{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T18:40:37Z","timestamp":1792608037229,"version":"4.5.0"},"reference-count":40,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:00:00Z","timestamp":1792540800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:00:00Z","timestamp":1792540800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12375335"],"award-info":[{"award-number":["12375335"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["25JL001"],"award-info":[{"award-number":["25JL001"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Segment Anything Model (SAM), a prompt\u2010guided foundation model, exhibits substantial potential for medical image segmentation by incorporating prior knowledge through user\u2010defined prompts. However, the application of SAM in radiotherapy target delineation remains limited.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study proposes a feasible prompt\u2010guided interactive delineation workflow driven by an optimized SAM.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 100 rectal cancer neoadjuvant radiotherapy cases were collected (60 for training and 40 for testing). This study utilized bounding\u2010box prompts to guide SAM for GTV segmentation. Physicians manually draw box prompts on certain slices, while box prompts for the remaining slices are automatically generated using an interpolation strategy. Four fine\u2010tuning strategies for SAM training were evaluated, and the impact of prompt numbers and placements was assessed as well. The performance of the finalized workflow with optimized SAM was compared with five state\u2010of\u2010the\u2010art (SOTA) models, and its robustness to prompt variations in middle\u2010slice selection and box\u2010prompt margins was analyzed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Compared to other fine\u2010tuning methods, freezing the image encoder obtained the most stable performance. Prompts on only 3 slices achieved accuracy comparable to prompts on all slices. The placement of the middle\u2010slice prompt exhibited negligible impact (\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&gt;\u00a00.05). The finalized SAM\u2010driven workflow outperformed end\u2010to\u2010end baseline models both visually and quantitatively (3D DSC: 0.92\u00a0vs 0.80; 3D HD95: 2.73\u00a0vs 12.70; IoU: 0.86\u00a0vs 0.67; Sensitivity: 91.20%\u00a0vs 85.98%; Precision: 93.65%\u00a0vs 79.23%), while maintaining stable performance across certain prompt variations.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed SAM\u2010driven interactive workflow with as few as 3 box prompts achieves favorable accuracy of GTV segmentation for rectal cancer neoadjuvant radiotherapy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70733","type":"journal-article","created":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T18:02:58Z","timestamp":1792605778000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Segment anything model (SAM)\u2010driven prompt\u2010guided interactive delineation of gross tumor volume for rectal cancer neoadjuvant radiotherapy"],"prefix":"10.1002","volume":"53","author":[{"given":"Si","family":"Wu","sequence":"first","affiliation":[{"name":"Institute of Medical Technology Peking University Health Science Center  Beijing China"},{"name":"Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education\/Beijing) Department of Radiation Oncology Peking University Cancer Hospital &amp; Institute  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhao","family":"Geng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education\/Beijing) Department of Radiation Oncology Peking University Cancer Hospital &amp; Institute  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Bai","sequence":"additional","affiliation":[{"name":"MedMind Technology Co., Ltd  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[{"name":"MedMind Technology Co., Ltd  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaobin","family":"Wang","sequence":"additional","affiliation":[{"name":"MedMind Technology Co., Ltd  Beijing China"},{"name":"Department of Biomedical Engineering School of Medicine Tsinghua University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education\/Beijing) Department of Radiation Oncology Peking University Cancer Hospital &amp; Institute  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Du","sequence":"additional","affiliation":[{"name":"Institute of Medical Technology Peking University Health Science Center  Beijing China"},{"name":"Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education\/Beijing) Department of Radiation Oncology Peking University Cancer Hospital &amp; Institute  Beijing China"},{"name":"Inner Mongolia Engineering Center of Digital\u2010Intelligent Integrated Prevention and Screening of Malignant Tumors Proton Center &amp; Department of Radiation Oncology Peking University Cancer Hospital (Inner Mongolia Campus)\/Affiliated Cancer Hospital of Inner Mongolia Medical University  Hohhot China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,21]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.21147\/j.issn.1000\u20109604.2021.04.07"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1097\/CM9.0000000000001076"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/pro6.1141"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2017.00221"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2016.07.017"},{"key":"e_1_2_9_8_1","volume-title":"Rectal Cancer","author":"NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines)","year":"2023"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2025.110999"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1510568"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12602"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.01.020"},{"key":"e_1_2_9_13_1","doi-asserted-by":"crossref","unstructured":"ChenL ZhuY PapandreouG SchroffF AdamH Encoder\u2010decoder with atrous separable convolution for semantic image segmentation. In:Proceedings of the European conference on computer vision (ECCV).Springer;2018:833\u2013851.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.4441"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014\u2010023\u201002350\u20100"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014\u2010025\u201002694\u20109"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001008\u2010z"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105715"},{"key":"e_1_2_9_19_1","unstructured":"KirillovA MintunE RaviN et\u00a0al.Segment anything. In:IEEE\/CVF Conference on Computer Vision (ICCV).IEEE;2023:4015\u20134026."},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2024.105526"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17785"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107140"},{"key":"e_1_2_9_23_1","doi-asserted-by":"crossref","unstructured":"RahmanMM MunirM JhaD BagciU MarculescuR PP\u2010SAM: perturbed prompts for robust adaption of segment anything model for polyp segmentation. In:IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE;2024:4989\u20134995. doi:10.1109\/CVPRW63382.2024.00504","DOI":"10.1109\/CVPRW63382.2024.00504"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2025.06.3550"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17958"},{"key":"e_1_2_9_26_1","first-page":"659","article-title":"Unified prompt\u2010visual interactive segmentation of clinical target volume in CT for nasopharyngeal carcinoma with prior anatomical information","author":"Khor HG","year":"2024","journal-title":"Medical Image Computing and Computer Assisted Intervention (MICCAI)"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16965"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2024.07.104"},{"key":"e_1_2_9_29_1","unstructured":"HuEJ ShenY WallisP et\u00a0al.LoRA: low\u2010rank adaptation of large language models. In:International Conference on Learning Representations;2022."},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2011.03.031"},{"key":"e_1_2_9_31_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT U\u2010Net: convolutional networks for biomedical image segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2015:234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_32_1","unstructured":"ChenJ LuY YuQ et\u00a0al.Transunet: Transformers make strong encoders for medical image segmentation. arXiv:2102.04306."},{"key":"e_1_2_9_33_1","doi-asserted-by":"crossref","unstructured":"CaoH WangY ChenJ et\u00a0al.Swin\u2010unet: unet\u2010like pure transformer for medical image segmentation. In:European Conference on Computer Vision.Springer;2022:205\u2013218.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278\u2010025\u201001464\u2010z"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103280"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2024.109248"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13104\u2010022\u201006096\u2010y"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00066\u2010024\u201002313\u20108"},{"key":"e_1_2_9_40_1","unstructured":"RaviN GabeurV HuY\u2010T et\u00a0al.SAM 2: segment anything in images and videos. In:The Thirteenth International Conference on Learning Representations.2024."},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201044824\u2010z"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70733","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70733","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T18:03:01Z","timestamp":1792605781000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70733"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,21]]},"references-count":40,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["10.1002\/mp.70733"],"URL":"https:\/\/doi.org\/10.1002\/mp.70733","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,21]]},"assertion":[{"value":"2026-01-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70733"}}