{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T17:51:23Z","timestamp":1787507483757,"version":"build-2736575974"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005088","name":"Beijing Municipal Health Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005088","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.fr","clinicalkey.jp","clinicalkey.es","clinicalkey.com.au","clinicalkey.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computerized Medical Imaging and Graphics"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1016\/j.compmedimag.2024.102368","type":"journal-article","created":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T12:40:13Z","timestamp":1710852013000},"page":"102368","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":11,"special_numbering":"C","title":["Multi modality fusion transformer with spatio-temporal feature aggregation module for psychiatric disorder diagnosis"],"prefix":"10.1016","volume":"114","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6193-0864","authenticated-orcid":false,"given":"Guoxin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengmei","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuyang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenshu","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaole","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuping","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunlong","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiren","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.compmedimag.2024.102368_b1","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1148\/radiol.2019182622","article-title":"Predicting breast cancer by applying deep learning to linked health records and mammograms","volume":"292","author":"Akselrod-Ballin","year":"2019","journal-title":"Radiology"},{"key":"10.1016\/j.compmedimag.2024.102368_b2","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1016\/S0140-6736(15)60692-4","article-title":"Global, regional, and national incidence, prevalence, and years lived with disability for 301 acute and chronic diseases and injuries in 188 countries, 1990\u20132013: A systematic analysis for the global burden of disease study 2013","volume":"386","author":"Anon","year":"2015","journal-title":"Lancet"},{"key":"10.1016\/j.compmedimag.2024.102368_b3","series-title":"Impact of fully connected layers on performance of convolutional neural networks for image classification","author":"Basha","year":"2019"},{"key":"10.1016\/j.compmedimag.2024.102368_b4","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","volume":"2022","author":"d\u2019Ascoli","year":"2021","journal-title":"J. Stat. Mech. Theory Exp."},{"key":"10.1016\/j.compmedimag.2024.102368_b5","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0206351","article-title":"Using resting state functional MRI to build a personalized autism diagnosis system","volume":"13","author":"Dekhil","year":"2018","journal-title":"PLoS ONE"},{"key":"10.1016\/j.compmedimag.2024.102368_b6","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.compmedimag.2024.102368_b7","first-page":"362","article-title":"Identifying autism from resting-state fMRI using long short-term memory networks","volume":"vol. 10541","author":"Dvornek","year":"2017"},{"key":"10.1016\/j.compmedimag.2024.102368_b8","series-title":"2018 International Conference on Artificial Intelligence and Data Processing","first-page":"1","article-title":"A model of deep neural network for iris classification with different activation functions","author":"Eldem","year":"2018"},{"key":"10.1016\/j.compmedimag.2024.102368_b9","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s11760-022-02229-9","article-title":"Diagnosis of Schizophrenia using brain resting-state fMRI with activity maps based on deep learning","volume":"17","author":"Ghanbari","year":"2022","journal-title":"Signal Image Vid. Process."},{"issue":"1","key":"10.1016\/j.compmedimag.2024.102368_b10","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1002\/hbm.26129","article-title":"The complexity of spontaneous brain activity changes in Schizophrenia, bipolar disorder, and ADHD was examined using different variations of entropy","volume":"44","author":"Guan","year":"2023","journal-title":"Hum. Brain Mapp."},{"key":"10.1016\/j.compmedimag.2024.102368_b11","series-title":"Transformer in transformer","author":"Han","year":"2021"},{"key":"10.1016\/j.compmedimag.2024.102368_b12","doi-asserted-by":"crossref","unstructured":"Matsubara, T., Tashiro, T., Uehara, K., 2018. Structured Deep Generative Model of fMRI Signals for Mental Disorder Diagnosis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention.","DOI":"10.1007\/978-3-030-00931-1_30"},{"issue":"8","key":"10.1016\/j.compmedimag.2024.102368_b13","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1038\/s41591-020-0931-3","article-title":"Artificial intelligence\u2013enabled rapid diagnosis of patients with COVID-19","volume":"26","author":"Mei","year":"2020","journal-title":"Nat. Med."},{"key":"10.1016\/j.compmedimag.2024.102368_b14","doi-asserted-by":"crossref","unstructured":"Narazani, M., Sarasua, I., P\u00f6lsterl, S., Lizarraga, A., Yakushev, I., Wachinger, C., 2022. Is a PET all you need? A multi-modal study for Alzheimer\u2019s disease using 3D CNNs. In: International Conference on Medical Image Computing and Computer-Assisted Intervention.","DOI":"10.1007\/978-3-031-16431-6_7"},{"key":"10.1016\/j.compmedimag.2024.102368_b15","series-title":"Neural Information Processing Systems","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","author":"Rao","year":"2021"},{"issue":"9","key":"10.1016\/j.compmedimag.2024.102368_b16","doi-asserted-by":"crossref","first-page":"3095","DOI":"10.1093\/cercor\/bhx179","article-title":"Local-global parcellation of the human cerebral cortex from intrinsic functional connectivity MRI","volume":"28","author":"Schaefer","year":"2018","journal-title":"Cereb. Cortex"},{"key":"10.1016\/j.compmedimag.2024.102368_b17","doi-asserted-by":"crossref","DOI":"10.3389\/fninf.2018.00070","article-title":"Unsupervised manifold learning using high-order morphological brain networks derived from T1-w MRI for autism diagnosis","volume":"12","author":"Soussia","year":"2018","journal-title":"Front. Neuroinform."},{"key":"10.1016\/j.compmedimag.2024.102368_b18","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.-Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A., 2021. Bottleneck Transformers for Visual Recognition. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 16514\u201316524.","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"10.1016\/j.compmedimag.2024.102368_b19","doi-asserted-by":"crossref","first-page":"1398","DOI":"10.1056\/NEJMc2026462","article-title":"Bipolar disorder","volume":"383","author":"Strejilevich","year":"2020","journal-title":"N. Engl. J. Med."},{"issue":"C2L-D-6","key":"10.1016\/j.compmedimag.2024.102368_b20","article-title":"Deep neural generative model for fMRI image based diagnosis of mental disorder","volume":"29","author":"Tashiro","year":"2017","journal-title":"IEICE Proceed. Ser."},{"key":"10.1016\/j.compmedimag.2024.102368_b21","doi-asserted-by":"crossref","unstructured":"Tomassini, S., Falcionelli, N., Sernani, P., M\u00fcller, H., Dragoni, A.F., 2021. An End-to-End 3D ConvLSTM-based Framework for Early Diagnosis of Alzheimer\u2019s Disease from Full-Resolution Whole-Brain sMRI Scans. In: 2021 IEEE 34th International Symposium on Computer-Based Medical Systems. CBMS, pp. 74\u201378.","DOI":"10.1109\/CBMS52027.2021.00081"},{"key":"10.1016\/j.compmedimag.2024.102368_b22","series-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020"},{"key":"10.1016\/j.compmedimag.2024.102368_b23","series-title":"NIPS","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.compmedimag.2024.102368_b24","series-title":"Multi-dimension-embedding-aware modality fusion transformer for psychiatric disorder clasification","author":"Wang","year":"2023"},{"key":"10.1016\/j.compmedimag.2024.102368_b25","series-title":"A bi-pyramid multimodal fusion method for the diagnosis of bipolar disorders","author":"Wang","year":"2024"},{"key":"10.1016\/j.compmedimag.2024.102368_b26","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L., 2021. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions. In: 2021 IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 548\u2013558.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"10.1016\/j.compmedimag.2024.102368_b27","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N.C.F., Liu, M., Dai, X., Yuan, L., Zhang, L., 2021. CvT: Introducing Convolutions to Vision Transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 22\u201331.","DOI":"10.1109\/ICCV48922.2021.00009"},{"issue":"1","key":"10.1016\/j.compmedimag.2024.102368_b28","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1148\/radiol.2019182716","article-title":"A deep learning mammography-based model for improved breast cancer risk prediction","volume":"292","author":"Yala","year":"2019","journal-title":"Radiology"},{"key":"10.1016\/j.compmedimag.2024.102368_b29","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1016\/j.ebiom.2019.08.023","article-title":"Discriminating Schizophrenia using recurrent neural network applied on time courses of multi-site FMRI data","volume":"47","author":"Yan","year":"2019","journal-title":"EBioMedicine"},{"issue":"6","key":"10.1016\/j.compmedimag.2024.102368_b30","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/s41551-021-00745-6","article-title":"Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images","volume":"5","author":"Zhang","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.compmedimag.2024.102368_b31","doi-asserted-by":"crossref","first-page":"23626","DOI":"10.1109\/ACCESS.2017.2762703","article-title":"3D CNN based automatic diagnosis of attention deficit hyperactivity disorder using functional and structural MRI","volume":"5","author":"Zou","year":"2017","journal-title":"IEEE Access"}],"container-title":["Computerized Medical Imaging and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611124000454?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611124000454?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,4,6]],"date-time":"2024-04-06T22:48:54Z","timestamp":1712443734000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0895611124000454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":31,"alternative-id":["S0895611124000454"],"URL":"https:\/\/doi.org\/10.1016\/j.compmedimag.2024.102368","relation":{},"ISSN":["0895-6111"],"issn-type":[{"value":"0895-6111","type":"print"}],"subject":[],"published":{"date-parts":[[2024,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi modality fusion transformer with spatio-temporal feature aggregation module for psychiatric disorder diagnosis","name":"articletitle","label":"Article Title"},{"value":"Computerized Medical Imaging and Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compmedimag.2024.102368","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"102368"}}