{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T14:18:02Z","timestamp":1781878682953,"version":"3.54.5"},"reference-count":34,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T00:00:00Z","timestamp":1704931200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100018625","name":"Science and Technology Innovation Plan Of Shanghai Science and Technology Commission","doi-asserted-by":"publisher","award":["18411967300"],"award-info":[{"award-number":["18411967300"]}],"id":[{"id":"10.13039\/501100018625","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":[[2024,10]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Hemangioblastoma (HB) is a highly vascularized tumor most commonly occurring in the posterior cranial fossa, requiring accurate preoperative diagnosis to avoid accidental intraoperative hemorrhage and even death.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To accurately distinguish HBs from other cerebellar\u2010and\u2010brainstem tumors using a convolutional neural network model based on a contrast\u2010enhanced brain MRI dataset.<\/jats:p><\/jats:sec><jats:sec><jats:title>Study Type<\/jats:title><jats:p>Retrospective.<\/jats:p><\/jats:sec><jats:sec><jats:title>Population<\/jats:title><jats:p>Four hundred five patients (182\u2009=\u2009HBs; 223\u2009=\u2009other cerebellar\u2010and brainstem tumors): 305 cases for model training, and 100 for evaluation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Field Strength\/Sequence<\/jats:title><jats:p>3\u2009T\/contrast\u2010enhanced T1\u2010weighted imaging (T1WI\u2009+\u2009C).<\/jats:p><\/jats:sec><jats:sec><jats:title>Assessment<\/jats:title><jats:p>A CNN\u2010based 2D classification network was trained by using sliced data along the z\u2010axis. To improve the performance of the network, we introduced demographic information, various data\u2010augmentation methods and an auxiliary task to segment tumor region. Then, this method was compared with the evaluations performed by experienced and intermediate\u2010level neuroradiologists, and the heatmap of deep feature, which indicates the contribution of each pixel to model prediction, was visualized by Grad\u2010CAM for analyzing the misclassified cases.<\/jats:p><\/jats:sec><jats:sec><jats:title>Statistical Tests<\/jats:title><jats:p>The Pearson chi\u2010square test and an independent <jats:italic>t<\/jats:italic>\u2010test were used to test for distribution difference in age and sex. And the independent <jats:italic>t<\/jats:italic>\u2010test was exploited to evaluate the performance between experts and our proposed method. <jats:italic>P<\/jats:italic> value &lt;0.05 was considered significant.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The trained network showed a higher accuracy for identifying HBs (accuracy\u2009=\u20090.902\u2009\u00b1\u20090.031, F1\u2009=\u20090.891\u2009\u00b1\u20090.035, AUC\u2009=\u20090.926\u2009\u00b1\u20090.040) than experienced (accuracy\u2009=\u20090.887\u2009\u00b1\u20090.013, F1\u2009=\u20090.868\u2009\u00b1\u20090.011, AUC\u2009=\u20090.881\u2009\u00b1\u20090.008) and intermediate\u2010level (accuracy\u2009=\u20090.827\u2009\u00b1\u20090.037, F1\u2009=\u20090.768\u2009\u00b1\u20090.068, AUC\u2009=\u20090.810\u2009\u00b1\u20090.047) neuroradiologists. The recall values were 0.910\u2009\u00b1\u20090.050, 0.659\u2009\u00b1\u20090.084, and 0.828\u2009\u00b1\u20090.019 for the trained network, intermediate and experienced neuroradiologists, respectively. Additional ablation experiments verified the utility of the introduced demographic information, data augmentation, and the auxiliary\u2010segmentation task.<\/jats:p><\/jats:sec><jats:sec><jats:title>Data Conclusion<\/jats:title><jats:p>Our proposed method can successfully distinguish HBs from other cerebellar\u2010and\u2010brainstem tumors and showed diagnostic efficiency comparable to that of experienced neuroradiologists.<\/jats:p><\/jats:sec><jats:sec><jats:title>Evidence Level<\/jats:title><jats:p>3<\/jats:p><\/jats:sec><jats:sec><jats:title>Technical Efficacy<\/jats:title><jats:p>Stage 2<\/jats:p><\/jats:sec>","DOI":"10.1002\/jmri.29230","type":"journal-article","created":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T17:49:25Z","timestamp":1704995365000},"page":"1512-1520","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Convolutional Neural Network Model for Distinguishing Hemangioblastomas From Other Cerebellar\u2010and\u2010Brainstem Tumors Using Contrast\u2010Enhanced <scp>MRI<\/scp>"],"prefix":"10.1002","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7629-9278","authenticated-orcid":false,"given":"Yaru","family":"Sheng","sequence":"first","affiliation":[{"name":"Radiology Department of Huashan Hospital Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Botao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Research Center for Augmented Intelligence, Zhejiang Lab  Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haixia","family":"Cheng","sequence":"additional","affiliation":[{"name":"Neuropathology Department of Huashan Hospital Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yu","sequence":"additional","affiliation":[{"name":"Radiology Department of Huashan Hospital Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8168-7788","authenticated-orcid":false,"given":"Weiwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Radiology Department of Huashan Hospital Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Radiology Department of Huashan Hospital Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueyue","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Ultrasonography Jing'an District Centre Hospital of Shanghai  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longhua","family":"Qiu","sequence":"additional","affiliation":[{"name":"Radiology Department of Huashan Hospital Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Qin","sequence":"additional","affiliation":[{"name":"Neurosurgery Department of Huashan Hospital Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5681-4308","authenticated-orcid":false,"given":"Zhenwei","family":"Yao","sequence":"additional","affiliation":[{"name":"Radiology Department of Huashan Hospital Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8965-1077","authenticated-orcid":false,"given":"Xiaoyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology for Brain\u2010Inspired Intelligence Fudan University  Shanghai China"},{"name":"MOE Key Laboratory of Computational Neuroscience and Brain\u2010Inspired Intelligence Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5993-9248","authenticated-orcid":false,"given":"Yan","family":"Ren","sequence":"additional","affiliation":[{"name":"Radiology Department of Huashan Hospital Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,1,11]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1097\/00006123-200101000-00009"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/nox034"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1227\/01.NEU.0000163250.71951.18"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.wneu.2017.11.173"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/ons\/opw045"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.194.3.7862955"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/not201"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1227\/01.NEU.0000313120.81565.D7"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-018-5879-z"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.20707"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/path.1943"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13764"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00305-2"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31037-5"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13825-8"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(19)30123-2"},{"key":"e_1_2_8_18_1","unstructured":"DosovitskiyA BeyerL KolesnikovA et al.An image is worth 16x16 words: Transformers for image recognition at scale.2021. ArXiv:2010.11929."},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"JangJ HwangD.M3T: Three\u2010dimensional medical image classifier using multi\u2010plane and multi\u2010slice transformer. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2022:20686\u201320697.","DOI":"10.1109\/CVPR52688.2022.02006"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3140236"},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","unstructured":"GeC QuQ GuIY\u2010H JakolaAS.3D multi\u2010scale convolutional networks for glioma grading using MR images. 2018 25th IEEE International Conference on Image Processing (ICIP)2018:141\u2013145.","DOI":"10.1109\/ICIP.2018.8451682"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2006.01.015"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2046908"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.021"},{"key":"e_1_2_8_25_1","unstructured":"ZhangH CisseM DauphinYN Lopez\u2010PazD.mixup: Beyond empirical risk minimization ICLR 2018 international conference on learning representations;2018."},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"e_1_2_8_27_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. 2016 IEEE conference on computer vision and pattern recognition (CVPR).2016:770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.25534"},{"issue":"5","key":"e_1_2_8_29_1","doi-asserted-by":"crossref","first-page":"v1","DOI":"10.1093\/neuonc\/noac202","article-title":"CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the United States in 2015\u20102019","volume":"24","author":"Ostrom QT","year":"2022","journal-title":"Neuro Oncol"},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","unstructured":"SelvarajuRR CogswellM DasA VedantamR ParikhD BatraD.Grad\u2010CAM: Visual explanations from deep networks via gradient\u2010based localization. 2017 IEEE International Conference on Computer Vision (ICCV).2017:618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102382"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013714"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(15)00303-8"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/noaa295"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.29230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T12:28:48Z","timestamp":1731587328000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.29230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,11]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["10.1002\/jmri.29230"],"URL":"https:\/\/doi.org\/10.1002\/jmri.29230","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,11]]},"assertion":[{"value":"2023-08-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}