{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T20:58:22Z","timestamp":1780088302475,"version":"3.54.0"},"reference-count":49,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T00:00:00Z","timestamp":1683849600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2023,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep learning (DL) models for radiation therapy (RT) image segmentation require accurately annotated training data. Multiple organ delineation guidelines exist; however, information on the used guideline is not provided with the delineation. Extraction of training data with coherent guidelines can therefore be challenging. We present a supervised classification method for pelvis structure delineations where bowel cavity, femoral heads, bladder, and rectum data, with two guidelines, were classified. The impact on DL\u2010based segmentation quality using mixed guideline training data was also demonstrated. Bowel cavity was manually delineated on CT images for anal cancer patients (<jats:italic>n<\/jats:italic>\u00a0=\u00a0170) according to guidelines Devisetty and RTOG. The DL segmentation quality from using training data with coherent or mixed guidelines was investigated. A supervised 3D squeeze\u2010and\u2010excite SENet\u2010154 model was trained to classify two bowel cavity delineation guidelines. In addition, a pelvis CT dataset with manual delineations from prostate cancer patients (<jats:italic>n<\/jats:italic>\u00a0=\u00a01854) was used where data with an alternative guideline for femoral heads, rectum, and bladder were generated using commercial software. The model was evaluated on internal (<jats:italic>n<\/jats:italic>\u00a0=\u00a0200) and external test data (<jats:italic>n<\/jats:italic>\u00a0=\u00a099). By using mixed, compared to coherent, delineation guideline training data mean DICE score decreased 3% units, mean Hausdorff distance (95%) increased 5\u00a0mm and mean surface distance (MSD) increased 1\u00a0mm. The classification of bowel cavity test data achieved 99.8% unweighted classification accuracy, 99.9% macro average precision, 97.2% macro average recall, and 98.5% macro average F1. Corresponding metrics for the pelvis internal test data were all 99% or above and for the external pelvis test data they were 96.3%, 96.6%, 93.3%, and 94.6%. Impaired segmentation performance was observed for training data with mixed guidelines. The DL delineation classification models achieved excellent results on internal and external test data. This can facilitate automated guideline\u2010specific data extraction while avoiding the need for consistent and correct structure labels.<\/jats:p>","DOI":"10.1002\/acm2.14022","type":"journal-article","created":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T06:39:56Z","timestamp":1683959996000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep learning\u2010based classification of organs at risk and delineation guideline in pelvic cancer radiation therapy"],"prefix":"10.1002","volume":"24","author":[{"given":"Michael","family":"Lempart","sequence":"first","affiliation":[{"name":"Radiation Physics, Department of Hematology Oncology, and Radiation Physics Sk\u00e5ne University Hospital  Lund Sweden"},{"name":"Department of Translational Medicine Medical Radiation Physics Lund University  Malm\u00f6 Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonas","family":"Scherman","sequence":"additional","affiliation":[{"name":"Radiation Physics, Department of Hematology Oncology, and Radiation Physics Sk\u00e5ne University Hospital  Lund Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin P.","family":"Nilsson","sequence":"additional","affiliation":[{"name":"Department of Hematology Oncology, and Radiation Physics Sk\u00e5ne University Hospital  Lund Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2931-5615","authenticated-orcid":false,"given":"Christian","family":"Jamtheim Gustafsson","sequence":"additional","affiliation":[{"name":"Radiation Physics, Department of Hematology Oncology, and Radiation Physics Sk\u00e5ne University Hospital  Lund Sweden"},{"name":"Department of Translational Medicine Medical Radiation Physics Lund University  Malm\u00f6 Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,5,12]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.canlet.2016.05.033"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2019.00977"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12032\u2010020\u201001374\u2010w"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41571\u2010020\u20100417\u20108"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2018.05.018"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjro.20180031"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11684\u2010020\u20100761\u20101"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.05.030"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.09.008"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2020.11.002"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014\u2010020\u201001677\u20102"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.canrad.2021.06.023"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.05.010"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014\u2010022\u201002088\u20101"},{"key":"e_1_2_9_16_1","first-page":"234","volume-title":"U\u2010Net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger O","year":"2015"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2022.04.007"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ab99e5"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13446"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2018.09.013"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2016.04.007"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.12701"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare8020120"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.12.013"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2011.09.054"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1093\/jicru\/10.1.Report83"},{"key":"e_1_2_9_27_1","unstructured":"National Reference Group.2016:20 A standardized Swedish naming convention for radiation therapy. SSM \u2013 Swedish Radiation Safety Authority.https:\/\/www.stralsakerhetsmyndigheten.se\/publikationer\/rapporter\/stralskydd\/2016\/201620\/"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2013.2251421"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103527"},{"key":"e_1_2_9_30_1","first-page":"10","article-title":"Towards automated data cleaning workflows","volume":"2454","author":"Mahdavi M","year":"2019","journal-title":"LWDA 2019"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/0471448354.ch1"},{"issue":"6","key":"e_1_2_9_32_1","first-page":"E263","article-title":"TG263\u2010Net: a deep learning model for organs\u2010at\u2010risk nomenclature standardization","volume":"46","author":"Rhee D","year":"2019","journal-title":"American Association of Physicists in Medicine Annual Meeting"},{"key":"e_1_2_9_33_1","unstructured":"RozarioT LongT ChenM LuW JiangS.Towards automated patient data cleaning using deep learning: a feasibility study on the standardization of organ labeling.arXiv:1801.00096.2017."},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/Access.2020.2999079"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2009.07.006"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2012.01.023"},{"key":"e_1_2_9_37_1","unstructured":"CoxRW AshburnerJ BremanH et\u00a0al.A (sort of) new image data format standard: niFTI\u20101.10th Annual Meeting of the Organization for Human Brain Mapping.2004:22."},{"key":"e_1_2_9_38_1","unstructured":"PhilT.Sikerdebaard\/dcmrtstruct2nii: v1.0.19. Accessed June 22 2021. doi:10.5281\/zenodo.4037865"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278\u2010017\u20100037\u20108"},{"key":"e_1_2_9_40_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition.IEEE Conference on Computer Vision and Pattern Pattern Recognition (CVPR).2016:770\u2010778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_41_1","doi-asserted-by":"crossref","unstructured":"XieS GirshickR Doll\u00e1rP TuZ HeK.Aggregated residual transformations for deep neural networks.IEEE Conference on Computer Vision and Pattern Pattern Recognition (CVPR).2017:5987\u20105995.","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","unstructured":"HuJ ShenL SunG.Squeeze\u2010and\u2010excitation networks.IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2018:7132\u20107141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_9_43_1","first-page":"6","article-title":"Pytorch lightning","volume":"3","author":"Falcon W","year":"2019","journal-title":"GitHub Note"},{"key":"e_1_2_9_44_1","unstructured":"MONAI: Medical Open Network for AI. Version 0.8.1. Zenodo doi:10.5281\/zenodo.6114127;2022."},{"key":"e_1_2_9_45_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ Delving Deep into Rectifiers: Surpassing Human\u2010Level Performance on ImageNet Classification.IEEE International Conference on Computer Vision (ICCV).2015:1026\u20101034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_9_46_1","article-title":"Scikit\u2010learn: machine learning in python","volume":"12","author":"Pedregosa F","year":"2012","journal-title":"J Mach Learn Res"},{"key":"e_1_2_9_47_1","unstructured":"KingmaD AdamBaJ.A method for stochastic optimization.International Conference on Learning Representations.2014."},{"key":"e_1_2_9_48_1","unstructured":"AbadiM AgarwalA BarhamP et\u00a0al.White Paper: TensorFlow: large\u2010scale machine learning on heterogeneous systems.arXiv:1603.04467.2015."},{"key":"e_1_2_9_49_1","unstructured":"Maier\u2010HeinL MenzeB.Metrics reloaded: pitfalls and recommendations for image analysis validation.arXiv:2206.01653.2022."},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102444"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.14022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T20:57:52Z","timestamp":1693861072000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.14022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,12]]},"references-count":49,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["10.1002\/acm2.14022"],"URL":"https:\/\/doi.org\/10.1002\/acm2.14022","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,12]]},"assertion":[{"value":"2022-10-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e14022"}}