{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:46:44Z","timestamp":1792082804233,"version":"4.4.0"},"reference-count":40,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2022,2,9]],"date-time":"2022-02-09T00:00:00Z","timestamp":1644364800000},"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":[[2022,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Magnetic resonance (MR) imaging is the gold standard in image\u2010guided brachytherapy (IGBT) due to its superior soft\u2010tissue contrast for target and organs\u2010at\u2010risk (OARs) delineation. Accurate and fast segmentation of MR images are very important for high\u2010quality IGBT treatment planning. The purpose of this work is to implement and evaluate deep learning (DL) models for the automatic segmentation of targets and OARs in MR image\u2010based high\u2010dose\u2010rate (HDR) brachytherapy for cervical cancer.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A 2D DL model using residual neural network architecture (ResNet50) was developed to contour the targets (gross tumor volume (GTV), high\u2010risk clinical target volume (HR CTV), and intermediate\u2010risk clinical target volume (IR CTV)) and OARs (bladder, rectum, sigmoid, and small intestine) automatically on axial MR slices of HDR brachytherapy patients. Furthermore, two additional 2D DL models using sagittal and coronal images were also developed. A 2.5D model was generated by combining the outputs from axial, sagittal, and coronal DL models. Similarly, a 2D and 2.5D DL models were also generated for the inception residual neural network (InceptionResNetv2 (InRN)) architecture. The geometric (Dice similarity coefficient (DSCs) and 95th percentile of Hausdorff distance (HD)) and dosimetric accuracy of 2D (axial only) and 2.5D (axial\u00a0+\u00a0sagittal\u00a0+\u00a0coronal) DL model generated contours were calculated and compared.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The mean (range) DSCs of ResNet50 across all contours were 0.674 (0.05\u20130.96) and 0.715 (0.26\u20130.96) for the 2D and 2.5D models, respectively. For InRN, these were 0.676 (0.11\u20130.96) and 0.723 (0.35\u20130.97) for the 2D and 2.5D models, respectively. The mean HD of ResNet50 across all contours was 15.6\u00a0mm (1.8\u201369\u00a0mm) and 12.1\u00a0mm (1.7\u201344\u00a0mm) for the 2D and 2.5D models, respectively. The similar results for InRN were 15.4\u00a0mm (2\u201368\u00a0mm) and 10.3\u00a0mm (2.7\u201339\u00a0mm) for the 2D and 2.5D models, respectively. The dosimetric parameters (D90) of GTV and HR CTV for manually contoured plans matched better with the 2.5D model (<jats:italic>p<\/jats:italic>\u00a0&gt;\u00a00.6) and the results from the 2D model were slightly lower (<jats:italic>p<\/jats:italic>\u00a0&lt;\u00a00.08). On the other hand, the IR CTV doses (D90) for all of the models were slightly lower (2D: \u20101.3 to \u20101.5\u00a0Gy and 2.5D: \u20100.5 to \u20100.6\u00a0Gy) and the differences were statistically significant for the 2D model (2D: <jats:italic>p<\/jats:italic>\u00a0&lt;\u00a00.000002 and 2.5D: <jats:italic>p<\/jats:italic>\u00a0&gt;\u00a00.06). In case of OARs, the 2.5D model segmentations resulted in closer dosimetry than 2D models (2D: <jats:italic>p<\/jats:italic>\u00a0=\u00a00.07\u20130.91 and 2.5D: <jats:italic>p<\/jats:italic>\u00a0=\u00a00.16\u20131.0).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The 2.5D DL models outperformed their respective 2D models for the automatic contouring of targets and OARs in MR image\u2010based HDR brachytherapy for cervical cancer. The InceptionResNetv2 model performed slightly better than ResNet50.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15506","type":"journal-article","created":{"date-parts":[[2022,1,30]],"date-time":"2022-01-30T10:29:10Z","timestamp":1643538550000},"page":"1571-1584","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":48,"title":["Automatic segmentation of magnetic resonance images for high\u2010dose\u2010rate cervical cancer brachytherapy using deep learning"],"prefix":"10.1002","volume":"49","author":[{"given":"SA","family":"Yoganathan","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology National Center for Cancer Care &amp; Research (NCCCR) Hamad Medical Corporation  Doha Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siji Nojin","family":"Paul","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology National Center for Cancer Care &amp; Research (NCCCR) Hamad Medical Corporation  Doha Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satheesh","family":"Paloor","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology National Center for Cancer Care &amp; Research (NCCCR) Hamad Medical Corporation  Doha Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tarraf","family":"Torfeh","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology National Center for Cancer Care &amp; Research (NCCCR) Hamad Medical Corporation  Doha Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suparna Halsnad","family":"Chandramouli","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology National Center for Cancer Care &amp; Research (NCCCR) Hamad Medical Corporation  Doha Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rabih","family":"Hammoud","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology National Center for Cancer Care &amp; Research (NCCCR) Hamad Medical Corporation  Doha Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noora","family":"Al\u2010Hammadi","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology National Center for Cancer Care &amp; Research (NCCCR) Hamad Medical Corporation  Doha Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,2,9]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2013.11.011"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360-3016(98)00482-9"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2013.05.033"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360-3016(00)00497-1"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2018.11.009"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2006.12.021"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2013.01.012"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2013.02.014"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2012.12.017"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2013.01.014"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4871620"},{"key":"e_1_2_8_13_1","unstructured":"NikolovS BlackwellS MendesR et\u00a0al.Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy. arXiv preprint arXiv:1809.04430.2018."},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.10.019"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2016.00178"},{"key":"e_1_2_8_16_1","first-page":"1","article-title":"Atlas\u2010based auto\u2010segmentation for postoperative radiotherapy planning in endometrial and cervical cancers","volume":"15","author":"Kim N","year":"2020","journal-title":"Radiother Oncol"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13024"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2021.03.030"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.07.681"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966210"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.06.011"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12831"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13264"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1186\/s41824-020-00086-8"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019190385"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13891"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2012.05.001"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2005.11.014"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2004.12.015"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_2_8_33_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; 2016:770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_34_1","doi-asserted-by":"crossref","unstructured":"SzegedyC IoffeS VanhouckeV AlemiAA.Inception\u2010v4 inception\u2010resnet and the impact of residual connections on learning. In: Proceedings of the Thirty\u2010First AAAI Conference on Artificial Intelligence 12 February 2017. AAAI Press; 2017:4278\u20104284.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2013.01.011"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.05.010"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2004.828354"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.06.076"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.10.038"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2019.07.006"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15506","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15506","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T21:01:09Z","timestamp":1692738069000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,9]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["10.1002\/mp.15506"],"URL":"https:\/\/doi.org\/10.1002\/mp.15506","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,9]]},"assertion":[{"value":"2021-08-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-24","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}