Deep learning-assisted cellular imaging for evaluating acrylamide toxicity through phenotypic changes

IF 3.9 3区医学 Q2 FOOD SCIENCE & TECHNOLOGY

Food and Chemical Toxicology Pub Date : 2025-03-19 DOI:10.1016/j.fct.2025.115401

Zhiyuan Ning , Yingming Zhang , Shikun Zhang , Xianfeng Lin , Lixin Kang , Nuo Duan , Zhouping Wang , Shijia Wu

{"title":"Deep learning-assisted cellular imaging for evaluating acrylamide toxicity through phenotypic changes","authors":"Zhiyuan Ning , Yingming Zhang , Shikun Zhang , Xianfeng Lin , Lixin Kang , Nuo Duan , Zhouping Wang , Shijia Wu","doi":"10.1016/j.fct.2025.115401","DOIUrl":null,"url":null,"abstract":"<div><div>Acrylamide (AA), a food hazard generated during thermal processing, poses significant safety risks due to its toxicity. Conventional methods for AA toxicology are time-consuming and inadequate for analyzing cellular morphology. This study developed a novel approach combining deep learning models (U-Net and ResNet34) with cell fluorescence imaging. U-Net was used for cell segmentation, generating a single-cell dataset, while ResNet34 trained the dataset over 200 epochs, achieving an 80 % validation accuracy. This method predicts AA concentration ranges by matching cell fluorescence features with the dataset and analyzes cellular phenotypic changes under AA exposure using k-means clustering and CellProfiler. The approach overcomes the limitations of traditional toxicological methods, offering a direct link between cell phenotypes and hazard toxicology. It provides a high-throughput, accurate solution to evaluate AA toxicology and refines the understanding of its cellular impacts.</div></div>","PeriodicalId":317,"journal":{"name":"Food and Chemical Toxicology","volume":"200 ","pages":"Article 115401"},"PeriodicalIF":3.9000,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Food and Chemical Toxicology","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0278691525001693","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"FOOD SCIENCE & TECHNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Acrylamide (AA), a food hazard generated during thermal processing, poses significant safety risks due to its toxicity. Conventional methods for AA toxicology are time-consuming and inadequate for analyzing cellular morphology. This study developed a novel approach combining deep learning models (U-Net and ResNet34) with cell fluorescence imaging. U-Net was used for cell segmentation, generating a single-cell dataset, while ResNet34 trained the dataset over 200 epochs, achieving an 80 % validation accuracy. This method predicts AA concentration ranges by matching cell fluorescence features with the dataset and analyzes cellular phenotypic changes under AA exposure using k-means clustering and CellProfiler. The approach overcomes the limitations of traditional toxicological methods, offering a direct link between cell phenotypes and hazard toxicology. It provides a high-throughput, accurate solution to evaluate AA toxicology and refines the understanding of its cellular impacts.

Abstract Image

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Food and Chemical Toxicology 工程技术-毒理学

CiteScore

10.90

自引率

4.70%

发文量

651

审稿时长

31 days

期刊介绍： Food and Chemical Toxicology (FCT), an internationally renowned journal, that publishes original research articles and reviews on toxic effects, in animals and humans, of natural or synthetic chemicals occurring in the human environment with particular emphasis on food, drugs, and chemicals, including agricultural and industrial safety, and consumer product safety. Areas such as safety evaluation of novel foods and ingredients, biotechnologically-derived products, and nanomaterials are included in the scope of the journal. FCT also encourages submission of papers on inter-relationships between nutrition and toxicology and on in vitro techniques, particularly those fostering the 3 Rs. The principal aim of the journal is to publish high impact, scholarly work and to serve as a multidisciplinary forum for research in toxicology. Papers submitted will be judged on the basis of scientific originality and contribution to the field, quality and subject matter. Studies should address at least one of the following: -Adverse physiological/biochemical, or pathological changes induced by specific defined substances -New techniques for assessing potential toxicity, including molecular biology -Mechanisms underlying toxic phenomena -Toxicological examinations of specific chemicals or consumer products, both those showing adverse effects and those demonstrating safety, that meet current standards of scientific acceptability. Authors must clearly and briefly identify what novel toxic effect (s) or toxic mechanism (s) of the chemical are being reported and what their significance is in the abstract. Furthermore, sufficient doses should be included in order to provide information on NOAEL/LOAEL values.