Health AI Central
Peer-Reviewed Publication
Nat Biomed Eng2026August 12, 2026Journal Article

Deep-learning triage of three-dimensional pathology datasets for comprehensive and efficient pathologist assessments.

Gan Gao1, Renao Yan1,2, Andrew H Song3,4,5, Huai-Ching Hsieh1,2,6,7, Lindsey A Erion Barner1, Fiona Wang1, David Brenes1,2, Sarah S L Chow1,2, Rui Wang1,2, Kevin W Bishop1,7, Yongjun Liu8, Xavier Farre9, Mukul Divatia8, Michelle R Downes10, Funda Vakar-Lopez8, Priti Lal11, Wynn Burke12,13, Anant Madabhushi14,15, Lawrence D True8, Deepti M Reddi8, William M Grady12,13, Faisal Mahmood3,16,17,18, Jonathan T C Liu19,20,21,22,23
1Department of Mechanical Engineering, University of Washington, Seattle, WA, USA.
2Department of Pathology, Stanford University School of Medicine, Stanford, CA, USA.
3Department of Pathology, Mass General Brigham, Harvard Medical School, Boston, MA, USA.
4Department of Translational Molecular Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
5Institute for Data Science in Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
6Department of Bioengineering, Stanford University, Stanford, CA, USA.
7Department of Bioengineering, University of Washington, Seattle, WA, USA.
8Department of Laboratory Medicine and Pathology, University of Washington, Seattle, WA, USA.
9Public Health Agency of Catalonia, Lleida, Spain.
10Division of Anatomic Pathology, Department of Laboratory Medicine and Molecular Diagnostics, Precision Diagnostics and Therapeutics Program, Sunnybrook Health Sciences Centre, Laboratory Medicine and Pathobiology, Toronto, Ontario, Canada.
11Pathology and Laboratory Medicine, University of Pennsylvania, Philadelphia, PA, USA.
12Department of Medicine, University of Washington, Seattle, WA, USA.
13The Translational Science and Therapeutics Division, Fred Hutchinson Cancer Research Center, Seattle, WA, USA.
14Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA.
15Atlanta Veterans Medical Center, Atlanta, GA, USA.
16Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA, USA.
17Data Science Program, Dana-Farber Cancer Institute, Boston, MA, USA.
18Harvard Data Science Initiative, Harvard University, Cambridge, MA, USA.
19Department of Mechanical Engineering, University of Washington, Seattle, WA, USA. jonliu@stanford.edu.
20Department of Pathology, Stanford University School of Medicine, Stanford, CA, USA. jonliu@stanford.edu.
21Department of Bioengineering, Stanford University, Stanford, CA, USA. jonliu@stanford.edu.
22Department of Bioengineering, University of Washington, Seattle, WA, USA. jonliu@stanford.edu.
23Department of Laboratory Medicine and Pathology, University of Washington, Seattle, WA, USA. jonliu@stanford.edu.
PubMed DOI

Abstract

Standard slide-based two-dimensional (2D) histopathology severely undersamples spatially heterogeneous tissue, with each thin 2D section representing <1% of the entire biopsy volume. Recent advances in non-destructive three-dimensional (3D) pathology, such as open-top light-sheet microscopy, enable comprehensive high-resolution imaging of large clinical specimens. Since manual review of these mass…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.