Accuracy of Foundation Artificial Intelligence Models for Hepatic Macrovesicular Steatosis Quantification in Frozen Sections.

Context.--Accurate intraoperative assessment of macrovesicular steatosis in donor liver biopsies is critical for transplant decisions but is often limited by interobserver variability and freezing artifacts that can obscure histologic details. Artificial intelligence (AI) offers a potential solution...

Descripción completa

Detalles Bibliográficos
Publicado en:Archives of Pathology & Laboratory Medicine Vol. 150; no. 5; pp. 374 - 381
Autores principales: Koga, Shunsuke, Guda, Anjani, Wang, Yujie, Sahni, Aarush, Wu, Jiahui, Rosen, Alyssa, Nield, Jaxson, Nandish, Nilan, Patel, Krunal, Goldman, Haviva, Rajapakse, Chamith S., Walle, Selemon, Stashek, Kristen, Tondon, Rashmi, Alipour, Zahra
Formato: pictorial research tables/charts Journal Article
Publicado: College of American Pathologists May2026
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=194029175&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 194029175
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        00039985
        1FS
      jtl: Archives of Pathology & Laboratory Medicine
      issn: 00039985
      maglogo: N
    pubinfo:
      dt: May2026
      vid: 150
      iid: 5
      pid: 2550
      pub: College of American Pathologists
      place: Northfield, Illinois
    artinfo:
      ui:
        194029175
        194029175
        194029175
        10.5858/arpa.2025-0232-OA
        194029175
      ppf: 374
      ppct: 7
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Accuracy of Foundation Artificial Intelligence Models for Hepatic Macrovesicular Steatosis Quantification in Frozen Sections.
      aug:
        au:
          Koga, Shunsuke
          Guda, Anjani
          Wang, Yujie
          Sahni, Aarush
          Wu, Jiahui
          Rosen, Alyssa
          Nield, Jaxson
          Nandish, Nilan
          Patel, Krunal
          Goldman, Haviva
          Rajapakse, Chamith S.
          Walle, Selemon
          Stashek, Kristen
          Tondon, Rashmi
          Alipour, Zahra
        affil: Departments of Pathology and Laboratory Medicine, Hospital of the University of Pennsylvania, Philadelphia
      sug:
        subj:
          Frozen Sections
          Fatty Liver Diagnosis
          Fatty Liver Pathology
          Artificial Intelligence
          Machine Learning Methods
          Biopsy
          Pathologists
          Liver Pathology
          Sensitivity and Specificity
          Human
          Male
          Female
          Adult
          Middle Age
          Observer Bias
          Retrospective Design
          Record Review
          Transplant Donors
          Liver Transplantation
          Image Processing, Computer Assisted
          Decision Making, Clinical
          Workflow Evaluation
          Quality Assessment
          Interprofessional Relations
          Prospective Studies
          Descriptive Statistics
          Comparative Studies
          McNemar's Test
          Confidence Intervals
          Adult: 19-44 years
          Middle Aged: 45-64 years
          Male
          Female
      ab: Context.--Accurate intraoperative assessment of macrovesicular steatosis in donor liver biopsies is critical for transplant decisions but is often limited by interobserver variability and freezing artifacts that can obscure histologic details. Artificial intelligence (AI) offers a potential solution for standardized and reproducible evaluation. Objective.--To evaluate the diagnostic performance of 2 self-supervised learning (SSL)--based foundation models, Prov-GigaPath and UNI, for classifying macrovesicular steatosis on frozen liver biopsy sections, compared with assessments by surgical pathologists. Design.--This retrospective study included 131 frozen liver biopsy specimens from 68 donors collected between November 2022 and September 2024. Slides were digitized into whole slide images, tiled into patches, and used to extract embeddings with Prov-GigaPath and UNI; slide-level classifiers were then trained and tested. Intraoperative diagnoses by on-call surgical pathologists were compared with ground truth determined from independent reviews of permanent sections by 2 liver pathologists. Accuracy was evaluated for both a 5-category classification and a clinically significant binary threshold (<30% versus ≥30%). Results.--For the binary classification, Prov-GigaPath achieved 96.4% accuracy, UNI 85.7%, and surgical pathologists, 89.3% (P = .37). For the 5-category classification, accuracies were lower: Prov-GigaPath, 57.1%; UNI, 50.0%; and pathologists, 64.2% (P = .47). Misclassification occurred mainly in intermediate categories (5% to <30% steatosis). Conclusions.--SSL-based foundation models performed comparably to surgical pathologists at the clinically relevant threshold of less than 30% versus 30% or greater. These findings support the potential role of AI in standardizing intraoperative evaluation of donor liver biopsies; however, the small sample size limits generalizability and requires validation in larger, balanced cohorts.
      pubtype: Academic Journal
      doctype:
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N