{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:32:02Z","timestamp":1779337922757,"version":"3.51.4"},"reference-count":38,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T00:00:00Z","timestamp":1655337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003569","name":"Ministry of Food and Drug Safety","doi-asserted-by":"publisher","award":["20183MFDS411"],"award-info":[{"award-number":["20183MFDS411"]}],"id":[{"id":"10.13039\/501100003569","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Although drug-induced liver injury (DILI) is a major target of the pharmaceutical industry, we currently lack an efficient model for evaluating liver toxicity in the early stage of its development. Recent progress in artificial intelligence-based deep learning technology promises to improve the accuracy and robustness of current toxicity prediction models. Mask region-based CNN (Mask R-CNN) is a detection-based segmentation model that has been used for developing algorithms. In the present study, we applied a Mask R-CNN algorithm to detect and predict acute hepatic injury lesions induced by acetaminophen (APAP) in Sprague-Dawley rats. To accomplish this, we trained, validated, and tested the model for various hepatic lesions, including necrosis, inflammation, infiltration, and portal triad. We confirmed the model performance at the whole-slide image (WSI) level. The training, validating, and testing processes, which were performed using tile images, yielded an overall model accuracy of 96.44%. For confirmation, we compared the model\u2019s predictions for 25 WSIs at 20\u00d7 magnification with annotated lesion areas determined by an accredited toxicologic pathologist. In individual WSIs, the expert-annotated lesion areas of necrosis, inflammation, and infiltration tended to be comparable with the values predicted by the algorithm. The overall predictions showed a high correlation with the annotated area. The R square values were 0.9953, 0.9610, and 0.9445 for necrosis, inflammation plus infiltration, and portal triad, respectively. The present study shows that the Mask R-CNN algorithm is a useful tool for detecting and predicting hepatic lesions in non-clinical studies. This new algorithm might be widely useful for predicting liver lesions in non-clinical and clinical settings.<\/jats:p>","DOI":"10.3390\/diagnostics12061478","type":"journal-article","created":{"date-parts":[[2022,6,17]],"date-time":"2022-06-17T01:48:12Z","timestamp":1655430492000},"page":"1478","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Artificial Intelligence-Assisted Image Analysis of Acetaminophen-Induced Acute Hepatic Injury in Sprague-Dawley Rats"],"prefix":"10.3390","volume":"12","author":[{"given":"Eun Bok","family":"Baek","sequence":"first","affiliation":[{"name":"College of Veterinary Medicine, Chungnam National University, Daejeon 34134, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji-Hee","family":"Hwang","sequence":"additional","affiliation":[{"name":"Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon 34114, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heejin","family":"Park","sequence":"additional","affiliation":[{"name":"Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon 34114, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byoung-Seok","family":"Lee","sequence":"additional","affiliation":[{"name":"Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon 34114, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hwa-Young","family":"Son","sequence":"additional","affiliation":[{"name":"College of Veterinary Medicine, Chungnam National University, Daejeon 34134, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong-Bum","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon 34114, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sang-Yeop","family":"Jun","sequence":"additional","affiliation":[{"name":"Research & Development Team, LAC Inc., Seoul 07807, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Her","sequence":"additional","affiliation":[{"name":"Research & Development Team, LAC Inc., Seoul 07807, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaeku","family":"Lee","sequence":"additional","affiliation":[{"name":"Research & Development Team, LAC Inc., Seoul 07807, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae-Woo","family":"Cho","sequence":"additional","affiliation":[{"name":"Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon 34114, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,6,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.1016\/j.ajpath.2019.05.007","article-title":"Pathology Image Analysis Using Segmentation Deep Learning Algorithms","volume":"189","author":"Wang","year":"2019","journal-title":"Am. J. Pathol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1038\/s41374-020-00514-0","article-title":"Artificial intelligence and computational pathology","volume":"101","author":"Cui","year":"2021","journal-title":"Lab. Investig."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1002\/path.5331","article-title":"Computational pathology definitions, best practices, and recommendations for regulatory guidance: A white paper from the Digital Pathology Association","volume":"249","author":"Abels","year":"2019","journal-title":"J. Pathol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1177\/0300985817709888","article-title":"The Pathologist 2.0: An Update on Digital Pathology in Veterinary Medicine","volume":"54","author":"Bertram","year":"2017","journal-title":"Vet. Pathol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1093\/ilar\/ily007","article-title":"Digital Microscopy, Image Analysis, and Virtual Slide Repository","volume":"59","author":"Aeffner","year":"2018","journal-title":"ILAR J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1177\/0192623320969130","article-title":"A Workflow for the Performance of the Differential Ovarian Follicle Count Using Deep Neuronal Networks","volume":"49","author":"Carboni","year":"2021","journal-title":"Toxicol. Pathol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1038\/s41598-018-37638-9","article-title":"Convolutional neural networks can accurately distinguish four histologic growth patterns of lung adenocarcinoma in digital slides","volume":"9","author":"Gertych","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1177\/01926233211057128","article-title":"Implementation and Practice of Deep Learning-Based Instance Segmentation Algorithm for Quantification of Hepatic Fibrosis at Whole Slide Level in Sprague-Dawley Rats","volume":"50","author":"Hwang","year":"2022","journal-title":"Toxicol. Pathol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"8351725","DOI":"10.1155\/2020\/8351725","article-title":"An Improved Mask R-CNN Model for Multiorgan Segmentation","volume":"2020","author":"Shu","year":"2020","journal-title":"Math. Probl. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hsia, C.H., Chang, T.H.W., Chiang, C.Y., and Chan, H.T. (2022). Mask R-CNN with New Data Augmentation Features for Smart Detection of Retail Products. Appl. Sci., 12.","DOI":"10.3390\/app12062902"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1159\/000514393","article-title":"Acute Liver Failure due to Hepatitis A Virus","volume":"15","author":"Shammout","year":"2021","journal-title":"Case Rep. Gastroenterol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1159\/000362442","article-title":"Acute liver injury in a patient with alcohol dependence: A case resembling autoimmune hepatitis or drug-induced liver injury","volume":"8","author":"Hayashi","year":"2014","journal-title":"Case Rep. Gastroenterol."},{"key":"ref_13","first-page":"73","article-title":"Drug-induced Liver Injury","volume":"6","author":"David","year":"2010","journal-title":"US Gastroenterol. Hepatol. Rev."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kang, M.G., and Kang, N.S. (2021). Predictive Model for Drug-Induced Liver Injury Using Deep Neural Networks Based on Substructure Space. Molecules, 26.","DOI":"10.3390\/molecules26247548"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1136\/jcp.2008.058248","article-title":"Histological patterns in drug-induced liver disease","volume":"62","author":"Ramachandran","year":"2009","journal-title":"J. Clin. Pathol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Papackova, Z., Heczkova, M., Dankova, H., Sticova, E., Lodererova, A., Bartonova, L., Poruba, M., and Cahova, M. (2018). Silymarin prevents acetaminophen-induced hepatotoxicity in mice. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0191353"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"42","DOI":"10.3389\/fphar.2019.00042","article-title":"Deep Neural Network Models for Predicting Chemically Induced Liver Toxicity Endpoints From Transcriptomic Responses","volume":"10","author":"Wang","year":"2019","journal-title":"Front. Pharmacol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.1021\/acs.jcim.5b00238","article-title":"Deep Learning for Drug-Induced Liver Injury","volume":"55","author":"Xu","year":"2015","journal-title":"J. Chem. Inf. Model."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"672","DOI":"10.3748\/wjg.v25.i6.672","article-title":"Artificial intelligence in medical imaging of the liver","volume":"25","author":"Zhou","year":"2019","journal-title":"World J. Gastroenterol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Decharatanachart, P., Chaiteerakij, R., Tiyarattanachai, T., and Treeprasertsuk, S. (2021). Application of artificial intelligence in chronic liver diseases: A systematic review and meta-analysis. BMC Gastroenterol., 21.","DOI":"10.1186\/s12876-020-01585-5"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/s11154-021-09681-x","article-title":"Applications of artificial intelligence (AI) in researches on non-alcoholic fatty liver disease (NAFLD): A systematic review","volume":"23","author":"Li","year":"2022","journal-title":"Rev. Endocr. Metab. Disord."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.tox.2007.10.010","article-title":"The potential protective role of alpha-lipoic acid against acetaminophen-induced hepatic and renal damage","volume":"243","author":"Mahmoud","year":"2008","journal-title":"Toxicology"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3246","DOI":"10.1016\/j.fct.2010.08.034","article-title":"Potential protective effects of quercetin and curcumin on paracetamol-induced histological changes, oxidative stress, impaired liver and kidney functions and haematotoxicity in rat","volume":"48","author":"Yousef","year":"2010","journal-title":"Food Chem. Toxicol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Baek, E.B., Rho, J.H., Jung, E., Seo, C.S., Kim, J.H., and Kwun, H.J. (2021). Protective effect of Palmijihwanghwan in a mouse model of cigarette smoke and lipopolysaccharide-induced chronic obstructive pulmonary disease. BMC Complement. Med. Ther., 21.","DOI":"10.1186\/s12906-021-03453-5"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1038\/s41379-021-00919-2","article-title":"Digital pathology and artificial intelligence in translational medicine and clinical practice","volume":"35","author":"Baxi","year":"2022","journal-title":"Mod. Pathol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"100443","DOI":"10.1016\/j.jhepr.2022.100443","article-title":"Artificial intelligence in liver diseases: Improving diagnostics, prognostics and response prediction","volume":"4","author":"Nam","year":"2022","journal-title":"JHEP Rep."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"129889","DOI":"10.1109\/ACCESS.2020.3006362","article-title":"Liver Cancer Detection Using Hybridized Fully Convolutional Neural Network Based on Deep Learning Framework","volume":"8","author":"Dong","year":"2020","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"18454","DOI":"10.1038\/s41598-019-54904-6","article-title":"Deep learning enables pathologist-like scoring of NASH models","volume":"9","author":"Heinemann","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"16016","DOI":"10.1038\/s41598-018-34300-2","article-title":"Deep learning enables automated scoring of liver fibrosis stages","volume":"8","author":"Yu","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"109","DOI":"10.3109\/15360288.2014.908993","article-title":"Patient perception and knowledge of acetaminophen in a large family medicine service","volume":"28","author":"Herndon","year":"2014","journal-title":"J. Pain Palliat. Care Pharmacother."},{"key":"ref_31","first-page":"131","article-title":"Acetaminophen-Induced Hepatotoxicity: A Comprehensive Update","volume":"4","author":"Yoon","year":"2016","journal-title":"J. Clin. Transl. Hepatol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"638410","DOI":"10.3389\/frai.2021.638410","article-title":"The Promise of AI for DILI Prediction","volume":"4","author":"Vall","year":"2021","journal-title":"Front. Artif. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Sahota, P.S., Popp, J.A., Hardisty, J.F., and Gopinath, C. (2013). Toxicologic Pathology: Nonclinical Safety Assessment, CRC Press.","DOI":"10.1201\/b13783"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"5S","DOI":"10.1177\/0192623310386499","article-title":"Proliferative and nonproliferative lesions of the rat and mouse hepatobiliary system","volume":"38","author":"Thoolen","year":"2010","journal-title":"Toxicol. Pathol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"100347","DOI":"10.1016\/j.patter.2021.100347","article-title":"Addressing bias in big data and AI for health care: A call for open science","volume":"2","author":"Norori","year":"2021","journal-title":"Patterns"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1038\/s41379-021-00948-x","article-title":"Integrating digital pathology into clinical practice (Oct, 10.1038\/s41379-021-00929-0, 2021)","volume":"35","author":"Hanna","year":"2022","journal-title":"Mod. Pathol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1186\/s13000-019-0921-2","article-title":"Next generation diagnostic pathology: Use of digital pathology and artificial intelligence tools to augment a pathological diagnosis","volume":"14","author":"Parwani","year":"2019","journal-title":"Diagn. Pathol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-014-0007-7","article-title":"Deep learning applications and challenges in big data analytics","volume":"2","author":"Najafabadi","year":"2015","journal-title":"J. Big Data"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/12\/6\/1478\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:33:21Z","timestamp":1760139201000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/12\/6\/1478"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,16]]},"references-count":38,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,6]]}},"alternative-id":["diagnostics12061478"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics12061478","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,16]]}}}