Deep Learning-based Modeling for Preclinical Drug Safety Assessment.

Jaume, Guillaume; De Brot, Simone; Song, Andrew H; Williamson, Drew F K; Oldenburg, Lukas; Zhang, Andrew; Chen, Richard J; Asin, Javier; Blatter, Sohvi; Dettwiler, Martina; Goepfert, Christine; Grau-Roma, Llorenç; Soto, Sara; Keller, Stefan M; Rottenberg, Sven; Del-Pozo, Jorge; Pettit, Rowland; Le, Long Phi; Mahmood, Faisal (23 July 2024). Deep Learning-based Modeling for Preclinical Drug Safety Assessment. (bioRxiv). Cold Spring Harbor Laboratory 10.1101/2024.07.20.604430

Preview

Text 2024.07.20.604430v1.full.pdf - Published Version Available under License Creative Commons: Attribution-Noncommercial (CC-BY-NC). Download (10MB) | Preview

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.

Interest & Impact

Downloads

1 since deposited on 12 Aug 2024
1 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item