{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:03:53Z","timestamp":1792080233246,"version":"4.4.0"},"reference-count":49,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T00:00:00Z","timestamp":1686096000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2023,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Deep learning auto\u2010segmentation (DLAS) models have been adopted in the clinic; however, they suffer from performance deterioration owing to the clinical practice variability. Some commercial DLAS software provide an incremental retraining function that enables users to train a custom model using their institutional data to account for clinical practice variability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>This study was performed to evaluate and implement the commercial DLAS software with the incremental retraining function for definitive treatment of patients with prostate cancer in a multi\u2010user environment.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>CT\u2010based target organs and organs\u2010at\u2010risk (OAR) delineation of 215 prostate cancer patients were utilized. The performance of three commercial DLAS software built\u2010in models was validated with 20 patients. A retrained custom model was developed using 100 patients and evaluated on the remaining data (<jats:italic>n<\/jats:italic>\u00a0=\u00a0115). Dice similarity coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), and surface DSC (SDSC) were utilized for quantitative evaluation. A multi\u2010rater qualitative evaluation was blindly performed with a five\u2010level scale. Visual inspection was performed in consensus and non\u2010consensus unacceptable cases to identify the failure modes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Three commercial DLAS vendor built\u2010in models achieved sub\u2010optimal performance in 20 patients. The retrained custom model had a mean DSC of 0.82 for prostate, 0.48 for seminal vesicles (SV), and 0.92 for rectum, respectively. This represents a significant improvement over the built\u2010in model with DSC of 0.73, 0.37, and 0.81 for the corresponding structures. Compared to the acceptance rate of 96.5% and consensus unacceptable rate (i.e., both reviewers rated as unacceptable) of 3.5% achieved by manual contours, the custom model achieved a 91.3% acceptance rate and 8.7% consensus unacceptable rate. The failure modes of retrained custom model were attributed to the following: cystogram (<jats:italic>n<\/jats:italic>\u00a0=\u00a02), hip prosthesis (<jats:italic>n<\/jats:italic>\u00a0=\u00a02), low dose rate brachytherapy seeds (<jats:italic>n<\/jats:italic>\u00a0=\u00a02), air in endorectal balloon(<jats:italic>n<\/jats:italic>\u00a0=\u00a01), non\u2010iodinated spacer (<jats:italic>n<\/jats:italic>\u00a0=\u00a02), and giant bladder(<jats:italic>n<\/jats:italic>\u00a0=\u00a01).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The commercial DLAS software with the incremental retraining function was validated and clinically adopted for prostate patients in a multi\u2010user environment. AI\u2010based auto\u2010delineation of the prostate and OARs is shown to achieve improved physician acceptance, overall clinical utility, and accuracy.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16537","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T05:22:16Z","timestamp":1686201736000},"page":"4079-4091","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Incremental retraining, clinical implementation, and acceptance rate of deep learning auto\u2010segmentation for male pelvis in a multiuser environment"],"prefix":"10.1002","volume":"50","author":[{"given":"Jingwei","family":"Duan","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"},{"name":"Department of Radiation Oncology University of Kentucky  Lexington Kentucky USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos E.","family":"Vargas","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathan Y.","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brady S.","family":"Laughlin","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego Santos","family":"Toesca","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sameer","family":"Keole","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean Claude M.","family":"Rwigema","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William W.","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven E.","family":"Schild","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Feng","sequence":"additional","affiliation":[{"name":"Carina Medical LLC  Lexington Kentucky USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology City of Hope Comprehensive Cancer Center  Duarte California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Rong","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic Arizona  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,6,7]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13466"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.07.013"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12197"},{"key":"e_1_2_8_5_1","unstructured":"NikolovS BlackwellS ZverovitchA et\u00a0al.Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy.arXiv preprint arXiv:180904430.2018."},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13141"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2007.11.030"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2017.11.012"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.03.004"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2019.02.001"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.10.019"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2015.05.012"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.11.011"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2021.04.019"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2020.11.002"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abb214"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2020.00105"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2020.01.006"},{"key":"e_1_2_8_19_1","unstructured":"WangB DohopolskiM BaiT et\u00a0al.Performance deterioration of deep learning models after clinical deployment: a case study with auto\u2010segmentation for definitive prostate cancer radiotherapy.arXiv preprint arXiv:221005673.2022."},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021210097"},{"key":"e_1_2_8_21_1","unstructured":"AzulayA WeissY Why do deep convolutional networks generalize so poorly to small image transformations?.arXiv preprint arXiv:180512177.2018."},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab7877"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMc2104626"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-019-00180-9"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2014.01.019"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/1754-9485.12844"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1080\/0284186X.2020.1825801"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-020-01528-0"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaf11c"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102195"},{"key":"e_1_2_8_31_1","unstructured":"BalagopalA NguyenD MashayekhiM et\u00a0al.Dosimetric impact of physician style variations in contouring CTV for post\u2010operative prostate cancer: a deep learning\u2010based simulation study. arXiv preprint arXiv:210201006.2021."},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15525"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2019.03.017"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-020-01641-3"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10110959"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11111964"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16056"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11041691"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.09.038"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2021.05.003"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2019.12.001"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2021.02.040"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20190001"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctro.2020.09.004"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2007.03.005"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360-3016(02)03011-0"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13814"},{"key":"e_1_2_8_48_1","first-page":"1","article-title":"Retrospective validation and clinical implementation of automated contouring of organs at risk in the head and neck: a step toward automated radiation treatment planning for low\u2010and middle\u2010income countries","volume":"4","author":"McCarroll RE","year":"2018","journal-title":"J Glob Oncol"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2010.07.009"},{"key":"e_1_2_8_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2008.08.007"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T21:03:20Z","timestamp":1692219800000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16537"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,7]]},"references-count":49,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["10.1002\/mp.16537"],"URL":"https:\/\/doi.org\/10.1002\/mp.16537","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,7]]},"assertion":[{"value":"2023-03-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-23","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}