{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T21:59:43Z","timestamp":1791237583524,"version":"4.1.0"},"reference-count":17,"publisher":"Radiation Research Society","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Radiation Research"],"published-print":{"date-parts":[[2026,2,3]]},"abstract":"<jats:p>Radiation dose assessment in exposed individuals relies on the dicentric assay, the gold-standard cytogenetic bio-dosimeter that quantifies radiation-induced chromosomal aberrations. Although fully automated methods have been proposed, their accuracy remains suboptimal for large-scale emergency response. Here, we present a hybrid, semi-automatic framework that couples a deep-learning-based dicentric classifier with expert review. Among 2 000 metaphase images analyzed with a semi-automatic method, the specificity was 99.8%, the accuracy 98.7%, and the area under the curve (AUC) 0.977. For radiation dose estimation, the system achieved a minimal deviation of 9.25% and a maximal deviation of 15%. By integrating rapid AI triage with targeted human confirmation, the platform improves the high throughput required for population-scale triage while preserving the diagnostic rigor demanded by retrospective dose reconstruction.<\/jats:p>","DOI":"10.1667\/rade-25-00227.1","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T19:02:27Z","timestamp":1770836547000},"page":"318-321","source":"Crossref","is-referenced-by-count":0,"title":["AI-Assisted Chromosome Aberration Analysis for Rapid Biological Dose Estimation of Ionizing Radiation"],"prefix":"10.1667","volume":"205","author":[{"given":"Ping","family":"Wang","sequence":"first","affiliation":[{"name":"Guangdong Province Hospital for Occupational Disease Prevention and Treatment, Guangzhou 510300, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingyi","family":"Peng","sequence":"additional","affiliation":[{"name":"Xiamen Hanshujie Medical Technology Company Limited, Xiamen 361012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifang","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Province Hospital for Occupational Disease Prevention and Treatment, Guangzhou 510300, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Li","sequence":"additional","affiliation":[{"name":"Xiamen Hanshujie Medical Technology Company Limited, Xiamen 361012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zhao","sequence":"additional","affiliation":[{"name":"Guangdong Province Hospital for Occupational Disease Prevention and Treatment, Guangzhou 510300, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1243","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"P. Voisin,  \"Mutat Res Genet Toxicol Environ Mutagen.\"  793, \"Standards in biological dosimetry: A requirement to perform an appropriate dose assessment.\" 115 (2015)","DOI":"10.1016\/j.mrgentox.2015.06.012"},{"key":"3","unstructured":"\"ISO 19238: radiation protection - performance criteria for service laboratories performing biological dosimetry by cytogenetics.\"  (2023)"},{"key":"5","doi-asserted-by":"crossref","unstructured":"G Snigiryova, H Braselmann, K Salassidis, et al.  \"Int J Radiat Biol.\"  71, \"Retrospective biodosimetry of Chernobyl clean-up workers using chromosome painting and conventional chromosome analysis.\" 119 (1997)","DOI":"10.1080\/095530097144247"},{"key":"8","doi-asserted-by":"crossref","unstructured":"SK Jeong, SJ Oh, S-H Kim, et al.  \"Sci Rep.\"  12, \"Dicentric chromosome assay using a deep learning-based automated system.\" 22097 (2022)","DOI":"10.1038\/s41598-022-25856-1"},{"key":"9","doi-asserted-by":"crossref","unstructured":"G Gruel, E Gr\u00e9goire, S Lecas, et al.  \"Radiat Res.\"  179, \"Biological dosimetry by automated dicentric scoring in a simulated emergency.\" 557 (2013)","DOI":"10.1667\/RR3196.1"},{"key":"10","doi-asserted-by":"crossref","unstructured":"R M'Kacher, EEL Maalouf, M Ricoul, et al.  \"Mutat Res.\"  770, \"New tool for biological dosimetry: reevaluation and automation of the gold standard method following telomere and centromere staining.\" 45 (2014)","DOI":"10.1016\/j.mrfmmm.2014.09.007"},{"key":"12","doi-asserted-by":"crossref","unstructured":"K He, G Gkioxari, P Dollar, et al.  \"IEEE Trans Pattern Anal Mach Intell.\"  42, \"Mask R-CNN.\" 386 (2018)","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"13","doi-asserted-by":"crossref","unstructured":"J Bai, J Zhu, R Zhao, et al.  \"Front Optoelectron.\"  13, \"Area-based non-maximum suppression algorithm for multi-object fault detection.\" 425 (2020)","DOI":"10.1007\/s12200-020-0967-5"},{"key":"14","doi-asserted-by":"crossref","unstructured":"X Shen, T Ma, C Li, et al.  \"Sci Rep.\"  13, \"High-precision automatic identification method for dicentric chromosome images using two-stage convolutional neural network.\" 2124 (2023)","DOI":"10.1038\/s41598-023-28456-9"},{"key":"15","doi-asserted-by":"crossref","unstructured":"R Huang, C Lin, A Yin, et al.  \"IEEE\/ACM Trans Comput Biol Bioinform.\"  19, \"A Clinical Dataset and Various Baselines for Chromosome Instance Segmentation.\" 31 (2022)","DOI":"10.1109\/TCBB.2021.3089507"},{"key":"16","doi-asserted-by":"crossref","unstructured":"L Mei, Y Yu, H Shen, et al.  \"Entropy (Basel).\"  24, \"Adversarial Multiscale Feature Learning Framework for Overlapping Chromosome Segmentation.\" (2022)","DOI":"10.3390\/e24040522"},{"key":"17","doi-asserted-by":"crossref","unstructured":"K Kim, KS Kim, WI Jang, et al.  \"Diagnostics (Basel).\"  13, \"Deep Neural Network-Based Automatic Dicentric Chromosome Detection Using a Model Pretrained on Common Objects.\" (2023)","DOI":"10.3390\/diagnostics13203191"},{"key":"6","doi-asserted-by":"crossref","unstructured":"Y Suto, M Hirai, M Akiyama, et al.  \"Health Phys.\"  105, \"Biodosimetry of restoration workers for the Tokyo Electric Power Company (TEPCO) Fukushima Daiichi nuclear power station accident.\" 366 (2013)","DOI":"10.1097\/HP.0b013e3182995e42"},{"key":"2","doi-asserted-by":"crossref","unstructured":"H Romm, RC Wilkins, CN Coleman, et al.  \"Radiat Res.\"  175, \"Biological dosimetry by the triage dicentric chromosome assay: potential implications for treatment of acute radiation syndrome in radiological mass casualties.\" 397 (2011)","DOI":"10.1667\/RR2321.1"},{"key":"4","doi-asserted-by":"crossref","unstructured":"I Hayata, R Kanda, M Minamihisamatsu, et al.  \"J Radiat Res.\"  42, \"Cytogenetical dose estimation for 3 severely exposed patients in the JCO criticality accident in Tokai-mura.\" S149 (2001)","DOI":"10.1269\/jrr.42.S149"},{"key":"11","unstructured":"\"Cytogenetic Dosimetry: Applications in Preparedness for and Response to Radiation Emergencies.\"  (2011)"},{"key":"7","doi-asserted-by":"crossref","unstructured":"C Capaccio, JR Perrier, L Cunha, et al.  \"Radiat Res.\"  196, \"CytoRADx: A high-throughput, standardized biodosimetry diagnostic system based on the cytokinesis-block micronucleus assay.\" 523 (2021)","DOI":"10.1667\/RADE-20-00030.1"}],"container-title":["Radiation Research"],"original-title":[],"link":[{"URL":"https:\/\/radiation-research.kglmeridian.com\/view\/journals\/rare\/aop\/article-10.1667-RADE-25-00227.1\/article-10.1667-RADE-25-00227.1.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/radiation-research.kglmeridian.com\/downloadpdf\/journals\/rare\/aop\/article-10.1667-RADE-25-00227.1\/article-10.1667-RADE-25-00227.1.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/radiation-research.kglmeridian.com\/downloadpdf\/journals\/rare\/aop\/article-10.1667-RADE-25-00227.1\/article-10.1667-RADE-25-00227.1.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T21:23:44Z","timestamp":1791235424000},"score":1,"resource":{"primary":{"URL":"https:\/\/bioone.org\/journals\/radiation-research\/volume-205\/issue-3\/RADE-25-00227.1\/AI-Assisted-Chromosome-Aberration-Analysis-for-Rapid-Biological-Dose-Estimation\/10.1667\/RADE-25-00227.1.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":17,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,1]]}},"URL":"https:\/\/doi.org\/10.1667\/rade-25-00227.1","relation":{},"ISSN":["0033-7587","1938-5404"],"issn-type":[{"value":"0033-7587","type":"print"},{"value":"1938-5404","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]}}}