{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:27:10Z","timestamp":1780536430615,"version":"3.54.1"},"reference-count":35,"publisher":"Wiley","issue":"12","license":[{"start":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T00:00:00Z","timestamp":1635465600000},"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":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To create a network which fully utilizes multi\u2010sequence MRI and compares favorably with manual human contouring.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We retrospectively collected 89 MRI studies of the pelvic cavity from patients with prostate cancer and cervical cancer. The dataset contained 89 samples from 87 patients with a total of 84 valid samples. MRI was performed with T1\u2010weighted (T1), T2\u2010weighted (T2), and Enhanced Dixon T1\u2010weighted (T1DIXONC) sequences. There were two cohorts. The training cohort contained 55 samples and the testing cohort contained 29 samples. The MRI images in the training cohort contained contouring data from radiotherapist \u03b1. The MRI images in the testing cohort contained contouring data from radiotherapist \u03b1 and contouring data from another radiotherapist: radiotherapist \u03b2. The training cohort was used to optimize the convolution neural networks, which included the attention mechanism through the proposed activation module and the blended module into multiple MRI sequences, to perform autodelineation. The testing cohort was used to assess the networks\u2019 autodelineation performance. The contoured organs at risk (OAR) were the anal canal, bladder, rectum, femoral head (L), and femoral head (R).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We compared our proposed network with UNet and FuseUNet using our dataset. When T1 was the main sequence, we input three sequences to segment five organs and evaluated the results using four metrics: the DSC (Dice similarity coefficient), the JSC (Jaccard similarity coefficient), the ASD (average mean distance), and the 95% HD (robust Hausdorff distance). The proposed network achieved improved results compared with the baselines among all metrics. The DSC were 0.834\u00b10.029, 0.818\u00b10.037, and 0.808\u00b10.050 for our proposed network, FuseUNet, and UNet, respectively. The 95% HD were 7.256\u00b12.748\u00a0mm, 8.404\u00b13.297\u00a0mm, and 8.951\u00b14.798\u00a0mm for our proposed network, FuseUNet, and UNet, respectively. Our proposed network also had superior performance on the JSC and ASD coefficients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our proposed activation module and blended module significantly improved the performance of FuseUNet for multi\u2010sequence MRI segmentation. Our proposed network integrated multiple MRI sequences efficiently and autosegmented OAR rapidly and accurately. We also discovered that three\u2010sequence fusion (T1\u2010T1DIXONC\u2010T2) was superior to two\u2010sequence fusion (T1\u2010T2 and T1\u2010T1DIXONC, respectively). We infer that the more MRI sequences fused, the better the automatic segmentation results.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15285","type":"journal-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T18:18:50Z","timestamp":1634753930000},"page":"7930-7945","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Integrating multiple MRI sequences for pelvic organs segmentation via the attention mechanism"],"prefix":"10.1002","volume":"48","author":[{"given":"Sijuan","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology Sun Yat\u2010sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy  Guangzhou Guangdong 510060 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zesen","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Sun Yat\u2010sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy  Guangzhou Guangdong 510060 China"},{"name":"School of Electronic and Information Engineering South China University of Technology  Guangzhou Guangdong 510641 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijuan","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering South China University of Technology  Guangzhou Guangdong 510641 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanjia","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Sun Yat\u2010sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy  Guangzhou Guangdong 510060 China"},{"name":"Department of Radiation Oncology Southern Theater Air Force Hospital of the People's Liberation Army  Guangzhou Guangdong 510050 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengxue","family":"He","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Sun Yat\u2010sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy  Guangzhou Guangdong 510060 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyun","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Sun Yat\u2010sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy  Guangzhou Guangdong 510060 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Sun Yat\u2010sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy  Guangzhou Guangdong 510060 China"},{"name":"School of Electronic and Information Engineering South China University of Technology  Guangzhou Guangdong 510641 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Sun Yat\u2010sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy  Guangzhou Guangdong 510060 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Sun Yat\u2010sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy  Guangzhou Guangdong 510060 China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,10,29]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26271"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(96)00048-3"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.218.2.r01fe44586"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2005.04.007"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1361-8415(01)80026-8"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2011.07.015"},{"key":"e_1_2_9_8_1","doi-asserted-by":"crossref","unstructured":"LongJ ShelhamerE DarrellT.Fully convolutional networks for semantic segmentation.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015;3431\u20103440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_9_9_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: convolutional networks for biomedical image segmentation.International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Cham:Springer;2015:234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2018.2865450"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837502"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2894322"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13221"},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","unstructured":"MyronenkoA.3D MRI brain tumor segmentation using autoencoder regularization.International MICCAI Brainlesion Workshop.Cham:Springer;2018:311\u2010320.","DOI":"10.1007\/978-3-030-11726-9_28"},{"key":"e_1_2_9_15_1","unstructured":"BakasS ReyesM JakabAet al.Identifying the best machine learning algorithms for brain tumor segmentation progression assessment and overall survival prediction in the BRATS challenge.2018. arXiv preprint arXiv:1811.02629v3"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2014.12.061"},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","unstructured":"NieD WangL GaoY et\u00a0al.Fully convolutional networks for multi\u2010modality isointense infant brain image segmentation.2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).IEEE;2016:1342\u20101345.","DOI":"10.1109\/ISBI.2016.7493515"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.04.034"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2878669"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"HuangG LiuZ Van Der MaatenL et\u00a0al.Densely connected convolutional networks.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:4700\u20104708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2937271"},{"key":"e_1_2_9_22_1","doi-asserted-by":"crossref","unstructured":"LiC SunH LiuZ et\u00a0al.Learning cross\u2010modal deep representations for multi\u2010modal MR image segmentation.International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Cham:Springer;2019:57\u201065.","DOI":"10.1007\/978-3-030-32245-8_7"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_2_9_24_1","unstructured":"MisraD.Mish: a self regularized non\u2010monotonic neural activation function.2019. arXiv preprint arXiv:1908.08681v3"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"HazirbasC MaL DomokosC et\u00a0al.FuseNet: incorporating depth into semantic segmentation via fusion\u2010based CNN architecture.Asian Conference on Computer Vision.Cham:Springer;2016:213\u2010228.","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"e_1_2_9_26_1","unstructured":"OktayO SchlemperJ FolgocLL et al.Attention U\u2010Net: learning where to look for the pancreas.2018. arXiv preprint arXiv:1804.03999v3."},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"JadonS.A survey of loss functions for semantic segmentation 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) 2020 pp.1\u20107 https:\/\/doi.org\/10.1109\/CIBCB48159.2020.9277638.https:\/\/ieeexplore.ieee.org\/abstract\/document\/9277638.","DOI":"10.1109\/CIBCB48159.2020.9277638"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"LinTY GoyalP GirshickR et\u00a0al.Focal loss for dense object detection.Proceedings of the IEEE International Conference on Computer Vision.2017:2980\u20102988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_9_29_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiSA.V\u2010Net: fully convolutional neural networks for volumetric medical image segmentation.2016 4th International Conference on 3D Vision (3DV).IEEE;2016:565\u2010571.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_9_30_1","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"Sudre CH"},{"key":"e_1_2_9_31_1","doi-asserted-by":"crossref","unstructured":"TianZ ShuM LyuP et\u00a0al.Learning shape\u2010aware embedding for scene text detection.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:4234\u20104243.","DOI":"10.1109\/CVPR.2019.00436"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2930068"},{"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":"10.1007\/978-1-4614-7657-3_19"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.2196\/27122"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101693"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15285","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15285","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T20:27:03Z","timestamp":1692822423000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15285"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,29]]},"references-count":35,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["10.1002\/mp.15285"],"URL":"https:\/\/doi.org\/10.1002\/mp.15285","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,29]]},"assertion":[{"value":"2021-03-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-14","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}