{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T14:47:16Z","timestamp":1786978036296,"version":"build-2736575974"},"reference-count":23,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T00:00:00Z","timestamp":1684800000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100010101","name":"Taichung Veterans General Hospital","doi-asserted-by":"publisher","award":["TCVGH\u2010YMCT1109111"],"award-info":[{"award-number":["TCVGH\u2010YMCT1109111"]}],"id":[{"id":"10.13039\/501100010101","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"published-print":{"date-parts":[[2024,2]]},"abstract":"\n Background<\/jats:title>\n The delineation of brain arteriovenous malformations (bAVMs) is crucial for subsequent treatment planning. Manual segmentation is time\u2010consuming and labor\u2010intensive. Applying deep learning to automatically detect and segment bAVM might help to improve clinical practice efficiency.<\/jats:p>\n <\/jats:sec>\n \n Purpose<\/jats:title>\n To develop an approach for detecting bAVM and segmenting its nidus on Time\u2010of\u2010flight magnetic resonance angiography using deep learning methods.<\/jats:p>\n <\/jats:sec>\n \n Study Type<\/jats:title>\n Retrospective.<\/jats:p>\n <\/jats:sec>\n \n Subjects<\/jats:title>\n 221 bAVM patients aged 7\u201379 underwent radiosurgery from 2003 to 2020. They were split into 177 training, 22 validation, and 22 test data.<\/jats:p>\n <\/jats:sec>\n \n Field Strength\/Sequence<\/jats:title>\n \n 1.5\u2009T<\/jats:styled-content>\n , Time\u2010of\u2010flight magnetic resonance angiography based on\n 3D<\/jats:styled-content>\n gradient echo.\n <\/jats:p>\n <\/jats:sec>\n \n Assessment<\/jats:title>\n The YOLOv5 and YOLOv8 algorithms were utilized to detect bAVM lesions and the U\u2010Net and U\u2010Net++ models to segment the nidus from the bounding boxes. The mean average precision, F1, precision, and recall were used to assess the model performance on the bAVM detection. To evaluate the model's performance on nidus segmentation, the Dice coefficient and balanced average Hausdorff distance (rbAHD) were employed.<\/jats:p>\n <\/jats:sec>\n \n Statistical Tests<\/jats:title>\n \n The Student's\n t<\/jats:italic>\n \u2010test was used to test the cross\u2010validation results (\n P<\/jats:italic>\n \u2009<\u20090.05). The Wilcoxon rank test was applied to compare the median for the reference values and the model inference results (\n P<\/jats:italic>\n \u2009<\u20090.05).\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The detection results demonstrated that the model with pretraining and augmentation performed optimally. The U\u2010Net++ with random dilation mechanism resulted in higher Dice and lower rbAHD, compared to that without that mechanism, across varying dilated bounding box conditions (\n P<\/jats:italic>\n \u2009<\u20090.05). When combining detection and segmentation, the Dice and rbAHD were statistically different from the references calculated using the detected bounding boxes (\n P<\/jats:italic>\n \u2009<\u20090.05). For the detected lesions in the test dataset, it showed the highest Dice of 0.82 and the lowest rbAHD of 5.3%.\n <\/jats:p>\n <\/jats:sec>\n \n Data Conclusion<\/jats:title>\n This study showed that pretraining and data augmentation improved YOLO detection performance. Properly limiting lesion ranges allows for adequate bAVM segmentation.<\/jats:p>\n <\/jats:sec>\n \n Level of Evidence<\/jats:title>\n 4<\/jats:p>\n <\/jats:sec>\n \n Technical Efficacy Stage<\/jats:title>\n 1<\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/jmri.28795","type":"journal-article","created":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T14:02:28Z","timestamp":1684850548000},"page":"587-598","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Deep Learning Detection and Segmentation of Brain Arteriovenous Malformation on Magnetic Resonance Angiography"],"prefix":"10.1002","volume":"59","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8066-8841","authenticated-orcid":false,"given":"Jia\u2010Sheng","family":"Hong","sequence":"first","affiliation":[{"name":"Institute of Biophotonics National Yang Ming Chiao Tung University Taipei City 112 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weir\u2010Chiang","family":"You","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Taichung Veterans General Hospital Taichung 407 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming\u2010Hsi","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery Taichung Veterans General Hospital Taichung 407 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung\u2010Chuan","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery Taichung Veterans General Hospital Taichung 407 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi\u2010Hui","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Taichung Veterans General Hospital Taichung 407 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yung\u2010Fa","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Taichung Veterans General Hospital Taichung 407 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuan\u2010Ming","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Biomedical Imaging and Radiological Sciences National Yang Ming Chiao Tung University Taipei City 112 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tzu\u2010Hsuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Biophotonics National Yang Ming Chiao Tung University Taipei City 112 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei\u2010Kai","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute of Biophotonics National Yang Ming Chiao Tung University Taipei City 112 Taiwan"},{"name":"Department of Biomedical Imaging and Radiological Sciences National Yang Ming Chiao Tung University Taipei City 112 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6942-0340","authenticated-orcid":false,"given":"Yu\u2010Te","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Biophotonics National Yang Ming Chiao Tung University Taipei City 112 Taiwan"},{"name":"Brain Research Center National Yang Ming Chiao Tung University Taipei City 112 Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,5,23]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1148\/rg.302095728"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12975-014-0351-0"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.23736\/S0390-5616.18.04452-1"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/cns.13200"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jstrokecerebrovasdis.2020.104863"},{"key":"e_1_2_7_7_1","volume-title":"U\u2010net: Convolutional networks for biomedical image segmentation","author":"Ronneberger O","year":"2015"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12975-021-00933-1"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11199180"},{"key":"e_1_2_7_10_1","first-page":"565","volume-title":"V\u2010net: Fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari F","year":"2016"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13560"},{"key":"e_1_2_7_12_1","first-page":"779","volume-title":"You only look once: Unified, real\u2010time object detection","author":"Redmon J","year":"2016"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4679653"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.00501"},{"key":"e_1_2_7_15_1","first-page":"3","article-title":"UNet++: A nested U\u2010net architecture for medical image segmentation","author":"Zhou Z","year":"2018","journal-title":"Deep Learn in Medical Image Analysis and Multimodal Learning for\u00a0Clinical\u00a0Decision Support. Cham: Springer International Publishing;"},{"key":"e_1_2_7_16_1","first-page":"626","article-title":"Detection of vestibular schwannoma on triple\u2010parametric magnetic resonance images using convolutional neural networks","volume":"41","author":"Huang T\u2010H","year":"2021","journal-title":"J Med Biol Eng"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2022.03.025"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"e_1_2_7_19_1","first-page":"202","article-title":"Comparison of jaccard, dice, cosine similarity coefficient to find best fitness value for web retrieved documents using genetic algorithm","volume":"2","author":"Thada V","year":"2013","journal-title":"Int J Innov Eng Technol"},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-020-00200-2"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/technologies11020040"},{"key":"e_1_2_7_22_1","volume-title":"Big Transfer (BiT): General Visual Representation Learning","author":"Kolesnikov A","year":"2020"},{"key":"e_1_2_7_23_1","first-page":"4918","volume-title":"Rethinking imagenet pre\u2010training","author":"He K","year":"2019"},{"key":"e_1_2_7_24_1","doi-asserted-by":"publisher","DOI":"10.37193\/CMI.2013.02.13"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.28795","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,21]],"date-time":"2024-01-21T08:57:40Z","timestamp":1705827460000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.28795"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,23]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["10.1002\/jmri.28795"],"URL":"https:\/\/doi.org\/10.1002\/jmri.28795","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,23]]},"assertion":[{"value":"2022-10-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-08","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}