{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T17:22:31Z","timestamp":1787764951422,"version":"build-2784847793"},"reference-count":28,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Clinical decisions for stroke treatments, such as thrombolytic drugs for ischemic strokes or anticoagulants for hemorrhagic strokes, rely on accurate diagnosis and severity assessment. Our study uses diffusion-weighted magnetic resonance imaging and Convolutional Neural Networks (CNNs) to differentiate healthy and stroke samples, classify stroke types, and predict severity, aiding in decision-making for stroke management.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>We evaluated 143 patients: 85 with ischemic stroke and 58 with hemorrhagic stroke. For stroke diagnosis, we compared multimodal (apparent diffusion coefficient and diffusion-weighted imaging [DWI]) and single-modal (using separate images) preprocessing techniques. Our study introduced two models, Added CNN Layer-ResNet-50 (ACL-ResNet-50) and Added CNN Layer-MobileNetV1 (ACL-MobileNetV1), based on transfer learning (MobileNetV1 and ResNet-50), enhancing performance through reinforced layers. We compared our proposed models with a scenario in which only the final layer was replaced in ResNet-50 and MobileNetV1. Furthermore, we predicted National Institutes of Health Stroke Scale (NIHSS) scores in three ranges based on DWI images to gauge stroke severity. Evaluation criteria for the models included accuracy, sensitivity, specificity, and area under the curve (AUC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>In stroke classification (normal, ischemic, and hemorrhagic), ACL-MobileNetV1 outperformed other models, achieving 98% accuracy, 99% sensitivity, 98% specificity, and 99% AUC. For assessing ischemic stroke severity using NIHSS ranges, ACL-ResNet-50 showed the optimal performance with an accuracy of 0.92, sensitivity of 0.84, specificity of 0.92, and AUC of 0.95.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>Our study\u2019s proposed method effectively classified stroke type and severity based on multimodal MR images, potentially as a practical decision support tool for stroke treatments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.4103\/jmss.jmss_37_24","type":"journal-article","created":{"date-parts":[[2025,4,19]],"date-time":"2025-04-19T16:00:07Z","timestamp":1745078407000},"update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":3,"title":["Multi-classification Deep Learning Approach for Diagnosing Stroke Type and Severity Using Multimodal Magnetic Resonance Images"],"prefix":"10.4103","volume":"15","author":[{"given":"Sahar","family":"Felehgari","sequence":"first","affiliation":[{"name":"Neuroscience Research Center, Health Policy and Promotion Institute, Kermanshah University of Medical Sciences, Kermanshah, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Payam","family":"Sariaslani","sequence":"additional","affiliation":[{"name":"Neuroscience Research Center, Health Policy and Promotion Institute, Kermanshah University of Medical Sciences, Kermanshah, Iran"},{"name":"Clinical Research Development Center, Imam Reza Hospital, Kermanshah University of Medical Sciences, Kermanshah, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sepideh","family":"Shamsizadeh","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Faculty of Computer Engineering, University of Padova, Padova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saba","family":"Felehgari","sequence":"additional","affiliation":[{"name":"Student Research Committee, Kermanshah University of Medical Sciences, Kermanshah, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anahita","family":"Rajabi","sequence":"additional","affiliation":[{"name":"Student Research Committee, Kermanshah University of Medical Sciences, Kermanshah, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiwa","family":"Mohammadi","sequence":"additional","affiliation":[{"name":"Neuroscience Research Center, Health Policy and Promotion Institute, Kermanshah University of Medical Sciences, Kermanshah, Iran"},{"name":"Clinical Research Development Center, Imam Reza Hospital, Kermanshah University of Medical Sciences, Kermanshah, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2025,4]]},"reference":[{"key":"R3-20250419","doi-asserted-by":"crossref","first-page":"103978","DOI":"10.1016\/j.bspc.2022.103978","article-title":"Automatic segmentation of the brain stroke lesions from MR FLAIR scans using improved U-net framework","volume":"78","author":"Khezrpour","year":"2022","journal-title":"Biomed Signal Process Control"},{"key":"R4-20250419","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.3390\/biomedicines11041138","article-title":"Artificial intelligence in acute ischemic stroke subtypes according to toast classification: A comprehensive narrative review","volume":"11","author":"Miceli","year":"2023","journal-title":"Biomedicines"},{"key":"R5-20250419","first-page":"268","article-title":"Update on treatment of acute ischemic stroke","volume":"26","author":"Rabinstein","year":"2020","journal-title":"Continuum (Minneap Minn)"},{"key":"R6-20250419","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1161\/01.STR.0000196957.55928.ab","article-title":"Time is brain-quantified","volume":"37","author":"Saver","year":"2005","journal-title":"Stroke"},{"key":"R7-20250419","doi-asserted-by":"crossref","first-page":"103948","DOI":"10.1016\/j.bspc.2022.103948","article-title":"Deep feature extraction based brain image classification model using preprocessed images: PDRNet","volume":"78","author":"Tasci","year":"2022","journal-title":"Biomed Signal Process Control"},{"key":"R8-20250419","doi-asserted-by":"crossref","first-page":"105728","DOI":"10.1016\/j.cmpb.2020.105728","article-title":"Neuroimaging and deep learning for brain stroke detection \u2013A review of recent advancements and future prospects","volume":"197","author":"Karthik","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"R9-20250419","doi-asserted-by":"crossref","first-page":"2736","DOI":"10.1080\/21681163.2023.2264410","article-title":"An artificial intelligence approach for segmenting and classifying brain lesions caused by stroke","volume":"11","author":"Menaa","year":"2023","journal-title":"Comput Methods in Biomech Biomed Eng Imaging Vis"},{"key":"R10-20250419","doi-asserted-by":"crossref","first-page":"1444","DOI":"10.1161\/STROKEAHA.118.024261","article-title":"Evaluation of diffusion lesion volume measurements in acute ischemic stroke using encoder-decoder convolutional network","volume":"50","author":"Kim","year":"2019","journal-title":"Stroke"},{"key":"R11-20250419","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1053\/j.sult.2022.02.004","article-title":"Application of deep learning to ischemic and hemorrhagic stroke computed tomography and magnetic resonance imaging","volume":"43","author":"Zhu","year":"2022","journal-title":"Semin Ultrasound CT MR"},{"key":"R12-20250419","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.1161\/01.STR.30.11.2347","article-title":"Underlying structure of the National Institutes of Health Stroke Scale: Results of a factor analysis. NINDS tPA stroke trial investigators","volume":"30","author":"Lyden","year":"1999","journal-title":"Stroke"},{"key":"R13-20250419","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1161\/01.STR.20.7.864","article-title":"Measurements of acute cerebral infarction: A clinical examination scale","volume":"20","author":"Brott","year":"1989","journal-title":"Stroke"},{"key":"R14-20250419","doi-asserted-by":"crossref","first-page":"4008","DOI":"10.3390\/jcm11144008","article-title":"Predicting the severity of neurological impairment caused by Ischemic stroke using deep learning based on diffusion-weighted images","volume":"11","author":"Zeng","year":"2022","journal-title":"J Clin Med"},{"key":"R15-20250419","doi-asserted-by":"crossref","first-page":"723637","DOI":"10.3389\/fneur.2021.723637","article-title":"Treatment challenges in acute minor ischemic stroke","volume":"12","author":"Slawski","year":"2021","journal-title":"Front Neurol"},{"key":"R16-20250419","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1001\/jama.2018.8496","article-title":"Effect of alteplase versus aspirin on functional outcome for patients with acute ischemic stroke and minor nondisabling neurologic deficits: The PRISMS randomized clinical trial","volume":"320","author":"Khatri","year":"2018","journal-title":"JAMA"},{"key":"R17-20250419","first-page":"23","article-title":"Current advances in emergency department care of acute ischemic stroke: Part 2: Endovascular therapy","volume":"21","author":"Nouri","year":"2019","journal-title":"Emerg Med Pract"},{"issue":"Suppl 3","key":"R18-20250419","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1159\/000047578","article-title":"Acute treatment of ischemic stroke. European Stroke Initiative (EUSI)","volume":"10","author":"Hacke","year":"2000","journal-title":"Cerebrovasc Dis"},{"key":"R19-20250419","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1016\/j.mayocp.2018.02.013","article-title":"Diagnosis and management of acute ischemic stroke","volume":"93","author":"Hasan","year":"2018","journal-title":"Mayo Clin Proc"},{"key":"R20-20250419","doi-asserted-by":"crossref","first-page":"3565","DOI":"10.1161\/STROKEAHA.113.003047","article-title":"Can DWI-ASPECTS substitute for lesion volume in acute stroke?","volume":"44","author":"de Margerie-Mellon","year":"2013","journal-title":"Stroke"},{"key":"R21-20250419","doi-asserted-by":"crossref","first-page":"6881","DOI":"10.1158\/0008-5472.CAN-18-0696","article-title":"3D deep learning from CT scans predicts tumor invasiveness of subcentimeter pulmonary adenocarcinomas","volume":"78","author":"Zhao","year":"2018","journal-title":"Cancer Res"},{"key":"R22-20250419","doi-asserted-by":"crossref","first-page":"37","DOI":"10.3390\/jimaging9020037","article-title":"Deep learning applied to intracranial hemorrhage detection","volume":"9","author":"Cort\u00e9s-Ferre","year":"2023","journal-title":"J Imaging"},{"key":"R23-20250419","doi-asserted-by":"crossref","first-page":"191","DOI":"10.17762\/ijritcc.v11i3.6335","article-title":"Enhanced deep learning models for efficient stroke detection using MRI brain imagery","volume":"11","author":"Patil","year":"2023","journal-title":"Int J Recent Innov Trends Comput Commun"},{"key":"R24-20250419","doi-asserted-by":"crossref","first-page":"104603","DOI":"10.1016\/j.bspc.2023.104603","article-title":"Automated ischemic acute infarction detection using pre-trained CNN models'deep features","volume":"82","author":"Tasci","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"R25-20250419","article-title":"A novel autoencoders-LSTM model for stroke outcome prediction using multimodal MRI Data","author":"Hatami","year":"2303","journal-title":"arXiv 2023"},{"key":"R26-20250419","doi-asserted-by":"crossref","first-page":"2841","DOI":"10.1007\/s11517-022-02636-7","article-title":"Using convolutional neural network to analyze brain MRI images for predicting functional outcomes of stroke","volume":"60","author":"Lai","year":"2022","journal-title":"Med Biol Eng Comput"},{"key":"R27-20250419","doi-asserted-by":"crossref","first-page":"3430","DOI":"10.1109\/EMBC48229.2022.9871735","article-title":"CNN-LSTM based multimodal MRI and clinical data fusion for predicting functional outcome in stroke patients","author":"Hatami","year":"2022","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc 2022"},{"key":"R28-20250419","doi-asserted-by":"crossref","first-page":"5395","DOI":"10.1007\/s12652-020-01789-3","article-title":"Diagnosis of cerebral microbleed via VGG and extreme learning machine trained by Gaussian map bat algorithm","volume":"14","author":"Lu","year":"2023","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"R29-20250419","doi-asserted-by":"crossref","first-page":"6323","DOI":"10.3233\/JIFS-230024","article-title":"Classification of ischemic and hemorrhagic stroke using Enhanced-CNN deep learning technique","volume":"45","author":"Shakunthala","year":"2023","journal-title":"J Intell Fuzzy Syst"},{"key":"R30-20250419","doi-asserted-by":"crossref","first-page":"120473","DOI":"10.1016\/j.eswa.2023.120473","article-title":"Collaborative multi-modal deep learning and radiomic features for classification of strokes within 6 h","volume":"228","author":"Yoon","year":"2023","journal-title":"Expert Syst Appl"}],"container-title":["Journal of Medical Signals &amp; Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.4103\/jmss.jmss_37_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T16:53:06Z","timestamp":1787763186000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.4103\/jmss.jmss_37_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":28,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.4103\/jmss.jmss_37_24","relation":{},"ISSN":["2228-7477"],"issn-type":[{"value":"2228-7477","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]},"assertion":[{"value":"2024-05-24","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-28","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}