{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T04:13:29Z","timestamp":1789186409155,"version":"build-2803163510"},"reference-count":71,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T00:00:00Z","timestamp":1721347200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009708","name":"Novo Nordisk Fonden","doi-asserted-by":"publisher","award":["NNF20OC0062056"],"award-info":[{"award-number":["NNF20OC0062056"]}],"id":[{"id":"10.13039\/501100009708","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004329","name":"Javna Agencija za Raziskovalno Dejavnost RS","doi-asserted-by":"publisher","award":["P2\u20100232"],"award-info":[{"award-number":["P2\u20100232"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004329","name":"Javna Agencija za Raziskovalno Dejavnost RS","doi-asserted-by":"publisher","award":["J2\u201050067"],"award-info":[{"award-number":["J2\u201050067"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2024,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>The pancreas is a complex abdominal organ with many anatomical variations, and therefore automated pancreas segmentation from medical images is a challenging\u00a0application.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>In this paper, we present a framework for segmenting individual pancreatic subregions and the pancreatic duct from three\u2010dimensional (3D) computed tomography (CT) images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A multiagent reinforcement learning (RL) network was used to detect landmarks of the head, neck, body, and tail of the pancreas, and landmarks along the pancreatic duct in a selected target CT image. Using the landmark detection results, an atlas of pancreases was nonrigidly registered to the target image, resulting in anatomical probability maps for the pancreatic subregions and duct. The probability maps were augmented with multilabel 3D U\u2010Net architectures to obtain the final segmentation\u00a0results.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>To evaluate the performance of our proposed framework, we computed the Dice similarity coefficient (DSC) between the predicted and ground truth manual segmentations on a database of 82 CT images with manually segmented pancreatic subregions and 37 CT images with manually segmented pancreatic ducts. For the four pancreatic subregions, the mean DSC improved from 0.38, 0.44, and 0.39 with standard 3D U\u2010Net, Attention U\u2010Net, and shifted windowing (Swin) U\u2010Net architectures, to 0.51, 0.47, and 0.49, respectively, when utilizing the proposed RL\u2010based framework. For the pancreatic duct, the RL\u2010based framework achieved a mean DSC of 0.70, significantly outperforming the standard approaches and existing methods on different datasets.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The resulting accuracy of the proposed RL\u2010based segmentation framework demonstrates an improvement against segmentation with standard U\u2010Net\u00a0architectures.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.17300","type":"journal-article","created":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T20:05:04Z","timestamp":1721419504000},"page":"7378-7392","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Reinforcement learning\u2010based anatomical maps for pancreas subregion and duct segmentation"],"prefix":"10.1002","volume":"51","author":[{"given":"Sepideh","family":"Amiri","sequence":"first","affiliation":[{"name":"Department of Computer Science University of Copenhagen Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toma\u017e","family":"Vrtovec","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering University of Ljubljana Ljubljana Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tamerlan","family":"Mustafaev","sequence":"additional","affiliation":[{"name":"Swanson School of Engineering University of Pittsburgh Rochester USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher L.","family":"Deufel","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Rochester USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henrik S.","family":"Thomsen","sequence":"additional","affiliation":[{"name":"Department of Radiology Herlev Gentofte Hospital Copenhagen University Hospital Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin Hylleholt","family":"Sillesen","sequence":"additional","affiliation":[{"name":"Department of Organ Surgery and Transplantation, and CSTAR Copenhagen University Hospital Rigshospitalet Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik Gudmann Steuble","family":"Brandt","sequence":"additional","affiliation":[{"name":"Department of Radiology Herlev Gentofte Hospital Copenhagen University Hospital Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael Brun","family":"Andersen","sequence":"additional","affiliation":[{"name":"Department of Radiology Herlev Gentofte Hospital Copenhagen University Hospital Copenhagen Denmark"},{"name":"Department of Clinical Medicine Copenhagen University Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph Felix","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Department of Radiology Herlev Gentofte Hospital Copenhagen University Hospital Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bulat","family":"Ibragimov","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Copenhagen Copenhagen Denmark"},{"name":"Faculty of Electrical Engineering University of Ljubljana Ljubljana Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,7,19]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.18.20901"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40792-015-0041-5"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)30974-0"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116444"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8070195"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28098"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI45749.2020.9098473"},{"key":"e_1_2_8_9_1","unstructured":"RothHR OdaH HayashiY et\u00a0al.Hierarchical 3D fully convolutional networks for multi\u2010organ segmentation. arXiv preprint arXiv:1704.06382.2017."},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.01.006"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106410"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109818"},{"key":"e_1_2_8_13_1","doi-asserted-by":"crossref","unstructured":"ZhouY XieL ShenW WangY FishmanEK YuilleAL.A fixed\u2010point model for pancreas segmentation in abdominal CT scans. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI 2017.Springer;2017:693\u2010701.","DOI":"10.1007\/978-3-319-66182-7_79"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2911588"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101884"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1120\/jacmp.v17i5.6236"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107762"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0252287"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-07848-3"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1080\/00365521.2020.1760345"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v13.i11.1701"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.14740\/wjon1166"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02530-x"},{"key":"e_1_2_8_24_1","doi-asserted-by":"crossref","unstructured":"XiaY YuQ ShenW ZhouY FishmanEK YuilleAL.Detecting pancreatic ductal adenocarcinoma in multi\u2010phase CT scans via alignment ensemble. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI 2020.Springer;2020:285\u2010295.","DOI":"10.1007\/978-3-030-59716-0_28"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"ZhouY LiY ZhangZ et\u00a0al.Hyper\u2010pairing network for multi\u2010phase pancreatic ductal adenocarcinoma segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI 2019.Springer;2019:155\u2010163.","DOI":"10.1007\/978-3-030-32245-8_18"},{"key":"e_1_2_8_26_1","first-page":"46","volume-title":"Clinical Image\u2010Based Procedures, Distributed and Collaborative Learning, Artificial Intelligence for Combating COVID\u201019 and Secure and Privacy\u2010Preserving Machine Learning","author":"Shen C","year":"2021"},{"key":"e_1_2_8_27_1","unstructured":"RothHR FaragA TurkbeyEB LuL LiuJ SummersRM.Data from pancreas\u2010CT (Version 2) [Data set].The Cancer Imaging Archive.2016. doi:https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.tNB1kqBU"},{"key":"e_1_2_8_28_1","doi-asserted-by":"crossref","unstructured":"ZhuZ XiaY XieL FishmanEK YuilleAL.Multi\u2010scale coarse\u2010to\u2010fine segmentation for screening pancreatic ductal adenocarcinoma. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI 2019.Springer;2019:3\u201012.","DOI":"10.1007\/978-3-030-32226-7_1"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3060066"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.665929"},{"key":"e_1_2_8_31_1","unstructured":"SMF.Anatomy of The Pancreas and Where The Pancreas is Located.2024.https:\/\/seenamagowitzfoundation.org\/the\u2010pancreas\/"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.07.002"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-013-9586-7"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2011.5872821"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101621"},{"key":"e_1_2_8_36_1","unstructured":"RonnebergerO FischerP BroxT.U\u2010Net: Convolutional networks for biomedical image segmentation. In: Navab N. Hornegger J. Wells W. Frangi A. (eds)Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI 2015. Lecture Notes in Computer Science vol 9351. Springer Cham.2015. doi:https:\/\/doi.org\/10.1007\/978\u20103\u2010319\u201024574\u20104_28"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107444"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.02.007"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12020309"},{"key":"e_1_2_8_40_1","unstructured":"NavarroF SekuboyinaA WaldmannstetterD PeekenJC CombsSE MenzeBH.Deep reinforcement learning for organ localization in CT. In:Proceedings of the Third Conference on Medical Imaging with Deep Learning PMLR.2020;121:544\u2010554."},{"key":"e_1_2_8_41_1","doi-asserted-by":"crossref","unstructured":"AlansaryA FolgocLL VaillantG et\u00a0al.Automatic view planning with multi\u2010scale deep reinforcement learning agents. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI 2018. Springer;2018:277\u2010285.","DOI":"10.1007\/978-3-030-00928-1_32"},{"key":"e_1_2_8_42_1","first-page":"81","article-title":"Reinforced redetection of landmark in pre\u2010 and post\u2010operative brain scan using anatomical guidance for image alignment. In:","volume":"12120","author":"Waldmannstetter D","year":"2020","journal-title":"International Workshop on Biomedical Image Registration \u2010 WBIR 2020"},{"key":"e_1_2_8_43_1","doi-asserted-by":"crossref","unstructured":"GhesuFC GeorgescuB MansiT NeumannD HorneggerJ ComaniciuD.An artificial agent for anatomical landmark detection in medical images. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI 2016. Springer;2016:229\u2010237.","DOI":"10.1007\/978-3-319-46726-9_27"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3048477"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66843-3_18"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"e_1_2_8_49_1","doi-asserted-by":"crossref","unstructured":"VlontzosA AlansaryA KamnitsasK RueckertD KainzB.Multiple landmark detection using multi\u2010agent reinforcement learning. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI 2019.Springer;2019:262\u2010270.","DOI":"10.1007\/978-3-030-32251-9_29"},{"key":"e_1_2_8_50_1","unstructured":"FoersterJN ChenRY Al\u2010ShedivatM WhitesonS AbbeelP MordatchI.Learning with opponent\u2010learning awareness. arXiv preprint arXiv:1709.04326.2017."},{"key":"e_1_2_8_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.12.007"},{"key":"e_1_2_8_52_1","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","volume":"7","author":"Jaakkola T","year":"1994","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_8_53_1","unstructured":"RashidT SamvelyanM SchroederC FarquharG FoersterJ WhitesonS.Qmix: Monotonic value function factorisation for deep multi\u2010agent reinforcement learning. In:International Conference on Machine Learning. Springer;2018:4295\u20104304."},{"key":"e_1_2_8_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2035616"},{"key":"e_1_2_8_55_1","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek\u00d6 AbdulkadirA LienkampSS BroxT RonnebergerO.3D U\u2010Net: learning dense volumetric segmentation from sparse annotation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention \u2010 MICCAI 2016. Springer;2016:424\u2010432.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"e_1_2_8_56_1","unstructured":"OktayO SchlemperJ FolgocLL et\u00a0al.Attention U\u2010Net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999.2018."},{"key":"e_1_2_8_57_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA NathV TangY YangD RothHR XuD.Swin UNETR: Swin transformers for semantic segmentation of brain tumors in MRI images. In:International MICCAI Brainlesion Workshop.Springer;2022:272\u2010284.","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"e_1_2_8_58_1","unstructured":"BahdanauD ChoK BengioY.Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.2014."},{"key":"e_1_2_8_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2806309"},{"key":"e_1_2_8_60_1","doi-asserted-by":"crossref","unstructured":"RothH LuL FaragA SohnA SummersR.Spatial aggregation of holistically\u2010nested networks for automated pancreas segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention\u2010MICCAI 2016.Springer;2016:451\u2010459.","DOI":"10.1007\/978-3-319-46723-8_52"},{"key":"e_1_2_8_61_1","doi-asserted-by":"crossref","unstructured":"LiuZ LinY CaoY et\u00a0al.Swin transformer: Hierarchical vision transformer using shifted windows. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE;2021:9992\u201010002.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_8_62_1","doi-asserted-by":"crossref","unstructured":"SmithLN.Cyclical learning rates for training neural networks. In:2017 IEEE Winter Conference on Applications of Computer Vision (WACV).IEEE;2017:464\u2010472.","DOI":"10.1109\/WACV.2017.58"},{"key":"e_1_2_8_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1499-3872(13)60076-4"},{"key":"e_1_2_8_64_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abf201"},{"key":"e_1_2_8_65_1","doi-asserted-by":"crossref","unstructured":"LeavensC VikT SchulzH et\u00a0al.Validation of automatic landmark identification for atlas\u2010based segmentation for radiation treatment planning of the head\u2010and\u2010neck region.Proc. SPIE 6914 Medical Imaging2008: Image Processing 69143G (26 March 2008); doi:https:\/\/doi.org\/10.1117\/12.769710","DOI":"10.1117\/12.769710"},{"key":"e_1_2_8_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912467"},{"key":"e_1_2_8_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102417"},{"key":"e_1_2_8_68_1","unstructured":"LiY YangS ZhangS et\u00a0al.Is 2D heatmap representation even necessary for human pose estimation?arXiv preprint arXiv:2107.03332.2021."},{"key":"e_1_2_8_69_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-019-6178-z"},{"key":"e_1_2_8_70_1","doi-asserted-by":"publisher","DOI":"10.21037\/jgo.2018.12.08"},{"key":"e_1_2_8_71_1","volume-title":"Gastrointestinal Endoscopy in Practice e\u2010Book: Expert Consult","author":"Canard JM","year":"2011"},{"key":"e_1_2_8_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-323-91015-6.00032-7"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T16:32:35Z","timestamp":1755880355000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17300"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,19]]},"references-count":71,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["10.1002\/mp.17300"],"URL":"https:\/\/doi.org\/10.1002\/mp.17300","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,19]]},"assertion":[{"value":"2024-01-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}