Deep Learning-based Modeling for Preclinical Drug Safety Assessment.

Autor: Jaume G; Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA.; Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA.; Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA.; Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA., de Brot S; Institute of Animal Pathology, Vetsuisse, University of Bern, Switzerland.; COMPATH, Institute of Animal Pathology, University of Bern, Switzerland.; Bern Center for Precision Medicine, University of Bern, Switzerland., Song AH; Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA.; Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA.; Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA.; Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA., Williamson DFK; Department of Pathology & Laboratory Medicine, Emory University School of Medicine, Atlanta, GA., Oldenburg L; Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA., Zhang A; Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA.; Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA.; Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA.; Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA.; Health Sciences and Technology, Harvard-MIT, Cambridge, MA., Chen RJ; Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA.; Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA.; Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA.; Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA., Asin J; California Animal Health and Food Safety Laboratory, University of California-Davis, San Bernardino, CA.; School of Veterinary Medicine, Department of Pathology, University of California-Davis, Davis, CA., Blatter S; Institute of Animal Pathology, Vetsuisse, University of Bern, Switzerland., Dettwiler M; Vetscope Pathologie Dettwiler, Riehen, Switzerland., Goepfert C; Institute of Animal Pathology, Vetsuisse, University of Bern, Switzerland.; COMPATH, Institute of Animal Pathology, University of Bern, Switzerland., Grau-Roma L; Institute of Animal Pathology, Vetsuisse, University of Bern, Switzerland.; COMPATH, Institute of Animal Pathology, University of Bern, Switzerland., Soto S; Institute of Animal Pathology, Vetsuisse, University of Bern, Switzerland., Keller SM; Vetscope Pathologie Dettwiler, Riehen, Switzerland., Rottenberg S; Institute of Animal Pathology, Vetsuisse, University of Bern, Switzerland.; COMPATH, Institute of Animal Pathology, University of Bern, Switzerland.; Bern Center for Precision Medicine, University of Bern, Switzerland.; Department for BioMedical Research, University of Bern, Switzerland., Del-Pozo J; Royal (Dick) School of Veterinary Studies, Roslin, United-Kingdom., Pettit R; Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA.; Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA., Le LP; Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA.; Harvard Data Science Initiative, Harvard University, Cambridge, MA., Mahmood F; Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA.; Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA.; Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA.; Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA.; Harvard Data Science Initiative, Harvard University, Cambridge, MA.
Jazyk: angličtina
Zdroj: BioRxiv : the preprint server for biology [bioRxiv] 2024 Jul 23. Date of Electronic Publication: 2024 Jul 23.
DOI: 10.1101/2024.07.20.604430
Abstrakt: In drug development, assessing the toxicity of candidate compounds is crucial for successfully transitioning from preclinical research to early-stage clinical trials. Drug safety is typically assessed using animal models with a manual histopathological examination of tissue sections to characterize the dose-response relationship of the compound - a time-intensive process prone to inter-observer variability and predominantly involving tedious review of cases without abnormalities. Artificial intelligence (AI) methods in pathology hold promise to accelerate this assessment and enhance reproducibility and objectivity. Here, we introduce TRACE, a model designed for toxicologic liver histopathology assessment capable of tackling a range of diagnostic tasks across multiple scales, including situations where labeled data is limited. TRACE was trained on 15 million histopathology images extracted from 46,734 digitized tissue sections from 157 preclinical studies conducted on Rattus norvegicus . We show that TRACE can perform various downstream toxicology tasks spanning histopathological response assessment, lesion severity scoring, morphological retrieval, and automatic dose-response characterization. In an independent reader study, TRACE was evaluated alongside ten board-certified veterinary pathologists and achieved higher concordance with the consensus opinion than the average of the pathologists. Our study represents a substantial leap over existing computational models in toxicology by offering the first framework for accelerating and automating toxicological pathology assessment, promoting significant progress with faster, more consistent, and reliable diagnostic processes.
Databáze: MEDLINE