{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T10:57:03Z","timestamp":1790852223443,"version":"4.1.0"},"reference-count":48,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR\u201020\u2010ASTR\u20100005"],"award-info":[{"award-number":["ANR\u201020\u2010ASTR\u20100005"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR\u201010\u2010INBS\u201004\u201007"],"award-info":[{"award-number":["ANR\u201010\u2010INBS\u201004\u201007"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011697","name":"R\u00e9gion Bretagne","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011697","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Cytometry Pt A"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>In biological dosimetry a radiation dose is estimated using the average number of chromosomal aberrations per peripheral blood lymphocytes. This analysis is still manually performed on 2D metaphase images depicting the 23 pairs of chromosomes because the false discovery rate of current automated detection systems is too high and variable because of sensitivity to small variations in image quality (chromosome spread, illumination variations \u2026). Therefore, the current systems are only used to assist human experts. Designing more performant automatic and reliable chromosomal aberration detection systems has become of paramount importance to improve diagnosis speed and reduce human expertise time. Here, we propose a novel deep\u2010learning method for automatic rare chromosomal aberration detection and uncertainty quantification. We formulate the problem as a unique regression problem requiring the minimization of a sparsity\u2010promoting loss to reduce the false alarm rate. Furthermore, we select checkpoints at the end of each epoch during training to form a model ensemble. The resulting artificial experts are further analyzed to derive a consensus voting, similar to an agreement of human annotator rating, to provide trustworthy aberration detections and confidence intervals. A radiation dose curve is finally derived from deep learning\u2010assisted counting of dicentrics and fragments in metaphase images, in high agreement with the reference hand\u2010crafted curve in biological dosimetry with a promising dose estimation validation.<\/jats:p>","DOI":"10.1002\/cyto.a.70042","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:31:16Z","timestamp":1781598676000},"page":"485-499","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Ensembling Unets for Rare Chromosomal Aberration Detection in Metaphase Images, Uncertainty Quantification, and Ionizing Radiation Dose Estimation"],"prefix":"10.1002","volume":"109","author":[{"given":"Antonin","family":"Deschemps","sequence":"first","affiliation":[{"name":"SAIRPICO Project\u2010Team, Inria Center at University of Rennes, Institut Curie, Cellular and Chemical Biology Unit (U1339 INSERM, UMR3666 CNRS) PSL Research University  Rennes France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Gr\u00e9goire","sequence":"additional","affiliation":[{"name":"SERAMED\/LRAcc, Radiobiology and Regenerative Medicine Research Service, Radiobiology of Accidental Exposure Laboratory ASNR\u2014French Authority for Nuclear Safety and Radiation Protection  Fontenay\u2010aux\u2010Roses France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan S.","family":"Martinez","sequence":"additional","affiliation":[{"name":"SERAMED\/LRAcc, Radiobiology and Regenerative Medicine Research Service, Radiobiology of Accidental Exposure Laboratory ASNR\u2014French Authority for Nuclear Safety and Radiation Protection  Fontenay\u2010aux\u2010Roses France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edmond D.","family":"Sanou","sequence":"additional","affiliation":[{"name":"SERAMED\/LRAcc, Radiobiology and Regenerative Medicine Research Service, Radiobiology of Accidental Exposure Laboratory ASNR\u2014French Authority for Nuclear Safety and Radiation Protection  Fontenay\u2010aux\u2010Roses France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aur\u00e9lie","family":"Vaurijoux","sequence":"additional","affiliation":[{"name":"SERAMED\/LRAcc, Radiobiology and Regenerative Medicine Research Service, Radiobiology of Accidental Exposure Laboratory ASNR\u2014French Authority for Nuclear Safety and Radiation Protection  Fontenay\u2010aux\u2010Roses France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascale","family":"Fernandez","sequence":"additional","affiliation":[{"name":"SERAMED\/LRAcc, Radiobiology and Regenerative Medicine Research Service, Radiobiology of Accidental Exposure Laboratory ASNR\u2014French Authority for Nuclear Safety and Radiation Protection  Fontenay\u2010aux\u2010Roses France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Delphine","family":"Dugue","sequence":"additional","affiliation":[{"name":"SERAMED\/LRAcc, Radiobiology and Regenerative Medicine Research Service, Radiobiology of Accidental Exposure Laboratory ASNR\u2014French Authority for Nuclear Safety and Radiation Protection  Fontenay\u2010aux\u2010Roses France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laure","family":"Bobyk","sequence":"additional","affiliation":[{"name":"Department of Radiation Biology IRBA\u2014Armed Forces Biomedical Research Institute  Br\u00e9tigny\u2010sur\u2010Orge France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Valente","sequence":"additional","affiliation":[{"name":"Department of Radiation Biology IRBA\u2014Armed Forces Biomedical Research Institute  Br\u00e9tigny\u2010sur\u2010Orge France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ga\u00ebtan","family":"Gruel","sequence":"additional","affiliation":[{"name":"SERAMED\/LRAcc, Radiobiology and Regenerative Medicine Research Service, Radiobiology of Accidental Exposure Laboratory ASNR\u2014French Authority for Nuclear Safety and Radiation Protection  Fontenay\u2010aux\u2010Roses France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Moebel","sequence":"additional","affiliation":[{"name":"SAIRPICO Project\u2010Team, Inria Center at University of Rennes, Institut Curie, Cellular and Chemical Biology Unit (U1339 INSERM, UMR3666 CNRS) PSL Research University  Rennes France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamedamine","family":"Benadjaoud","sequence":"additional","affiliation":[{"name":"SERAMED\/LRAcc, Radiobiology and Regenerative Medicine Research Service, Radiobiology of Accidental Exposure Laboratory ASNR\u2014French Authority for Nuclear Safety and Radiation Protection  Fontenay\u2010aux\u2010Roses France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6263-0452","authenticated-orcid":false,"given":"Charles","family":"Kervrann","sequence":"additional","affiliation":[{"name":"SAIRPICO Project\u2010Team, Inria Center at University of Rennes, Institut Curie, Cellular and Chemical Biology Unit (U1339 INSERM, UMR3666 CNRS) PSL Research University  Rennes France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"e_1_2_10_2_1","unstructured":"IAEA \u201cCytogenetic Dosimetry: Applications in Preparedness for and Response to Radiation Emergencies \u201dtech. rep. IAEA\u2014International Atomic Energy Agency 2011."},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1161(91)90135-U"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.12688\/f1000research.9075.1"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-25856-1"},{"key":"e_1_2_10_6_1","doi-asserted-by":"crossref","unstructured":"Y.Li A.Wickramasinghe A. A.Subasinghe et\u00a0al. \u201cTowards Large Scale Automated Interpretation of Cytogenetic Biodosimetry Data \u201dinIEEE International Conference on Information and Automation for Sustainability 2012 30\u201335.","DOI":"10.1109\/ICIAFS.2012.6420039"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/jemt.22642"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.12688\/f1000research.12226.1"},{"key":"e_1_2_10_9_1","first-page":"42","article-title":"Radiation Dose Estimation by Completely Automated Interpretation of the Discentric Chromosome Assay","volume":"186","author":"Li Y.","year":"2019","journal-title":"Radiation Protection Dosimetry"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1667\/RR1664.1"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1667\/RR3196.1"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mrgentox.2019.503087"},{"key":"e_1_2_10_13_1","first-page":"1097","article-title":"ImageNet Classification With Deep Convolutional Neural Networks","volume":"1","author":"Krizhevsky A.","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_2_10_14_1","first-page":"234","article-title":"U\u2010Net: Convolutional Networks for Biomedical Image Segmentation","volume":"9351","author":"Ronneberger O.","year":"2015","journal-title":"Proceeding of the Medical Image Computing and Computer\u2010Assisted Intervention (MICCAI)"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0261-2"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0458-z"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01275-4"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3286572"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3026483"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2021.3089507"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3062234"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3293854"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034684"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101943"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2020.3003445"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2905841"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3007642"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3178786"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-28456-9"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1080\/09553002.2024.2338531"},{"key":"e_1_2_10_31_1","first-page":"1321","article-title":"On Calibration of Modern Neural Networks","volume":"70","author":"Guo C.","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"e_1_2_10_32_1","first-page":"163","article-title":"Feasibility Study on Automatic Interpretation of Radiation Dose Using Deep Learning Technique for Dicentric Chromosome Assay","volume":"195","author":"Jang S.","year":"2021","journal-title":"Radiation Research"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102830"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1080\/09553002.2025.2542320"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-26178-y"},{"key":"e_1_2_10_36_1","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma D.","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"e_1_2_10_37_1","unstructured":"P.Izmailov D.Podoprikhin T.Garipov D.Vetrov andA.Wilson \u201cAveraging Weights Leads to Wider Optima and Better Generalization \u201dinConference on Uncertainty in Artificial Intelligence 2018."},{"key":"e_1_2_10_38_1","unstructured":"A.Paszke S.Gross F.Massa et\u00a0al. \u201cPyTorch: An Imperative Style High\u2010Performance Deep Learning Library \u201dinAdvances in Neural Information Processing Systems (NeurIPS) 32 2019."},{"key":"e_1_2_10_39_1","unstructured":"B.Lakshminarayanan A.Pritzel andC.Blundell \u201cSimple and Scalable Predictive Uncertainty Estimation Using Deep Ensembles \u201dinAdvances in Neural Information Processing Systems (NeurIPS) 30 2017."},{"key":"e_1_2_10_40_1","unstructured":"W. J.Maddox P.Izmailov T.Garipov D. P.Vetrov andA. G.Wilson \u201cA Simple Baseline for Bayesian Uncertainty in Deep Learning \u201dinAdvances in Neural Information Processing Systems (NeurIPS) 32 2019."},{"key":"e_1_2_10_41_1","first-page":"4697","article-title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","volume":"33","author":"Wilson A. G.","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00418-022-02148-3"},{"key":"e_1_2_10_43_1","unstructured":"G.Huang Y.Li G.Pleiss Z.Liu J. E.Hopcroft andK. Q.Weinberger \u201cSnapshot Ensembles: Train 1 Get M for Free \u201dinInternational Conference on Learning Representations (ICLR) 2016."},{"key":"e_1_2_10_44_1","unstructured":"T.Garipov P.Izmailov D.Podoprikhin D. P.Vetrov andA. G.Wilson \u201cLoss Surfaces Mode Connectivity and Fast Ensembling of DNNs \u201dinAdvances in Neural Information Processing Systems (NeurIPS) 31 2018."},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1080\/09553002.2023.2176564"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01323412"},{"key":"e_1_2_10_47_1","first-page":"1","article-title":"Stochastic Gradient Descent as Approximate Bayesian Inference","volume":"18","author":"Mandt S.","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1093\/rpd\/ncw161"},{"key":"e_1_2_10_49_1","first-page":"42","article-title":"Radiation Dose Estimation by Completely Automated Interpretation of the Dicentric Chromosome Assay","volume":"186","author":"Li Y.","year":"2019","journal-title":"Radiation Protection Dosimetry"}],"container-title":["Cytometry Part A"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cyto.a.70042","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cyto.a.70042","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cyto.a.70042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T10:11:13Z","timestamp":1790849473000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cyto.a.70042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":48,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1002\/cyto.a.70042"],"URL":"https:\/\/doi.org\/10.1002\/cyto.a.70042","archive":["Portico"],"relation":{},"ISSN":["1552-4922","1552-4930"],"issn-type":[{"value":"1552-4922","type":"print"},{"value":"1552-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,16]]},"assertion":[{"value":"2025-04-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}