{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T14:19:10Z","timestamp":1788272350231,"version":"build-2803163510"},"reference-count":26,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":2,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Real\u2010time multi\u2010class motion tracking on cine images during magnetic resonance\u2010guided radiation therapy (MRgRT) would enable instant monitoring of anatomical structures, facilitating dynamic beam control to minimize overdose to normal tissues and maximize tumor dose. However, conventional segmentation strategies incur significant time delays, making their clinical application impractical. Emerging deep learning (DL) technologies can provide a path to address this clinical challenge.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To propose a patient\u2010specific framework for real\u2010time automated simultaneous tracking of multiple anatomical structures on 2D magnetic resonance cine (cine MR) images acquired in two orthogonal planes, using DL techniques without the need for extensive training data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, we evaluated SegResNet, a DL\u2010based auto\u2010segmentation model, and TransMorph, a DL\u2010based registration model. Additionally, conventional rigid and B\u2010spline registration algorithms served as baseline models. Our datasets consist of 10 subjects, with both coronal and sagittal image sequences acquired for each subject using Elekta Unity MR\u2010Linac protocols. With ground truth contours manually delineated for every frame, each model was trained and tested on a subject\u00a0and plane\u2010specific basis. Dice similarity coefficient (DSC), 95th\u2010percentile Hausdorff distance (HD95), average surface distance (ASD), and center\u2010of\u2010mass errors (COME) were chosen to evaluate the output segmentations of each model. Furthermore, to analyze segmentation motion consistency across two orthogonal planes, the temporal rhythm and physical magnitude of the liver centroid trajectory were evaluated using the Pearson correlation coefficient (PCC) and the mean\u2010centered Concordance correlation coefficient (CCC), respectively. Finally, a phase\u2010resolved analysis was conducted to assess the robustness of each model across the motion cycle.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      SegResNet yielded significantly better results than registration models (\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.05). Averaged across all organs, planes, and subjects, SegResNet achieved an overall DSC of 0.97\u00a0\u00b1\u00a00.01, HD95 of 3.0\u00a0\u00b1\u00a00.9\u00a0mm, ASD of 1.1\u00a0\u00b1\u00a00.3\u00a0mm, and COME of 0.9\u00a0\u00b1\u00a00.4\u00a0mm. The PCC and mean\u2010centered CCC of SegResNet are 0.77\u00a0\u00b1\u00a00.07 and 0.75\u00a0\u00b1\u00a00.08, respectively. Furthermore, phase\u2010resolved analysis demonstrated SegResNet's phase\u2010agnostic spatial stability, with no statistically significant differences (\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&gt;\u00a00.05) observed across the three kinematic states for any organ across all evaluated segmentation metrics. The average inference time for SegResNet is approximately 0.3\u00a0ms per frame.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>SegResNet outperformed TransMorph, as well as conventional B\u2010spline and rigid registration models in terms of segmentation accuracy, cross\u2010plane consistency, and robustness across different motion phases, and computation efficiency, potentially allowing for real\u2010time simultaneous motion tracking of multiple anatomical structures on cine MR during MRgRT.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70622","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T03:40:31Z","timestamp":1785814831000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Patient\u2010specific automated multi\u2010class anatomical motion tracking on real\u2010time cine MR images using deep learning techniques"],"prefix":"10.1002","volume":"53","author":[{"given":"Kaishen","family":"Li","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology University of Florida  Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjiv S.","family":"Samant","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Florida  Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.7150\/ijms.3635"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2016.01.033"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0205917"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.3978\/j.issn.2078\u20106891.2014.028"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0360\u20103016(00)00625\u20108"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2014.12.013"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2010.08.003"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0360\u20103016(01)01516\u20104"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167\u20108140(00)00226\u20107"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2005.05.066"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360\u20103016(99)00056\u20105"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2007.10.034"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2018.08.001"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014\u2010019\u20101275\u20103"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13002"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14230"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2022.09.086"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2897538"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2025.3599457"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14659"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2024.10.021"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11726-9_28"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102615"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Delving deep into rectifiers: Surpassing human\u2010level performance on ImageNet classification.In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV);2015:1026\u20101034. doi:10.1109\/ICCV.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42979\u2010021\u201000815\u20101"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16342"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70622","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70622","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T13:43:06Z","timestamp":1788270186000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70622"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":26,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1002\/mp.70622"],"URL":"https:\/\/doi.org\/10.1002\/mp.70622","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"2025-11-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70622"}}