact information
Junhan Zhao: Harvard Medical School
Shih-Yen Lin: Harvard Medical School
Raphaël Attias: Harvard Medical School
Liza Mathews: Harvard Medical School
Christian Engel: Harvard Medical School
Guillaume Larghero: Harvard Medical School
Dmytro Vremenko: Harvard Medical School
Ting-Wan Kao: Harvard Medical School
Tsung-Hua Lee: Harvard Medical School
Yu-Hsuan Wang: National Cheng Kung University
Cheng Che Tsai: Harvard Medical School
Eliana Marostica: Harvard Medical School
Ying-Chun Lo: Mayo Clinic
David Meredith: Brigham and Women’s Hospital
Keith L. Ligon: Dana-Farber Cancer Institute
Omar Arnaout: Brigham and Women’s Hospital
Thomas Roetzer-Pejrimovsky: Medical University of Vienna
Shih-Chieh Lin: Taipei Veterans General Hospital
Natalie NC Shih: Perelman School of Medicine at the University of Pennsylvania
Nipon Chaisuriya: Mayo Clinic
David J. Cook: Mayo Clinic
Jung-Hsien Chiang: National Cheng Kung University
Chia-Jen Liu: Harvard Medical School
Adelheid Woehrer: Medical University of Vienna
Jeffrey A. Golden: Cedars-Sinai Medical Center
MacLean P. Nasrallah: Perelman School of Medicine at the University of Pennsylvania
Kun-Hsing Yu: Harvard Medical School

Nature Communications, 2025, vol. 16, issue 1, 1-16

Abstract: Abstract Accurate pathological diagnosis is crucial in guiding personalized treatments for patients with central nervous system cancers. Distinguishing glioblastoma and primary central nervous system lymphoma is particularly challenging due to their overlapping pathology features, despite the distinct treatments required. To address this challenge, we establish the Pathology Image Characterization Tool with Uncertainty-aware Rapid Evaluations (PICTURE) system using 2141 pathology slides collected worldwide. PICTURE employs Bayesian inference, deep ensemble, and normalizing flow to account for the uncertainties in its predictions and training set labels. PICTURE accurately diagnoses glioblastoma and primary central nervous system lymphoma with an area under the receiver operating characteristic curve (AUROC) of 0.989, with the results validated in five independent cohorts (AUROC = 0.924-0.996). In addition, PICTURE identifies samples belonging to 67 types of rare central nervous system cancers that are neither gliomas nor lymphomas. Our approaches provide a generalizable framework for differentiating pathological mimics and enable rapid diagnoses for central nervous system cancer patients.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-64249-6 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-64249-6

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-64249-6

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().