{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:46:36Z","timestamp":1792082796459,"version":"4.4.0"},"reference-count":41,"publisher":"IOP Publishing","issue":"19","license":[{"start":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T00:00:00Z","timestamp":1727395200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/page\/copyright"},{"start":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T00:00:00Z","timestamp":1727395200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2024,10,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>\n                  <jats:italic>Objective.<\/jats:italic> To develop and evaluate a 3D Prompt-ResUNet module that utilized the prompt-based model combined with 3D nnUNet for rapid and consistent autosegmentation of high-risk clinical target volume (HRCTV) and organ at risk (OAR) in high-dose-rate brachytherapy for cervical cancer patients. <jats:italic>Approach.<\/jats:italic> We used 73 computed tomography scans and 62 magnetic resonance imaging scans from 135 (103 for training, 16 for validation, and 16 for testing) cervical cancer patients across two hospitals for HRCTV and OAR segmentation. A novel comparison of the deep learning neural networks 3D Prompt-ResUNet, nnUNet, and segment anything model-Med3D was applied for the segmentation. Evaluation was conducted in two parts: geometric and clinical assessments. Quantitative metrics included the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95%), Jaccard index (JI), and Matthews correlation coefficient (MCC). Clinical evaluation involved interobserver comparison, 4-grade expert scoring, and a double-blinded Turing test. <jats:italic>Main results.<\/jats:italic> The Prompt-ResUNet model performed most similarly to experienced radiation oncologists, outperforming less experienced ones. During testing, the DSC, HD95% (mm), JI, and MCC value (mean \u00b1 SD) for HRCTV were 0.92 \u00b1 0.03, 2.91 \u00b1 0.69, 0.85 \u00b1 0.04, and 0.92 \u00b1 0.02, respectively. For the bladder, these values were 0.93 \u00b1 0.05, 3.07 \u00b1 1.05, 0.87 \u00b1 0.08, and 0.93 \u00b1 0.05, respectively. For the rectum, they were 0.87 \u00b1 0.03, 3.54 \u00b1 1.46, 0.78 \u00b1 0.05, and 0.87 \u00b1 0.03, respectively. For the sigmoid, they were 0.76 \u00b1 0.11, 7.54 \u00b1 5.54, 0.63 \u00b1 0.14, and 0.78 \u00b1 0.09, respectively. The Prompt-ResUNet achieved a clinical viability score of at least 2 in all evaluation cases (100%) for both HRCTV and bladder and exceeded the 30% positive rate benchmark for all evaluated structures in the Turing test. <jats:italic>Significance.<\/jats:italic> The Prompt-ResUNet architecture demonstrated high consistency with ground truth in autosegmentation of HRCTV and OARs, reducing interobserver variability and shortening treatment times.<\/jats:p>","DOI":"10.1088\/1361-6560\/ad7ad1","type":"journal-article","created":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T22:59:41Z","timestamp":1726268381000},"page":"195008","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Deep learning-based segmentation for high-dose-rate brachytherapy in cervical cancer using 3D Prompt-ResUNet"],"prefix":"10.1088","volume":"69","author":[{"given":"Xian","family":"Xue","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lining","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dazhu","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lele","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3570-4461","authenticated-orcid":true,"given":"Quanfu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hefeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianwei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaosha","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjing","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangkun","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laiyuan","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinsheng","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengxiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fugen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2024,9,27]]},"reference":[{"key":"pmbad7ad1bib1","doi-asserted-by":"publisher","first-page":"181","DOI":"10.3390\/bioengineering10020181","article-title":"Comparing 3D, 2.5D, and 2D approaches to brain image auto-segmentation","volume":"10","author":"Avesta","year":"2023","journal-title":"Bioengineering"},{"key":"pmbad7ad1bib2","doi-asserted-by":"publisher","first-page":"1712","DOI":"10.1002\/mp.15490","article-title":"Automatic segmentation of high\u2010risk clinical target volume for tandem\u2010and\u2010ovoids brachytherapy patients using an asymmetric dual\u2010path convolutional neural network","volume":"49","author":"Cao","year":"2022","journal-title":"Med. Phys."},{"key":"pmbad7ad1bib3","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1007\/s40846-021-00624-0","article-title":"Image segmentation in 3D brachytherapy using convolutional LSTM","volume":"41","author":"Chang","year":"2021","journal-title":"J. Med. Biol. Eng."},{"key":"pmbad7ad1bib4","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.ygyno.2004.12.039","article-title":"Extended-field radiotherapy and high-dose-rate brachytherapy with concurrent and adjuvant cisplatin-based chemotherapy for locally advanced cervical cancer: a phase I\/II study","volume":"97","author":"Chung","year":"2005","journal-title":"Gynecol. Oncol."},{"key":"pmbad7ad1bib5","first-page":"1","author":"Deng","year":"2023"},{"key":"pmbad7ad1bib6","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.radonc.2011.12.024","article-title":"Recommendations from Gynaecological (GYN) GEC-ESTRO Working Group (IV): basic principles and parameters for MR imaging within the frame of image based adaptive cervix cancer brachytherapy","volume":"103","author":"Dimopoulos","year":"2012","journal-title":"Radiother. Oncol."},{"key":"pmbad7ad1bib7","doi-asserted-by":"publisher","first-page":"253","DOI":"10.5114\/jcb.2023.131242","article-title":"Inter-observer variation of target volume delineation for CT-guided cervical cancer brachytherapy","volume":"15","author":"Elmali","year":"2023","journal-title":"J. Contemp. Brachytherapy"},{"key":"pmbad7ad1bib8","author":"Fowler","year":"2024"},{"key":"pmbad7ad1bib9","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1186\/s13014-023-02350-0","article-title":"Towards deep-learning (DL) based fully automated target delineation for rectal cancer neoadjuvant radiotherapy using a divide-and-conquer strategy: a study with multicenter blind and randomized validation","volume":"18","author":"Geng","year":"2023","journal-title":"Radiother. Oncol."},{"key":"pmbad7ad1bib10","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1080\/14737140.2021.1879646","article-title":"Optimal treatment in locally advanced cervical cancer","volume":"21","author":"Gennigens","year":"2021","journal-title":"Expert Rev. Anticancer"},{"key":"pmbad7ad1bib11","author":"He","year":"2023"},{"key":"pmbad7ad1bib12","author":"Huang","year":"2024"},{"key":"pmbad7ad1bib13","doi-asserted-by":"publisher","DOI":"10.1093\/jicru\/ndw027","article-title":"Prescribing, recording, and reporting brachytherapy for cancer of the cervix","volume":"13","author":"International Commission on Radiation Units and Measurements","year":"2013"},{"key":"pmbad7ad1bib14","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"pmbad7ad1bib15","doi-asserted-by":"publisher","first-page":"1721","DOI":"10.21037\/atm-21-4074","article-title":"RefineNet-based automatic delineation of the clinical target volume and organs at risk for three-dimensional brachytherapy for cervical cancer","volume":"9","author":"Jiang","year":"2021","journal-title":"Ann. Transl. Med."},{"key":"pmbad7ad1bib16","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1056\/NEJM199904153401503","article-title":"Cisplatin, radiation, and adjuvant hysterectomy compared with radiation and adjuvant hysterectomy for bulky stage IB cervical carcinoma","volume":"340","author":"Keys","year":"1999","journal-title":"New Engl. J. Med."},{"key":"pmbad7ad1bib17","author":"Kirillov","year":"2023"},{"key":"pmbad7ad1bib18","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1186\/s13014-022-02121-3","article-title":"A deep learning-based self-adapting ensemble method for segmentation in gynecological brachytherapy","volume":"17","author":"Li","year":"2022","journal-title":"Radiother. Oncol."},{"key":"pmbad7ad1bib19","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"pmbad7ad1bib20","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.radonc.2021.03.030","article-title":"Deep learning-based auto-segmentation of organs at risk in high-dose rate brachytherapy of cervical cancer","volume":"159","author":"Mohammadi","year":"2021","journal-title":"Radiother. Oncol."},{"key":"pmbad7ad1bib21","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1056\/NEJM199904153401501","article-title":"Pelvic radiation with concurrent chemotherapy compared with pelvic and para-aortic radiation for high-risk cervical cancer","volume":"340","author":"Morris","year":"1999","journal-title":"New Engl. J. Med."},{"key":"pmbad7ad1bib22","doi-asserted-by":"publisher","DOI":"10.1016\/j.critrevonc.2022.103704","article-title":"Postoperative treatment of intermediate-risk early stage cervical cancer: results of a survey from the Gynecology Study Group in the AIRO Gyn and MITO Groups","volume":"174","author":"Perrucci","year":"2022","journal-title":"Crit. Rev. Oncol. Hematol."},{"key":"pmbad7ad1bib23","doi-asserted-by":"publisher","first-page":"4605","DOI":"10.1200\/JCO.22.02769","article-title":"Concurrent chemotherapy and pelvic radiation therapy compared with pelvic radiation therapy alone as adjuvant therapy after radical surgery in high-risk early-stage cancer of the cervix","volume":"41","author":"Peters","year":"2023","journal-title":"J. Clin. Oncol."},{"key":"pmbad7ad1bib24","doi-asserted-by":"publisher","first-page":"1144","DOI":"10.1056\/NEJM199904153401502","article-title":"Concurrent cisplatin-based radiotherapy and chemotherapy for locally advanced cervical cancer","volume":"340","author":"Rose","year":"1999","journal-title":"New Engl. J. Med."},{"key":"pmbad7ad1bib25","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/S0167-8140(00)00185-7","article-title":"Inter-observer variation in delineation of bladder and rectum contours for brachytherapy of cervical cancer","volume":"56","author":"Saarnak","year":"2000","journal-title":"Radiother. Oncol."},{"key":"pmbad7ad1bib26","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.3390\/diagnostics13111947","article-title":"Generalist vision foundation models for medical imaging: a case study of segment anything model on zero-shot medical segmentation","volume":"13","author":"Shi","year":"2023","journal-title":"Diagnostics"},{"key":"pmbad7ad1bib27","author":"Stein","year":"2023"},{"key":"pmbad7ad1bib28","doi-asserted-by":"publisher","first-page":"1770","DOI":"10.3390\/cancers12071770","article-title":"FIGO 2018 staging for cervical cancer: influence on stage distribution and outcomes in the 3D-image-guided brachytherapy era","volume":"12","author":"Tomizawa","year":"2020","journal-title":"Cancers"},{"key":"pmbad7ad1bib29","doi-asserted-by":"publisher","first-page":"4558","DOI":"10.1002\/mp.13147","article-title":"Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks","volume":"45","author":"Tong","year":"2018","journal-title":"Med. Phys."},{"key":"pmbad7ad1bib30","article-title":"Attention Is All You Need","author":"Vaswani","year":"2017"},{"key":"pmbad7ad1bib31","article-title":"SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images","author":"Wang","year":"2023"},{"key":"pmbad7ad1bib32","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.media.2019.03.003","article-title":"CT male pelvic organ segmentation using fully convolutional networks with boundary sensitive representation","volume":"54","author":"Wang","year":"2019","journal-title":"Med. Image Anal."},{"key":"pmbad7ad1bib33","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1200\/JCO.1999.17.5.1339","article-title":"Randomized comparison of fluorouracil plus cisplatin versus hydroxyurea as an adjunct to radiation therapy in stage IIB-IVA carcinoma of the cervix with negative para-aortic lymph nodes: a Gynecologic Oncology Group and Southwest Oncology Group study","volume":"17","author":"Whitney","year":"1999","journal-title":"J. Clin. Oncol."},{"key":"pmbad7ad1bib34","doi-asserted-by":"publisher","first-page":"S34","DOI":"10.1016\/S0167-8140(20)30964-6","article-title":"72: deep learning-based auto-segmentation for pelvic organs-at-risk and clinical target volumes in intracavitary high dose rate brachytherapy","volume":"150","author":"Wong","year":"2020","journal-title":"Radiother. Oncol."},{"key":"pmbad7ad1bib35","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14371","article-title":"A deep learning-based 3D Prompt-nnUnet model for automatic segmentation in brachytherapy of postoperative endometrial carcinoma","volume":"25","author":"Xue","year":"2024","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"pmbad7ad1bib36","doi-asserted-by":"publisher","first-page":"1571","DOI":"10.1002\/mp.15506","article-title":"Automatic segmentation of magnetic resonance images for high\u2010dose\u2010rate cervical cancer brachytherapy using deep learning","volume":"49","author":"Yoganathan","year":"2022","journal-title":"Med. Phys."},{"key":"pmbad7ad1bib37","doi-asserted-by":"publisher","first-page":"7028","DOI":"10.1002\/mp.15268","article-title":"Fully automated multiorgan segmentation of female pelvic magnetic resonance images with coarse\u2010to\u2010fine convolutional neural network","volume":"48","author":"Zabihollahy","year":"2021","journal-title":"Med. Phys."},{"key":"pmbad7ad1bib38","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1002\/acm2.13024","article-title":"Automatic segmentation and applicator reconstruction for CT-based brachytherapy of cervical cancer using 3D convolutional neural networks","volume":"21","author":"Zhang","year":"2020","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"pmbad7ad1bib39","author":"Zhang","year":"2023"},{"key":"pmbad7ad1bib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2022.102088","article-title":"Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: an empirical study of 2.5D solutions","volume":"99","author":"Zhang","year":"2022","journal-title":"Comput. Med. Imaging Graph."},{"key":"pmbad7ad1bib41","article-title":"Segment Everything Everywhere All at Once","author":"Zou","year":"2023"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad7ad1","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad7ad1\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad7ad1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad7ad1\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad7ad1\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad7ad1\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad7ad1\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad7ad1\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T12:13:30Z","timestamp":1727439210000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad7ad1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,27]]},"references-count":41,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2024,9,27]]},"published-print":{"date-parts":[[2024,10,7]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ad7ad1","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,27]]},"assertion":[{"value":"Deep learning-based segmentation for high-dose-rate brachytherapy in cervical cancer using 3D Prompt-ResUNet","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2024-04-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-09-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-09-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}