{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T06:57:17Z","timestamp":1792652237084,"version":"4.5.0"},"reference-count":63,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>BACKGROUND<\/jats:title>\n                    <jats:p>High\u2010dose\u2010rate brachytherapy (HDR\u2010BT) is a cornerstone of cervical cancer (CC) treatment, requiring the precise delineation of high\u2010risk clinical target volumes (HR\u2010CTV) and organs at risk (OARs) for effective dose delivery and toxicity reduction. However, the time\u2010sensitive nature of HDR\u2010BT planning and its reliance on expert contouring introduce inter\u2010 and intra\u2010observer variability, posing challenges for consistent and accurate treatment planning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>PURPOSE<\/jats:title>\n                    <jats:p>This study proposes a novel deep learning (DL)\u2010based auto\u2010segmentation framework, guided by task\u2010specific prompts generated from large language models (LLMs), to address these challenges and improve segmentation accuracy and efficiency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>\n                      A retrospective dataset of 32 CC patients, encompassing 124 planning computed tomography (pCT) images, was utilized. The framework integrates clinical guidelines for organ contouring from the American Brachytherapy Society (ABS), the European Society for Radiotherapy and Oncology (ESTRO), and the International Commission on Radiation Units and Measurements (ICRU). LLMs, particularly Chat\u2010GPT, extracts domain knowledge from these contouring guidelines to generate task\u2010specific prompts, which guide a Swin transformer\u2010based encoder and a fully convolutional network (FCN) decoder for segmentation. The DL pipeline was evaluated on HR\u2010CTV and OARs, including the bladder, rectum, and sigmoid. Metrics such as Dice similarity coefficient (DSC), Hausdorff distance (HD95%), mean surface distance (MSD), and center\u2010of\u2010mass distance (CMD) were used for performance assessment. An ablation study compared the prompt\u2010guided approach with a baseline model without prompt guidance. Statistical differences were tested with two\u2010tailed paired\n                      <jats:italic>t<\/jats:italic>\n                      \u2010tests, and\n                      <jats:italic>p<\/jats:italic>\n                      \u2010values were adjusted using the Benjamini\u2013Hochberg method to address the multiple comparisons correction and results with adjusted\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.05 were deemed significant. Cohen's d values were calculated to quantify effect sizes.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>\n                      The proposed framework achieved the highest segmentation for the bladder (DSC of 0.91\u00a0\u00b1\u00a00.07), followed by the HR\u2010CTV (DSC of 0.80\u00a0\u00b1\u00a00.08) and the rectum (DSC of 0.78\u00a0\u00b1\u00a00.07), and a lower accuracy for sigmoid (DSC of 0.63\u00a0\u00b1\u00a00.15) due to its small size and irregular shape. Boundary precision was highest for the HR\u2010CTV (HD95%: 6.32\u00a0\u00b1\u00a02.31\u00a0mm). The ablation study confirmed the contribution of prompt guidance, with statistically significant improvements in DSC and\/or HD95% (\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.05) for all OARs. Prompt guidance, however, did not improve the accuracy of HR\u2010CTV delineation.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSIONS<\/jats:title>\n                    <jats:p>This study demonstrates the feasibility and effectiveness of integrating LLM\u2010generated task\u2010specific prompts with DL\u2010based segmentation for HDR\u2010BT in CC. The proposed framework enhances segmentation consistency to support accurate treatment planning, addressing critical challenges in HDR\u2010BT workflows.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70034","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T12:47:45Z","timestamp":1758631665000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Enhancing auto\u2010contouring with large language model in high\u2010dose rate brachytherapy for cervical cancers"],"prefix":"10.1002","volume":"52","author":[{"given":"Jing","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology Icahn School of Medicine at Mount Sinai  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Icahn School of Medicine at Mount Sinai  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaida","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Icahn School of Medicine at Mount Sinai  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beth Bradshaw","family":"Ghavidel","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology and Winship Cancer Institute Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benyamin","family":"Khajetash","sequence":"additional","affiliation":[{"name":"Department of Medical Physics School of Medicine Iran University of Medical Sciences  Tehran IRAN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abolfazl","family":"Sarikhani","sequence":"additional","affiliation":[{"name":"Department of Medical Physics School of Medicine Iran University of Medical Sciences  Tehran IRAN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Houshyari","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Shahid Beheshti University of Medical Sciences  Tehran IRAN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Icahn School of Medicine at Mount Sinai  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Icahn School of Medicine at Mount Sinai  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meysam","family":"Tavakoli","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology and Winship Cancer Institute Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,9,23]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(19)30482-6"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acba76"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-022-02121-3"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2018.11.009"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.11.012"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2016.11.011"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(21)00720-8"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/61\/17\/6531"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2011.12.024"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2010.06.004"},{"issue":"1","key":"e_1_2_9_12_1","first-page":"48","article-title":"ICRU report 89: prescribing, recording, and reporting brachytherapy for cancer of the cervix","volume":"42","author":"Swamidas J","year":"2017","journal-title":"J Med Phys"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.09.060"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-018-1033-y"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2013.08.010"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2020.01.002"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8140(02)00373-0"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12602"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8140(01)00386-3"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8140(00)00185-7"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4819945"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.5114\/jcb.2019.88762"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3302141"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1080\/0284186X.2018.1529421"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.10.019"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13988"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110332"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0185844"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpj.2025.03.023"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.05.003"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-020-05013-4"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13296"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13300"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.09.022"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2021.08.002"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-020-01617-0"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2017.11.012"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2021.06.017"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-022-02121-3"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.4630"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1219326"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1169595"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.2196\/65033"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/hcs2.79"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-024-02972-y"},{"key":"e_1_2_9_46_1","unstructured":"OpenAI \u201cJSON mode \u201dOpenAI Developer Documentation December 13 2023.https:\/\/community.openai.com\/t\/openai\u2010api\u2010guide\u2010using\u2010json\u2010mode\/557265"},{"issue":"4","key":"e_1_2_9_47_1","article-title":"Capacity of ChatGPT to identify guideline\u2010based treatments for advanced solid tumors","volume":"15","author":"Schulte B","year":"2023","journal-title":"Cureus"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00404-024-07667-z"},{"key":"e_1_2_9_49_1","doi-asserted-by":"crossref","unstructured":"ZhongY XuM LiangK ChenK WuM.Ariadne's thread: using text prompts to improve segmentation of infected areas from chest X\u2010ray images.Medical Image Computing and Computer Assisted Intervention Miccai 2023 Pt Iv Vol.14223 pp.724\u2013733.Springer;2023.","DOI":"10.1007\/978-3-031-43901-8_69"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad0d45"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7962-2_30"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17235"},{"key":"e_1_2_9_53_1","series-title":"PMLR: Proceedings of Machine Learning Research","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford A","year":"2021"},{"key":"e_1_2_9_54_1","unstructured":"ChenH ZhouY WangX et\u00a0al.Multi\u2010modal generative AI: multi\u2010modal LLM diffusion and beyond.2024. arXiv preprint arXiv:2409.14993"},{"key":"e_1_2_9_55_1","doi-asserted-by":"crossref","unstructured":"OuyangX DongdongG XuejianL et al.Prompt\u2010based segmentation model of anatomical structures and Lesions in CT images. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention. Cham: Springer Nature Switzerland;2024 pp.522\u2010532.","DOI":"10.1007\/978-3-031-72111-3_49"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2004.12.015"},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"e_1_2_9_58_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2009.0127"},{"key":"e_1_2_9_59_1","unstructured":"BeckerLA.Effect size (ES).2000."},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_2_9_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrras.2024.100925"},{"key":"e_1_2_9_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2021.04.019"},{"key":"e_1_2_9_63_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-021-01837-y"},{"key":"e_1_2_9_64_1","unstructured":"ZhaoZ LiuY WuH et\u00a0al.Clip in medical imaging: A comprehensive survey.2023.arXiv preprint arXiv:2312.07353"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70034","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70034","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:48:33Z","timestamp":1772992113000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,23]]},"references-count":63,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1002\/mp.70034"],"URL":"https:\/\/doi.org\/10.1002\/mp.70034","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,23]]},"assertion":[{"value":"2025-02-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70034"}}