{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:00:58Z","timestamp":1753891258665,"version":"3.41.2"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T00:00:00Z","timestamp":1747094400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>In non-clinical safety evaluation of drugs, pathological result is one of the gold standards for determining toxic effects. However, pathological diagnosis might be challenging and affected by pathologist expertise. In carcinogenicity studies, drug-induced squamous cell carcinoma (SCC) of the mouse stomach represents a diagnostic challenge for toxicopathologists. This study aims to establish a detection model for mouse gastric squamous cell carcinoma (GSCC) using deep learning algorithms, to improve the accuracy and consistency of pathological diagnoses.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 93 cases of drug-induced mouse GSCC and 56 cases of normal mouse stomach tissue from carcinogenicity studies were collected. After scanning into digital slides, semi-automated data annotation was performed. All images underwent preprocessing, including tissue extraction, artifact removal, and exclusion of normal epithelial regions. The images were then randomly divided into training, validation, and test sets in an 8:1:1 ratio. Five different convolutional neural networks (CNNs)-FCN, LR-ASPP, DeepLabv3+, U-Net, and DenseNet were applied to identify GSCC and non-GSCC regions. Tumor prediction images (algorithm results shown as overlays) derived from the slide images were compared, and the performance of the constructed models was evaluated using Precision, Recall, and F1-score.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The Precision, Recall, and F1-scores of DenseNet, U-Net, and DeepLabv3\u202f+\u202falgorithms were all above 90%. Specifically, the DenseNet model achieved an overall Precision of 0.9044, Recall of 0.9291, and F1-score of 0.9157 in the test set. Compared to the other algorithms, DenseNet exhibited the highest F1-score and Recall, demonstrating superior generalization ability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The DenseNet algorithm model developed in this study shown promising application potential for assisting in the diagnosis of mouse GSCC. As artificial intelligence (AI) technology continues to advance in non-clinical safety evaluation of drugs, CNN-based toxicological pathology detection models will become essential tools to assist pathologists in precise diagnosis and consistency evaluation.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1587417","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T05:29:32Z","timestamp":1747114172000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Application of deep learning convolutional neural networks to identify gastric squamous cell carcinoma in mice"],"prefix":"10.3389","volume":"12","author":[{"given":"Yuke","family":"Ren","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuangxing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongtian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guitao","family":"Huo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobing","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingchao","family":"Geng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,13]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"103747","DOI":"10.1016\/j.drudis.2023.103747","article-title":"Building a nonclinical pathology laboratory of the future for pharmaceutical research excellence","volume":"28","author":"Rudmann","year":"2023","journal-title":"Drug Discov Today"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1177\/0192623320983244","article-title":"Artificial intelligence in Toxicologic pathology: quantitative evaluation of compound-induced hepatocellular hypertrophy in rats","volume":"49","author":"Pischon","year":"2021","journal-title":"Toxicol Pathol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1177\/0192623320980674","article-title":"Deep learning in Toxicologic pathology: a new approach to evaluate rodent retinal atrophy","volume":"49","author":"Mudry","year":"2021","journal-title":"Toxicol Pathol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1177\/0192623320972614","article-title":"Using artificial intelligence to detect, classify, and objectively score severity of rodent cardiomyopathy","volume":"49","author":"Tokarz","year":"2021","journal-title":"Toxicol Pathol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1080\/10408444.2024.2314056","article-title":"Consideration of the variability in control tumor incidence data at the Ramazzini institute in evaluating treatment-related effects following chemical exposure","volume":"54","author":"Gentry","year":"2024","journal-title":"Crit Rev Toxicol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1080\/15376516.2020.1760986","article-title":"The 2-year rodent bioassay in drug and chemical carcinogenesis testing: sensitivity, according to the framework of carcinogenic action","volume":"30","author":"Suarez-Torres","year":"2020","journal-title":"Toxicol Mech Methods"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1002\/jmor.21496","article-title":"No news from old drawings? Stomach anatomy in muroid rodents in relation to body size and ecology","volume":"283","author":"Steiner","year":"2022","journal-title":"J Morphol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1016\/j.mehy.2011.07.032","article-title":"Induction the cornification of squamous cancerous cells to eliminate tumor cells by promotion cell differentiation and stratum","volume":"77","author":"Zhou","year":"2011","journal-title":"Med Hypotheses"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"85","DOI":"10.3969\/j.issn.1674-5817.2003.02.006","article-title":"Rat gastric carcinomas induced by administration of MNNG associated with high dose sodium-chloride diet","volume":"23","author":"Zhu","year":"2003","journal-title":"Shanghai Lab Anim Sci"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"656","DOI":"10.3969\/j.issn.1006-5709.2022.06.010","article-title":"Application and research of chronic atrophic gastritis model based on U-net deep learning","volume":"31","author":"Zhao","year":"2022","journal-title":"J Gastroenterol Hepatol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.compmedimag.2017.06.001","article-title":"Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology","volume":"61","author":"Sharma","year":"2017","journal-title":"Comput Med Imaging Graph"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1365550","DOI":"10.3389\/fonc.2024.1365550","article-title":"Machine learning models based on quantitative dynamic contrast-enhanced MRI parameters assess the expression levels of CD3+, CD4+, and CD8+ tumor-infiltrating lymphocytes in advanced gastric carcinoma","volume":"14","author":"Huang","year":"2024","journal-title":"Front Oncol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1111\/his.15153","article-title":"Pros and cons of artificial intelligence implementation in diagnostic pathology","volume":"84","author":"Diest","year":"2024","journal-title":"Histopathology"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"100357","DOI":"10.1016\/j.jpi.2023.100357","article-title":"Computational pathology: a survey review and the way forward","volume":"15","author":"Hosseini","year":"2024","journal-title":"J Pathol Inform"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1S","DOI":"10.1293\/tox.29.1S","article-title":"Nonproliferative and proliferative lesions of the gastrointestinal tract, pancreas and salivary glands of the rat and mouse","volume":"29","author":"Nolte","year":"2016","journal-title":"J Toxicol Pathol"},{"volume-title":"International norms for pathological terminology and diagnostic criteria of rats and mice (INHAND)","year":"2019","author":"Yang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"8044887","DOI":"10.1155\/2022\/8044887","article-title":"Breast Cancer classification using FCN and Beta wavelet autoencoder","volume":"2022","author":"AlEisa","year":"2022","journal-title":"Comput Intell Neurosci"},{"key":"ref18","first-page":"1314","article-title":"Searching for mobilenetv 3","author":"Howard","year":"2019"},{"key":"ref19","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"4189781","DOI":"10.1155\/2022\/4189781","article-title":"U-net-based medical image segmentation","volume":"2022","author":"Yin","year":"2022","journal-title":"J Healthc Eng"},{"key":"ref21","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.3115\/1072064.1072067","article-title":"MUC-4 evaluation metrics","author":"Chinchor","year":"1992"},{"volume-title":"Ji qi xue xi (machine learning) [in Chinese]","year":"2016","author":"Zhou","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"2095","DOI":"10.1007\/s00432-022-04187-8","article-title":"Looking at NSAIDs from a historical perspective and their current status in drug repurposing for cancer treatment and prevention","volume":"149","author":"Ozleyen","year":"2023","journal-title":"J Cancer Res Clin Oncol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1093\/carcin\/17.2.293","article-title":"Effect of selective and non-selective muscarinic blockade on baclofen inhibition of gastric carcinogenesis induced by N-methyl-N'-nitro-N-nitrosoguanidine in Wistar rats","volume":"17","author":"Tatsuta","year":"1996","journal-title":"Carcinogenesis"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1080\/13880209.2019.1710219","article-title":"Genome-wide transcriptional analysis of Aristolochia manshuriensis induced gastric carcinoma","volume":"58","author":"Wang","year":"2020","journal-title":"Pharm Biol"},{"volume-title":"*ICH Harmonised Guideline S1B (R1): Testing for Carcinogenicity of Pharmaceuticals*","year":"2022","key":"ref27"},{"volume-title":"Test No. 451: Carcinogenicity Studies. OECD Guidelines for the Testing of Chemicals, Section 4","year":"2018","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1177\/03009858211040484","article-title":"Whole-slide imaging, tissue image analysis, and artificial intelligence in veterinary pathology: an updated introduction and review","volume":"59","author":"Zuraw","year":"2022","journal-title":"Vet Pathol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1177\/0192623319827485","article-title":"Toxicologic pathology forum*: opinion on integrating innovative digital pathology tools in the regulatory framework","volume":"47","author":"Gauthier","year":"2019","journal-title":"Toxicol Pathol"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"42","DOI":"10.4103\/jpi.jpi_36_21","article-title":"Deep learning approaches and applications in Toxicologic histopathology: current status and future perspectives","volume":"12","author":"Mehrvar","year":"2021","journal-title":"J Pathol Inform"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med Image Anal"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1016\/j.neunet.2023.11.006","article-title":"A survey on cancer detection via convolutional neural networks: current challenges and future directions","volume":"169","author":"Sharma","year":"2024","journal-title":"Neural Netw"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"239","DOI":"10.3390\/jimaging10100239","article-title":"A survey on explainable artificial intelligence (XAI) techniques for visualizing deep learning models in medical imaging","volume":"10","author":"Bhati","year":"2024","journal-title":"J Imaging"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"102809","DOI":"10.1016\/j.media.2023.102809","article-title":"From modern CNNs to vision transformers: assessing the performance, robustness, and classification strategies of deep learning models in histopathology","volume":"87","author":"Springenberg","year":"2023","journal-title":"Med Image Anal"},{"volume-title":"Better together: Artificial intelligence approach improves accuracy in breast cancer diagnosis","year":"2016","author":"Prescott","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.ejca.2019.06.012","article-title":"(2019). Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images","volume":"118","author":"Hekler","year":"2019","journal-title":"Eur J Cancer"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"166","DOI":"10.12182\/20210360501","article-title":"Application and Progress of convolutional neural network-based pathological diagnosis of gastric Cancer","volume":"52","author":"Guo","year":"2021","journal-title":"J Sichuan Univ"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"63","DOI":"10.15912\/j.cnki.gocm.2023.28.052","article-title":"Progress in the clinical application of artificial intelligence deep learning in gastric Cancer","volume":"21","author":"Yang","year":"2023","journal-title":"China Med Guide"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"100335","DOI":"10.1016\/j.jpi.2023.100335","article-title":"Applications of discriminative and deep learning feature extraction methods for whole slide image analysis: a survey","volume":"14","author":"Al-Thelaya","year":"2023","journal-title":"J Pathol Inform."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"e036423","DOI":"10.1136\/bmjopen-2019-036423","article-title":"Automatic deep learning-based colorectal adenoma detection system and its similarities with pathologists","volume":"10","author":"Song","year":"2020","journal-title":"BMJ Open"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"1948","DOI":"10.1109\/TMI.2019.2891305","article-title":"Fast scan net: fast and dense analysis of multi-Gigapixel whole-slide images for Cancer metastasis detection","volume":"38","author":"Lin","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"3358","DOI":"10.1038\/s41598-019-40041-7","article-title":"Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks","volume":"9","author":"Wei","year":"2019","journal-title":"Sci Rep"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"18466","DOI":"10.1038\/s41598-022-22731-x","article-title":"Deep learning model to predict Epstein-Barr virus associated gastric cancer in histology","volume":"12","author":"Jeong","year":"2022","journal-title":"Sci Rep"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s00428-019-02653-2","article-title":"PD-L1 expression in gastric cancer determined by digital image analyses: pitfalls and correlation with pathologist interpretation","volume":"476","author":"Kim","year":"2020","journal-title":"Virchows Arch"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1587417\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T05:29:38Z","timestamp":1747114178000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1587417\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,13]]},"references-count":45,"alternative-id":["10.3389\/fmed.2025.1587417"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1587417","relation":{},"ISSN":["2296-858X"],"issn-type":[{"type":"electronic","value":"2296-858X"}],"subject":[],"published":{"date-parts":[[2025,5,13]]},"article-number":"1587417"}}