{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T20:18:58Z","timestamp":1792613938621,"version":"4.5.0"},"reference-count":43,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Adaptive radiation treatment (ART) for locally advanced pancreatic cancer (LAPC) requires consistently accurate segmentation of the extremely mobile gastrointestinal (GI) organs at risk (OAR) including the stomach, duodenum, large and small bowel. Also, due to lack of sufficiently accurate and fast deformable image registration (DIR), accumulated dose to the GI OARs is currently only approximated, further limiting the ability to more precisely adapt treatments.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Develop a 3\u2010D <jats:styled-content>Pro<\/jats:styled-content>gressively refined joint <jats:styled-content>R<\/jats:styled-content>egistration\u2010<jats:styled-content>Seg<\/jats:styled-content>mentation (ProRSeg) deep network to deformably align and segment treatment fraction magnetic resonance images (MRI)s, then evaluate segmentation accuracy, registration consistency, and feasibility for OAR dose\u00a0accumulation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Method<\/jats:title><jats:p>ProRSeg was trained using five\u2010fold cross\u2010validation with 110 T2\u2010weighted MRI acquired at five treatment fractions from 10 different patients, taking care that same patient scans were not placed in training and testing folds. Segmentation accuracy was measured using Dice similarity coefficient (DSC) and Hausdorff distance at 95th percentile (HD95). Registration consistency was measured using coefficient of variation (CV) in displacement of OARs. Statistical comparison to other deep learning and iterative registration methods were done using the Kruskal\u2010Wallis test, followed by pair\u2010wise comparisons with Bonferroni correction applied for multiple testing. Ablation tests and accuracy comparisons against multiple methods were done. Finally, applicability of ProRSeg to segment cone\u2010beam CT (CBCT) scans was evaluated on a publicly available dataset of 80 scans using five\u2010fold\u00a0cross\u2010validation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>ProRSeg processed 3D volumes (128 \u00d7 192 \u00d7 128) in 3 s on a NVIDIA Tesla V100 GPU. It's segmentations were significantly more accurate () than compared methods, achieving a DSC of 0.94 \u00b10.02 for liver, 0.88\u00b10.04 for large bowel, 0.78\u00b10.03 for small bowel and 0.82\u00b10.04 for stomach\u2010duodenum from MRI. ProRSeg achieved a DSC of 0.72\u00b10.01 for small bowel and 0.76\u00b10.03 for stomach\u2010duodenum from public CBCT dataset. ProRSeg registrations resulted in the lowest CV in displacement (stomach\u2010duodenum : 0.75%, : 0.73%, and : 0.81%; small bowel : 0.80%, : 0.80%, and : 0.68%; large bowel : 0.71%,  : 0.81%, and : 0.75%). ProRSeg based dose accumulation accounting for intra\u2010fraction (pre\u2010treatment to post\u2010treatment MRI scan) and inter\u2010fraction motion showed that the organ dose constraints were violated in four patients for stomach\u2010duodenum and for three patients for small bowel. Study limitations include lack of independent testing and ground truth phantom datasets to measure dose accumulation\u00a0accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>ProRSeg produced more accurate and consistent GI OARs segmentation and DIR of MRI and CBCTs compared to multiple methods. Preliminary results indicates feasibility for OAR dose accumulation using\u00a0ProRSeg.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16527","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T10:43:32Z","timestamp":1685702612000},"page":"4758-4774","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Progressively refined deep joint registration segmentation (ProRSeg) of gastrointestinal organs at risk: Application to MRI and cone\u2010beam CT"],"prefix":"10.1002","volume":"50","author":[{"given":"Jue","family":"Jiang","sequence":"first","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kathryn","family":"Tringale","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Memorial Sloan Kettering Cancer Center New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marsha","family":"Reyngold","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Memorial Sloan Kettering Cancer Center New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Crane","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Memorial Sloan Kettering Cancer Center New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neelam","family":"Tyagi","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harini","family":"Veeraraghavan","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,6,2]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.10.021"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2017.11.032"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_2_8_5_1","first-page":"234","article-title":"U\u2010net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger O","year":"2015","journal-title":"MICCAI"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2806309"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14429"},{"key":"e_1_2_8_8_1","first-page":"1748","article-title":"Unetr: Transformers for 3d medical image segmentation","author":"Hatamizadeh A","year":"2022","journal-title":"IEEE\/CVF Winter Conf. Applications of Computer Vision"},{"key":"e_1_2_8_9_1","first-page":"S0360","article-title":"A prior knowledge guided deep learning based semi\u2010automatic segmentation for complex anatomy on MRI","volume":"22","author":"Ying Z","year":"2022","journal-title":"Intl J of Radiat Oncol Biol Phys"},{"key":"e_1_2_8_10_1","doi-asserted-by":"crossref","unstructured":"JiangJ TyagiN TringaleK CraneC VeeraraghavanH.Self\u2010supervised 3d anatomy segmentation using self\u2010distilled masked image transformer (SMIT).Medical Image Computing and Computer Assisted Intervention \u2010 MICCAI 2022. MICCAI 2022. Lecture Notes in Computer Science.Springer;2022.","DOI":"10.1007\/978-3-031-16440-8_53"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12307"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.06.007"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2020.04.027"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2007.07.007"},{"key":"e_1_2_8_15_1","first-page":"420","article-title":"Deepatlas: Joint semi\u2010supervised learning of image registration and segmentation","author":"Xu Z","year":"2019","journal-title":"MICCAI"},{"key":"e_1_2_8_16_1","doi-asserted-by":"crossref","unstructured":"HeY LiT YangG et\u00a0al.Deep complementary joint model for complex scene registration and few\u2010shot segmentation on medical images.Computer Vision \u2010 ECCV 2020. ECCV 2020.Springer;2020:1.","DOI":"10.1007\/978-3-030-58523-5_45"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","unstructured":"EstienneT VakalopoulouM ChristodoulidisS et\u00a0al.U\u2010resnet: Ultimate coupling of registration and segmentation with deep nets.Medical Image Computing and Computer Assisted Intervention \u2010 MICCAI 2019. MICCAI 2019.Springer;2019:310\u2010319.","DOI":"10.1007\/978-3-030-32248-9_35"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2897538"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"MokTC ChungA.Fast symmetric diffeomorphic image registration with convolutional neural networks.2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE;2020:4644\u20104653.","DOI":"10.1109\/CVPR42600.2020.00470"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12734"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2014.05.005"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.11.010"},{"key":"e_1_2_8_23_1","doi-asserted-by":"crossref","unstructured":"ZhaoS DongY ChangEI et\u00a0al.Recursive cascaded networks for unsupervised medical image registration.2019 IEEE\/CVF International Conference on Computer Vision (ICCV).IEEE 2019:10\u00a0600\u201010\u00a0610.","DOI":"10.1109\/ICCV.2019.01070"},{"key":"e_1_2_8_24_1","first-page":"8758","article-title":"Recurrent registration neural networks for deformable image registration","volume":"32","author":"Sandk\u00fchler R","year":"2019","journal-title":"NeurIPS"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3154934"},{"key":"e_1_2_8_26_1","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"Shi X","year":"2015","journal-title":"arXiv preprint arXiv:1506.04214"},{"key":"e_1_2_8_27_1","first-page":"62","article-title":"A cross\u2010stitch architecture for joint registration and segmentation in adaptive radiotherapy","author":"Beljaards L","year":"2020","journal-title":"Med Imaging with Deep Learning"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2022.02.007"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-022-00732-6"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14906"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01758-9"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2021.07.006"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4734928"},{"key":"e_1_2_8_34_1","article-title":"Spatial transformer networks","author":"Jaderberg M","year":"2015","journal-title":"arXiv preprint arXiv:1506.02025"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.07.006"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2007.06.004"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1177\/1948550617697177"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14906"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2021.01.007"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13620"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.01.021"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32226-7_1"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2022.100968"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102041"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T14:53:16Z","timestamp":1755874396000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16527"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,2]]},"references-count":43,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10.1002\/mp.16527"],"URL":"https:\/\/doi.org\/10.1002\/mp.16527","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,2]]},"assertion":[{"value":"2022-09-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}