{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T04:19:31Z","timestamp":1769573971158,"version":"3.49.0"},"reference-count":38,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T00:00:00Z","timestamp":1703116800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12075095"],"award-info":[{"award-number":["12075095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017958","name":"Health Commission of Hubei Province","doi-asserted-by":"publisher","award":["WJ2021M192"],"award-info":[{"award-number":["WJ2021M192"]}],"id":[{"id":"10.13039\/100017958","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017958","name":"Health Commission of Hubei Province","doi-asserted-by":"publisher","award":["WJ2021Q046"],"award-info":[{"award-number":["WJ2021Q046"]}],"id":[{"id":"10.13039\/100017958","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Obvious inconsistencies in auto\u2010segmentations exist among various AI software. In this study, we have developed a novel convolutional neural network (CNN) fine\u2010tuning workflow to achieve precise and robust localized segmentation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The datasets include Hubei Cancer Hospital dataset, Cetuximab Head and Neck Public Dataset, and Qu\u00e9bec Public Dataset. Seven organs\u2010at\u2010risks (OARs), including brain stem, left parotid gland, esophagus, left optic nerve, optic chiasm, mandible, and pharyngeal constrictor, were selected. The auto\u2010segmentation results from four commercial AI software were first compared with the manual delineations. Then a new multi\u2010scale lightweight residual CNN model with an attention module (named as HN\u2010Net) was trained and tested on 40 samples and 10 samples from Hubei Cancer Hospital, respectively. To enhance the network's accuracy and generalization ability, the fine\u2010tuning workflow utilized an uncertainty estimation method for automatic selection of candidate samples of worthiness from Cetuximab Head and Neck Public Dataset for further training. The segmentation performances were evaluated on the Hubei Cancer Hospital dataset and\/or the entire Qu\u00e9bec Public Dataset.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>A maximum difference of 0.13 and 0.7\u00a0mm in average Dice value and Hausdorff distance value for the seven OARs were observed by four AI software. The proposed HN\u2010Net achieved an average Dice value of 0.14 higher than that of the AI software, and it also outperformed other popular CNN models (HN\u2010Net: 0.79, U\u2010Net: 0.78, U\u2010Net++: 0.78, U\u2010Net\u2010Multi\u2010scale: 0.77, AI software: 0.65). Additionally, the HN\u2010Net fine\u2010tuning workflow by using the local datasets and external public datasets further improved the automatic segmentation with the average Dice value by 0.02.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The delineations of commercial AI software need to be carefully reviewed, and localized further training is necessary for clinical practice. The proposed fine\u2010tuning workflow could be feasibly adopted to implement an accurate and robust auto\u2010segmentation model by using local datasets and external public datasets.<\/jats:p><\/jats:sec>","DOI":"10.1002\/acm2.14248","type":"journal-article","created":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T20:38:38Z","timestamp":1703191118000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Accurate and robust auto\u2010segmentation of head and neck organ\u2010at\u2010risks based on a novel CNN fine\u2010tuning workflow"],"prefix":"10.1002","volume":"25","author":[{"given":"Shunyao","family":"Luan","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology Hubei Cancer Hospital, Tongji Medical College Huazhong University of Science and Technology  Wuhan China"},{"name":"School of Integrated Circuits Laboratory for Optoelectronics Huazhong University of Science and Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Hubei Cancer Hospital, Tongji Medical College Huazhong University of Science and Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Hubei Cancer Hospital, Tongji Medical College Huazhong University of Science and Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benpeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits Laboratory for Optoelectronics Huazhong University of Science and Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Hubei Cancer Hospital, Tongji Medical College Huazhong University of Science and Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Xue","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Hubei Cancer Hospital, Tongji Medical College Huazhong University of Science and Technology  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,12,21]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1715715"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.03.004"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2010.11.017"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2015.06.012"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2011.07.015"},{"key":"e_1_2_9_7_1","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/978-0-387-09749-7_12","volume-title":"Atlas\u2010based segmentation. handbook of biomedical imaging","author":"Cuadra MB","year":"2015"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.34133\/2020\/8620932"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.34133\/2022\/9860179"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.04.041"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acf98f"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.34133\/2022\/9765307"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ad0a5a"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13416"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2017.00315"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.34133\/2022\/9764501"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aa82ec"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12045"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13463"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13300"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2015.07.041"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.833816"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12602"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1235461"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/jrr\/rraa094"},{"key":"e_1_2_9_26_1","doi-asserted-by":"crossref","unstructured":"WooS ParkJ LeeJY KweonIS Cbam: convolutional block attention module. Inproceedings of the European conference on computer vision (ECCV):2018:3\u201019.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ \u201cDeep Residual Learning for Image Recognition \u201d2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 pp.770\u2010778 doi:10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.00524"},{"key":"e_1_2_9_29_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT (2015).U\u2010net: convolutional networks for biomedical image segmentation. InMedical Image Computing and Computer\u2010Assisted Intervention\u2013MICCAI 2015: 18th International Conference Munich Germany October 5\u20139 2015 Proceedings Part III 18 (pp.234\u2010241).Springer International Publishing.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"e_1_2_9_31_1","doi-asserted-by":"crossref","unstructured":"HuH ZhengY ZhouQ XiaoJ ChenS GuanQ (2019 November).MC\u2010Unet: multi\u2010scale convolution unet for bladder cancer cell segmentation in phase\u2010contrast microscopy images. In2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)(pp.1197\u20101199).IEEE.","DOI":"10.1109\/BIBM47256.2019.8983121"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12197"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2020.11.005"},{"key":"e_1_2_9_34_1","unstructured":"OktayO SchlemperJ FolgocLL et\u00a0al (2018).Attention u\u2010net: learning where to look for the pancreas.arXiv preprintarXiv:1804.03999."},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.680807"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1177788"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.061"},{"key":"e_1_2_9_38_1","unstructured":"DodgeJesse IlharcoGabriel SchwartzRoy FarhadiAli HajishirziHannaneh SmithNoah Fine\u2010Tuning Pretrained Language Models: Weight Initializations Data Orders and Early Stopping. arXiv:2002.06305 2020."},{"key":"e_1_2_9_39_1","unstructured":"MaJ WangB Segment anything in medical images.arXiv preprintarXiv:2304.12306.2023;2023."}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.14248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T12:13:20Z","timestamp":1706012000000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.14248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,21]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["10.1002\/acm2.14248"],"URL":"https:\/\/doi.org\/10.1002\/acm2.14248","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,21]]},"assertion":[{"value":"2023-09-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-11","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e14248"}}