{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T02:50:13Z","timestamp":1791946213196,"version":"4.3.4"},"reference-count":23,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"5","license":[{"start":{"date-parts":[[2020,11,16]],"date-time":"2020-11-16T00:00:00Z","timestamp":1605484800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:p>Although intracranial hemorrhage in moyamoya disease can occur repeatedly, predicting the disease is difficult. Deep learning algorithms developed in recent years provide a new angle for identifying hidden risk factors, evaluating the weight of different factors, and quantitatively evaluating the risk of intracranial hemorrhage in moyamoya disease. To investigate whether convolutional neural network algorithms can be used to recognize moyamoya disease and predict hemorrhagic episodes, we retrospectively selected 460 adult unilateral hemispheres with moyamoya vasculopathy as positive samples for diagnosis modeling, including 418 hemispheres with moyamoya disease and 42 hemispheres with moyamoya syndromes. Another 500 hemispheres with normal vessel appearance were selected as negative samples. We used deep residual neural network (ResNet-152) algorithms to extract features from raw data obtained from digital subtraction angiography of the internal carotid artery, then trained and validated the model. The accuracy, sensitivity, and specificity of the model in identifying unilateral moyamoya vasculopathy were 97.64 \u00b1 0.87%, 96.55 \u00b1 3.44%, and 98.29 \u00b1 0.98%, respectively. The area under the receiver operating characteristic curve was 0.990. We used a combined multi-view conventional neural network algorithm to integrate age, sex, and hemorrhagic factors with features of the digital subtraction angiography. The accuracy of the model in predicting unilateral hemorrhagic risk was 90.69 \u00b1 1.58% and the sensitivity and specificity were 94.12 \u00b1 2.75% and 89.86 \u00b1 3.64%, respectively. The deep learning algorithms we proposed were valuable and might assist in the automatic diagnosis of moyamoya disease and timely recognition of the risk for re-hemorrhage. This study was approved by the Institutional Review Board of Huashan Hospital, Fudan University, China (approved No. 2014-278) on January 12, 2015.<\/jats:p>","DOI":"10.4103\/1673-5374.297085","type":"journal-article","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T12:02:23Z","timestamp":1605873743000},"page":"830-835","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":21,"title":["Recognition of moyamoya disease and its hemorrhagic risk using deep learning algorithms: sourced from retrospective studies"],"prefix":"10.4103","volume":"16","author":[{"given":"Yu","family":"Lei","sequence":"first","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Ni","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia-Bin","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin-Hua","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4580-2205","authenticated-orcid":false,"given":"Yu-Xiang","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8055-115X","authenticated-orcid":false,"given":"Ying","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2021,5]]},"reference":[{"key":"R1-20260525","doi-asserted-by":"crossref","first-page":"3642","DOI":"10.1109\/CVPR.2012.6248110","article-title":"Multi-column deep neural networks for image classification","author":"Ciregan","year":"2012","journal-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"R2-20260525","first-page":"411","article-title":"Mitosis detection in breast cancer histology images with deep neural networks","volume":"16","author":"Cire\u015fan","year":"2013","journal-title":"Med Image Comput Comput Assist Interv"},{"key":"R4-20260525","doi-asserted-by":"crossref","first-page":"2200110","DOI":"10.1109\/JTEHM.2014.2361757","article-title":"A bayesian algorithm for anxiety index prediction based on cerebral blood oxygenation in the prefrontal cortex measured by near infrared spectroscopy","volume":"2","author":"Fukuda","year":"2014","journal-title":"IEEE J Transl Eng Health Med"},{"key":"R5-20260525","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"Glorot","year":"2010","journal-title":"J Mach Learn Res"},{"key":"R6-20260525","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"2016 IEEE conference on computer vision and pattern recognition (CVPR)"},{"key":"R7-20260525","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1161\/01.STR.27.8.1342","article-title":"Surgical therapy for adult moyamoya disease. Can surgical revascularization prevent the recurrence of intracerebral hemorrhage","volume":"27","author":"Houkin","year":"1996","journal-title":"Stroke"},{"key":"R11-20260525","doi-asserted-by":"crossref","first-page":"1048","DOI":"10.3171\/2014.7.JNS132434","article-title":"Outcome in adult patients with hemorrhagic moyamoya disease after combined extracranial-intracranial bypass","volume":"121","author":"Jiang","year":"2014","journal-title":"J Neurosurg"},{"key":"R12-20260525","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1161\/STROKEAHA.118.022771","article-title":"Natural course of moyamoya disease in patients with prior hemorrhagic stroke","volume":"50","author":"Kang","year":"2019","journal-title":"Stroke"},{"key":"R13-20260525","doi-asserted-by":"crossref","first-page":"1287","DOI":"10.1007\/BF01411057","article-title":"Characteristics of intracranial aneurysms associated with moyamoya disease. A review of 111 cases","volume":"138","author":"Kawaguchi","year":"1996","journal-title":"Acta Neurochir (Wien)"},{"key":"R14-20260525","doi-asserted-by":"crossref","first-page":"976","DOI":"10.3171\/jns.2000.93.6.0976","article-title":"Long-term natural history of hemorrhagic moyamoya disease in 42 patients","volume":"93","author":"Kobayashi","year":"2000","journal-title":"J Neurosurg"},{"key":"R15-20260525","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun ACM"},{"key":"R16-20260525","doi-asserted-by":"crossref","first-page":"1056","DOI":"10.1016\/S1474-4422(08)70240-0","article-title":"Moyamoya disease: current concepts and future perspectives","volume":"7","author":"Kuroda","year":"2008","journal-title":"Lancet Neurol"},{"key":"R17-20260525","doi-asserted-by":"crossref","first-page":"904860","DOI":"10.1155\/2013\/904860","article-title":"Clinical outcome prediction in aneurysmal subarachnoid hemorrhage using Bayesian neural networks with fuzzy logic inferences","volume":"2013","author":"Lo","year":"2013","journal-title":"Comput Math Methods Med"},{"key":"R18-20260525","first-page":"1049","article-title":"High-risk age for rebleeding in patients with hemorrhagic moyamoya disease: long-term follow-up study","volume":"52","author":"Morioka","year":"2003","journal-title":"Neurosurgery"},{"key":"R19-20260525","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1161\/01.STR.0000047120.67507.0D","article-title":"Angiographic dilatation and branch extension of the anterior choroidal and posterior communicating arteries are predictors of hemorrhage in adult moyamoya patients","volume":"34","author":"Morioka","year":"2003","journal-title":"Stroke"},{"key":"R20-20260525","doi-asserted-by":"crossref","first-page":"245","DOI":"10.2176\/nmc.52.245","article-title":"Health Labour Sciences Research Grant for Research on Measures for Infractable Diseases (2012) Guidelines for diagnosis and treatment of moyamoya disease (spontaneous occlusion of the circle of Willis)","volume":"52","journal-title":"Neurol Med Chir (Tokyo)"},{"key":"R21-20260525","doi-asserted-by":"crossref","first-page":"72","DOI":"10.4103\/2152-7806.97730","article-title":"Hemorrhage and risk of further hemorrhagic strokes following cerebral revascularization in Moyamoya disease: A review of the literature","volume":"3","author":"Ryan","year":"2012","journal-title":"Surg Neurol Int"},{"key":"R22-20260525","doi-asserted-by":"crossref","first-page":"S196","DOI":"10.1016\/S0303-8467(97)00079-6","article-title":"Hemorrhagic type moyamoya disease","volume":"2","author":"Saeki","year":"1997","journal-title":"Clin Neurol Neurosurg 99 Suppl"},{"key":"R23-20260525","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1056\/NEJMra0804622","article-title":"Moyamoya disease and moyamoya syndrome","volume":"360","author":"Scott","year":"2009","journal-title":"N Engl J Med"},{"key":"R25-20260525","doi-asserted-by":"crossref","first-page":"858","DOI":"10.4103\/1673-5374.249234","article-title":"Microstructural damage pattern of vascular cognitive impairment: a comparison between moyamoya disease and cerebrovascular atherosclerotic disease","volume":"14","author":"Su","year":"2019","journal-title":"Neural Regen Res"},{"key":"R26-20260525","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1161\/01.STR.14.1.104","article-title":"Moyamoya disease--a review","volume":"14","author":"Suzuki","year":"1983","journal-title":"Stroke"},{"key":"R27-20260525","doi-asserted-by":"crossref","first-page":"2869","DOI":"10.1002\/hbm.22445","article-title":"Support vector machine learning-based cerebral blood flow quantification for arterial spin labeling MRI","volume":"35","author":"Wang","year":"2014","journal-title":"Hum Brain Mapp"},{"key":"R28-20260525","doi-asserted-by":"crossref","first-page":"2272","DOI":"10.1161\/01.STR.30.11.2272","article-title":"Clinical course, surgical management, and long-term outcome of moyamoya patients with rebleeding after an episode of intracerebral hemorrhage: an extensive follow-up study","volume":"30","author":"Yoshida","year":"1999","journal-title":"Stroke"}],"container-title":["Neural Regeneration Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.4103\/1673-5374.297085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T19:30:15Z","timestamp":1786735815000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.4103\/1673-5374.297085"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,16]]},"references-count":23,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.4103\/1673-5374.297085","relation":{},"ISSN":["1673-5374","1876-7958"],"issn-type":[{"value":"1673-5374","type":"print"},{"value":"1876-7958","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,16]]},"assertion":[{"value":"2020-03-26","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-07-22","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}