{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T10:33:21Z","timestamp":1793442801002,"version":"4.5.0"},"reference-count":26,"publisher":"Radiation Research Society","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Radiation Research"],"published-print":{"date-parts":[[2020,12,14]]},"abstract":"<jats:p>The interpretation of radiation dose is an important procedure for both radiological operators and persons who are exposed to background or artificial radiations. Dicentric chromosome assay (DCA) is one of the representative methods of dose estimation that discriminates the aberration in chromosomes modified by radiation. Despite the DCA-based automated radiation dose estimation methods proposed in previous studies, there are still limitations to the accuracy of dose estimation. In this study, a DCA-based automated dose estimation system using deep learning methods is proposed. The system is comprised of three stages. In the first stage, a classifier based on a deep learning technique is used for filtering the chromosome images that are not appropriate for use in distinguishing the chromosome; 99% filtering accuracy was achieved with 2,040 test images. In the second stage, the dicentric rate is evaluated by counting and identifying chromosomes based on the Feature Pyramid Network, which is one of the object detection algorithms based on deep learning architecture. The accuracies of the neural networks for counting and identifying chromosomes were estimated at over 97% and 90%, respectively. In the third stage, dose estimation is conducted using the dicentric rate and the dose-response curve. The accuracies of the system were estimated using two independent samples; absorbed doses ranging from 1\u2013 4 Gy agreed well within a 99% confidential interval showing highest accuracy compared to those in previous studies. The goal of this study was to provide insights towards achieving complete automation of the radiation dose estimation, especially in the event of a large-scale radiation exposure incident.<\/jats:p>","DOI":"10.1667\/rade-20-00167.1","type":"journal-article","created":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T09:07:22Z","timestamp":1612170442000},"page":"163-172","source":"Crossref","is-referenced-by-count":9,"title":["Feasibility Study on Automatic Interpretation of Radiation Dose Using Deep Learning Technique for Dicentric Chromosome Assay"],"prefix":"10.1667","volume":"195","author":[{"given":"Seungsoo","family":"Jang","sequence":"first","affiliation":[{"name":"Division of Advanced Nuclear Engineering, POSTECH, 77 Cheongam-Ro, Nam-Gu, Pohang 37673, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung-Gyun","family":"Shin","sequence":"additional","affiliation":[{"name":"Division of Advanced Nuclear Engineering, POSTECH, 77 Cheongam-Ro, Nam-Gu, Pohang 37673, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min-Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"Division of Advanced Nuclear Engineering, POSTECH, 77 Cheongam-Ro, Nam-Gu, Pohang 37673, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sangsoo","family":"Han","sequence":"additional","affiliation":[{"name":"Division of Advanced Nuclear Engineering, POSTECH, 77 Cheongam-Ro, Nam-Gu, Pohang 37673, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chan-Ho","family":"Choi","sequence":"additional","affiliation":[{"name":"Division of Advanced Nuclear Engineering, POSTECH, 77 Cheongam-Ro, Nam-Gu, Pohang 37673, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungkyum","family":"Kim","sequence":"additional","affiliation":[{"name":"Division of Advanced Nuclear Engineering, POSTECH, 77 Cheongam-Ro, Nam-Gu, Pohang 37673, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Woo-Sung","family":"Cho","sequence":"additional","affiliation":[{"name":"Division of Advanced Nuclear Engineering, POSTECH, 77 Cheongam-Ro, Nam-Gu, Pohang 37673, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song-Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Division of Advanced Nuclear Engineering, POSTECH, 77 Cheongam-Ro, Nam-Gu, Pohang 37673, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeong-Rok","family":"Kang","sequence":"additional","affiliation":[{"name":"Dongnam Institute of Radiological and Medical Science, 40 Jwadong-Gil, Jangan-Eup, Gijang-Gun, Busan, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wolsoon","family":"Jo","sequence":"additional","affiliation":[{"name":"Dongnam Institute of Radiological and Medical Science, 40 Jwadong-Gil, Jangan-Eup, Gijang-Gun, Busan, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sookyung","family":"Jeong","sequence":"additional","affiliation":[{"name":"Dongnam Institute of Radiological and Medical Science, 40 Jwadong-Gil, Jangan-Eup, Gijang-Gun, Busan, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sujung","family":"Oh","sequence":"additional","affiliation":[{"name":"Dongnam Institute of Radiological and Medical Science, 40 Jwadong-Gil, Jangan-Eup, Gijang-Gun, Busan, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1243","reference":[{"key":"4","doi-asserted-by":"crossref","unstructured":"A Vral, M Fenech, H Thierens,  \"Mutagenesis.\"  26, \"The micronucleus assay as a biological dosimeter of in vivo ionising radiation exposure.\" 11 (2011)","DOI":"10.1093\/mutage\/geq078"},{"key":"16","unstructured":"et al.  \"Cytogenetic dosimetry: applications in preparedness for and response to radiation emergencies.\"  ,  (2011)"},{"key":"1","unstructured":"H Romm, U Oestreicher, U Kulka,  \"Ann Ist Super Sanita.\"  45, \"Cytogenetic damage analysed by the dicentric assay.\" 251 (2009)"},{"key":"3","doi-asserted-by":"crossref","unstructured":"S Balakrishnan, K Shirsath, N Bhat, et al.  \"Mutat Res.\"  699, \"Biodosimetry for high dose accidental exposures by drug induced premature chromosome condensation (PCC) assay.\" 11 (2010)","DOI":"10.1016\/j.mrgentox.2010.03.008"},{"key":"2","doi-asserted-by":"crossref","unstructured":"C Beinke  and V Meineke  \"Health Phys.\"  103, \"High potential for methodical improvements of FISH-based translocation analysis for retrospective radiation biodosimetry.\" 127 (2012)","DOI":"10.1097\/HP.0b013e31824645fb"},{"key":"5","doi-asserted-by":"crossref","unstructured":"Y Lee, YW Jin, RC Wilkins, et al.  \"J Radiat Res.\"  60, \"Validation of the dicentric chromosome assay for radiation biological dosimetry in South Korea.\" 555 (2019)","DOI":"10.1093\/jrr\/rrz039"},{"key":"6","doi-asserted-by":"crossref","unstructured":"Y Li, JH Knoll, RC Wilkins, et al.  \"Microsc Res Tech.\"  79, \"Automated discrimination of dicentric and monocentric chromosomes by machine learning-based image processing.\" 393 (2016)","DOI":"10.1002\/jemt.22642"},{"key":"7","doi-asserted-by":"crossref","unstructured":"B Shirley, Y Li, JH Knoll, et al.  \"J Vis Exp.\"  127, \"Expedited radiation biodosimetry by automated dicentric chromosome identification (ADCI) and dose estimation.\" 56245 (2017)","DOI":"10.3791\/56245-v"},{"key":"8","doi-asserted-by":"crossref","unstructured":"TL Ryan, MB Escalona, TL Smith, et al.  \"Mutat Res Gen Tox En.\"  847, \"Optimization and validation of automated dicentric chromosome analysis for radiological\/nuclear triage applications.\" 503087 (2019)","DOI":"10.1016\/j.mrgentox.2019.503087"},{"key":"9","doi-asserted-by":"crossref","unstructured":"X Shen, Y Qi, T Ma, et al.  \"Sci Rep.\"  9, \"A dicentric chromosome identification method based on clustering and watershed algorithm.\" 2285 (2019)","DOI":"10.1038\/s41598-019-38614-7"},{"key":"10","doi-asserted-by":"crossref","unstructured":"H Dai, J Feng, H Bian, et al.  \"Dose Response.\"  16, \"Complete technical scheme for automatic biological dose estimation platform.\" 1559325818799951 (2018)","DOI":"10.1177\/1559325818799951"},{"key":"11","doi-asserted-by":"crossref","unstructured":"JM. Cho,  \"IEEE Eng Med Biol.\"  19, \"Chromosome classification using backpropagation neural networks.\" 28 (2000)","DOI":"10.1109\/51.816241"},{"key":"12","doi-asserted-by":"crossref","unstructured":"JM Cho, SY Ryu, SH Woo,  \"IEEE Eng Med Biol.\"  2, \"A study for the hierarchical artificial neural network model for giemsa-stained human chromosome classification.\" 4588 (2004)","DOI":"10.1109\/IEMBS.2004.1404272"},{"key":"13","doi-asserted-by":"crossref","unstructured":"S. Delshadpour,  \"IEEE Eng Med Biol.\"  3, \"Reduced size multi layer perceptron neural network for human chromosome classification.\" 2249 (2003)","DOI":"10.1109\/IEMBS.2003.1280243"},{"key":"14","doi-asserted-by":"crossref","unstructured":"Swati, G Gupta, M Yadav, et al.  \"IEEE Int Conf Comput Vis Workshops.\"  , \"Siamese networks for chromosome classification.\" 72 (2018)","DOI":"10.1109\/ICCVW.2017.17"},{"key":"15","doi-asserted-by":"crossref","unstructured":"M Sharma, O Saha, A Sriraman, et al.  \"Proc IEEE Conf Comput Vis Pattern Recognit Workshops.\"  , \"Crowdsourcing for chromosome segmentation and deep classification.\" 786 (2017)","DOI":"10.1109\/CVPRW.2017.109"},{"key":"17","doi-asserted-by":"crossref","unstructured":"C Szegedy, V Vanhoucke, S Ioffe, et al.  \"Comput Vis Pattern Recognit.\"  , \"Rethinking the inception architecture for computer vision.\" 2818 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"18","doi-asserted-by":"crossref","unstructured":"T Lin, P Dollar, R Girshick, et al.  \"Comput Vis Pattern Recognit.\"  , \"Feature pyramid networks for object detection.\" 2117 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"19","doi-asserted-by":"crossref","unstructured":"R Girshick, J Donahue, T Darrell, et al.  \"Comput Vis Pattern Recognit.\"  , \"Rich feature hierarchies for accurate object detection and semantic segmentation.\" 580 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"20","doi-asserted-by":"crossref","unstructured":"S Ren, K He, R Girshick, et al.  \"Faster R-CNN: Towards real-time object detection with region proposal networks.\"  ,  (2016)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"21","doi-asserted-by":"crossref","unstructured":"C Szegedy, S Ioffe, V Vanhoucke, et al.  \"Inception-v4, Inception-ResNet and the impact of residual connections on learning.\"  ,  (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"22","doi-asserted-by":"crossref","unstructured":"M. Rosenblatt,  \"Proc Natl Acad Sci U S A.\"  42, \"A central limit theorem and a strong mixing condition.\" 43 (1956)","DOI":"10.1073\/pnas.42.1.43"},{"key":"23","unstructured":"M Abadi, A Agarwal, P Barham, et al.  \"TensorFlow: Large-scale machine learning on heterogeneous distributed systems.\"  ,  (2016)"},{"key":"24","unstructured":"et al.  \"The OpenCV reference manual, release 2.4.13.7.\"  ,  (2019)"},{"key":"25","unstructured":"K Simonyan  and A Zisserman  \"Very deep convolutional networks for large-scale image recognition.\"  ,  (2015)"},{"key":"26","unstructured":"DP Kingma  and J Ba  \"ADAM: A method for stochastic optimization.\"  ,  (2017)"}],"container-title":["Radiation Research"],"original-title":[],"deposited":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T10:07:54Z","timestamp":1793441274000},"score":1,"resource":{"primary":{"URL":"https:\/\/bioone.org\/journals\/radiation-research\/volume-195\/issue-2\/RADE-20-00167.1\/Feasibility-Study-on-Automatic-Interpretation-of-Radiation-Dose-Using-Deep\/10.1667\/RADE-20-00167.1.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":26,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,2,1]]}},"URL":"https:\/\/doi.org\/10.1667\/rade-20-00167.1","relation":{},"ISSN":["0033-7587","1938-5404"],"issn-type":[{"value":"0033-7587","type":"print"},{"value":"1938-5404","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,14]]}}}