{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T17:28:07Z","timestamp":1785432487771,"version":"3.56.0"},"reference-count":43,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000261","name":"MS Canada","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000261","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/04d8ywj90","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/01gavpb45","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Brain Sciences"],"abstract":"<jats:p>Objectives: Secondary progressive multiple sclerosis (SPMS) is a natural transition from relapsing-remitting multiple sclerosis (RRMS) in many cases. However, whether and how these phenotypes differ on an individual basis is not fully understood, limiting timely diagnosis and management for SPMS. This study aimed to investigate how deep learning using 3-dimensional (3D) frameworks including VGG19, ResNet152, and DenseNet-121 helped differentiate SPMS from RRMS based on routine clinical datasets, and what brain areas mostly contributed to this differentiation using model explanation techniques. Methods: We examined 140 participants (70 each for RRMS and SPMS) as part of an ongoing study comprising prospectively collected clinical and imaging data from routine healthcare. The data was curated to improve consistency and completeness using different strategies and were then randomly split by subject into training (n = 120) and held-out testing (n = 20). The former was used for model development through five-fold cross validation. Deep learning used T1-weighted, T2-weighted, and FLAIR brain MRI, with optional clinical variables (n = 6). A 3D gradient-weighted class activation mapping (Grad-CAM) technique was applied to identify brain areas of significance followed by ablation studies for additional insight. Results: Among the 3D frameworks validated, VGG19 was deemed the best. Based on MRI and the best 3D VGG19 model, different data curation strategies showed largely similar results. Additionally, the models combining clinical variables with MRI achieved equivalent or slightly greater performance than MRI-only models, with an average testing area under the receiver operating characteristic curve of 0.84 when datasets were fused at the flatten layer, best at 0.92, versus 0.82 and 0.89. Model explanation indicated brain regions of significance in distinguishing SPMS from RRMS individuals, including bilateral frontal lobes, left occipital and temporal lobes, and cerebellum. Conclusions: Overall findings suggest the potential of 3D deep learning models such as VGG19 for distinguishing SPMS from RRMS using routine brain MRI and clinical data, which, along with 3D Grad-CAM, could facilitate discovery of new biomarkers underlying disease worsening.<\/jats:p>","DOI":"10.3390\/brainsci16070670","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T02:11:57Z","timestamp":1782785517000},"page":"670","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Three-Dimensional Deep Learning with Routine Brain Magnetic Resonance Imaging and Clinical Data for Identification of Secondary Progressive Multiple Sclerosis"],"prefix":"10.3390","volume":"16","author":[{"given":"Mahshid","family":"Soleymani","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, University of Calgary, Calgary, AB T2N 4N1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olayinka","family":"Oladosu","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Calgary, Calgary, AB T2N 4N1, Canada"},{"name":"Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, AB T2N 4N1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2700-0369","authenticated-orcid":false,"given":"Saahim","family":"Salman","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of Calgary, Calgary, AB T2N 4N1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahum","family":"Rashid","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of Calgary, Calgary, AB T2N 4N1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5125-0294","authenticated-orcid":false,"given":"Mariana","family":"Bento","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of Calgary, Calgary, AB T2N 4N1, Canada"},{"name":"Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, AB T2N 4N1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7440-5420","authenticated-orcid":false,"given":"Yunyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Calgary, Calgary, AB T2N 4N1, Canada"},{"name":"Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, AB T2N 4N1, Canada"},{"name":"Department of Clinical Neurosciences, University of Calgary, Calgary, AB T2N 4N1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1111\/ene.13819","article-title":"Multiple sclerosis\u2014A review","volume":"26","author":"Dobson","year":"2019","journal-title":"Eur. J. Neurol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"028928","DOI":"10.1101\/cshperspect.a028928","article-title":"Clinical Course of Multiple Sclerosis","volume":"8","author":"Klineova","year":"2018","journal-title":"Cold Spring Harb. Perspect. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1136\/jnnp-2012-304333","article-title":"Onset of secondary progressive phase and long-term evolution of multiple sclerosis","volume":"85","author":"Scalfari","year":"2014","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1654","DOI":"10.1177\/1352458514521517","article-title":"Diagnostic uncertainty during the transition to secondary progressive multiple sclerosis","volume":"20","author":"Sand","year":"2014","journal-title":"Mult. Scler. J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e200064","DOI":"10.1212\/NXI.0000000000200064","article-title":"Secondary Progressive Multiple Sclerosis: A Review of Clinical Characteristics, Definition, Prognostic Tools, and Disease-Modifying Therapies","volume":"10","author":"Ziemssen","year":"2023","journal-title":"Neurol. Neuroimmunol. Neuroiinflamm."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"University of California, San Francisco MS-EPIC Team, Cree, B., Hollenbach, J.A., Bove, R., Kirkish, G., Sacco, S., Caverzasi, E., Bischof, A., Gundel, T., and Zhu, A.H. (2019). Silent progression in disease activity-free relapsing multiple sclerosis. Ann. Neurol., 85, 653\u2013666.","DOI":"10.1002\/ana.25463"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"109530","DOI":"10.1016\/j.compbiomed.2024.109530","article-title":"Deep Learning techniques to detect and analysis of multiple sclerosis through MRI: A systematic literature review","volume":"185","author":"Belwal","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e70568","DOI":"10.1111\/ene.70568","article-title":"Explainable Artificial Intelligence to Predict Neurocognitive Disorder Progression in Multiple Sclerosis Using MRI and Clinical Data","volume":"33","author":"Storelli","year":"2026","journal-title":"Eur. J. Neurol."},{"key":"ref_9","first-page":"100706","article-title":"A Convolutional Neural Network model for identifying Multiple Sclerosis on brain FLAIR MRI","volume":"35","author":"Acar","year":"2022","journal-title":"Sustain. Comput. Inform. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"0460a6","DOI":"10.1088\/1741-2552\/ac0f4b","article-title":"Interpretable deep learning as a means for decrypting disease signature in multiple sclerosis","volume":"18","author":"Cruciani","year":"2021","journal-title":"J. Neural Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103376","DOI":"10.1016\/j.nicl.2023.103376","article-title":"Deciphering multiple sclerosis disability with deep learning attention maps on clinical MRI","volume":"38","author":"Coll","year":"2023","journal-title":"Neuroimage Clin."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e230514","DOI":"10.1148\/ryai.230514","article-title":"Addressing the Generalizability of AI in Radiology Using a Novel Data Augmentation Framework with Synthetic Patient Image Data: Proof-of-Concept and External Validation for Classification Tasks in Multiple Sclerosis","volume":"6","author":"Brugnara","year":"2024","journal-title":"Radiol. Artif. Intell."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"RSelvaraju, R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"109098","DOI":"10.1016\/j.jneumeth.2021.109098","article-title":"Grad-CAM helps interpret the deep learning models trained to classify multiple sclerosis types using clinical brain magnetic resonance imaging","volume":"353","author":"Zhang","year":"2021","journal-title":"J. Neurosci. Methods"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1007\/s12021-011-9109-y","article-title":"An open source multivariate framework for n-tissue segmentation with evaluation on public data","volume":"9","author":"Avants","year":"2011","journal-title":"Neuroinformatics"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Shahrokhi, S., Oladosu, O., Tariq, R., and Zhang, Y. (2026). CycleGAN models show consistent brain MRI synthesis across datasets supporting downstream tissue characterization in multiple sclerosis. Front. Neuroinform., 20.","DOI":"10.3389\/fninf.2026.1762794"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e70313","DOI":"10.1002\/nbm.70313","article-title":"A Z-Score Template Method for Person-Specific Augmentation of Clinical Brain MRI: An Investigation in Multiple Sclerosis","volume":"39","author":"Oladosu","year":"2026","journal-title":"NMR Biomed."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"102169","DOI":"10.1016\/j.media.2021.102169","article-title":"Learning to synthesise the ageing brain without longitudinal data","volume":"73","author":"Xia","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_19","unstructured":"Simonyan, K., and Zisserman, A. (2021). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., and Satoh, Y. (2018, January 18\u201323). Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Li, F.-F. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez, I.S., Yang, E., Calvachi, P., Amengual-Gual, M., Wu, J.Y., Krueger, D., Northrup, H., Bebin, M.E., Sahin, M., and Yu, K.-H. (2020). Deep learning in rare disease. Detection of tubers in tuberous sclerosis complex. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0232376"},{"key":"ref_24","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA. Available online: http:\/\/arxiv.org\/abs\/1412.6980."},{"key":"ref_25","unstructured":"(2024, May 28). Available online: https:\/\/github.com\/keras-team\/keras-io\/blob\/master\/examples\/vision\/grad_cam.py."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1007\/s00429-009-0203-y","article-title":"Brain volumes and Val66Met polymorphism of the BDNF gene: Local or global effects?","volume":"213","author":"Toro","year":"2009","journal-title":"Brain Struct. Funct."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"102003","DOI":"10.1016\/j.nicl.2019.102003","article-title":"Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagation","volume":"24","author":"Eitel","year":"2019","journal-title":"Neuroimage Clin."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1097\/JTO.0b013e3181ec173d","article-title":"Receiver Operating Characteristic Curve in Diagnostic Test Assessment","volume":"5","author":"Mandrekar","year":"2010","journal-title":"J. Thorac. Oncol."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kaur, A., Alshammari, F.S., Rehman, A.U., and Bharany, S. (2025). Intelligent Alzheimer\u2019s diagnosis and disability assessment: Robust medical imaging analysis using ensemble learning with ResNet-50 and EfficientNet-B3. Front. Med., 12.","DOI":"10.3389\/fmed.2025.1619228"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, P., Ding, Y., Deng, L., Zhang, T., and Liu, Y. (2025). Magnetic resonance imaging-based deep learning for predicting subtypes of glioma. Front. Neurol., 16.","DOI":"10.3389\/fneur.2025.1518815"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1158","DOI":"10.1016\/j.jacr.2019.04.005","article-title":"An Initiative to Reduce Unnecessary Gadolinium-Based Contrast in Multiple Sclerosis Patients","volume":"16","author":"Rudie","year":"2019","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22\u201329). Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1097\/RLI.0000000000000854","article-title":"A Deep Learning Approach to Predicting Disease Progression in Multiple Sclerosis Using Magnetic Resonance Imaging","volume":"57","author":"Storelli","year":"2022","journal-title":"Investig. Radiol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1176\/jnp.14.1.44","article-title":"Frontal cortex atrophy predicts cognitive impairment in multiple sclerosis","volume":"14","author":"Benedict","year":"2002","journal-title":"J. Neuropsychiatry Clin. Neurosci."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1220","DOI":"10.1177\/1352458510376405","article-title":"Basal ganglia and frontal\/parietal cortical atrophy is associated with fatigue in relapsing-remitting multiple sclerosis","volume":"16","author":"Calabrese","year":"2010","journal-title":"Mult. Scler. J."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"103429","DOI":"10.1016\/j.msard.2021.103429","article-title":"Recognizing visual complaints in people with multiple sclerosis: Prevalence, nature and associations with key characteristics of MS","volume":"57","author":"Huizinga","year":"2022","journal-title":"Mult. Scler. Relat. Disord."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wilkins, A. (2017). Cerebellar Dysfunction in Multiple Sclerosis. Front. Neurol., 8.","DOI":"10.3389\/fneur.2017.00312"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Guo, Z., Long, L., Qiu, W., Lu, T., Zhang, L., Shu, Y., Zhang, K., Fang, L., and Chen, S. (2021). The Distributional Characteristics of Multiple Sclerosis Lesions on Quantitative Susceptibility Mapping and Their Correlation With Clinical Severity. Front. Neurol., 12.","DOI":"10.3389\/fneur.2021.647519"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"11625","DOI":"10.1038\/s41598-023-38271-x","article-title":"Differentiation between multiple sclerosis and neuromyelitis optica spectrum disorder using a deep learning model","volume":"13","author":"Seok","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.schres.2019.07.034","article-title":"Classification of schizophrenia and normal controls using 3D convolutional neural network and outcome visualization","volume":"212","author":"Oh","year":"2019","journal-title":"Schizophr. Res."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Binder, A., Montavon, G., Bach, S., Muller, K.-R., and Samek, W. (2016). Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers. arXiv.","DOI":"10.1007\/978-3-319-44781-0_8"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/S0140-6736(07)61194-5","article-title":"Effect of early versus delayed interferon beta-1b treatment on disability after a first clinical event suggestive of multiple sclerosis: A 3-year follow-up analysis of the BENEFIT study","volume":"370","author":"Kappos","year":"2007","journal-title":"Lancet"}],"container-title":["Brain Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3425\/16\/7\/670\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:25:16Z","timestamp":1782966316000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3425\/16\/7\/670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":43,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["brainsci16070670"],"URL":"https:\/\/doi.org\/10.3390\/brainsci16070670","relation":{},"ISSN":["2076-3425"],"issn-type":[{"value":"2076-3425","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,26]]}}}