{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T18:47:07Z","timestamp":1773514027195,"version":"3.50.1"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>This study presents an automated system using Convolutional Neural Networks (CNNs) for segmenting FLAIR Magnetic Resonance Imaging (MRI) images to aid in the diagnosis of Multiple Sclerosis (MS). The dataset included 103 patients from Imam Khomeini Hospital, Tehran and an additional 10 patients from an external center. Key preprocessing steps included skull stripping, normalization, resizing, segmentation mask processing, entropy-based exclusion, and data augmentation. The nnU-Net architecture tailored for 2D slices was employed and trained using a fivefold cross-validation approach. In the slice-level classification approach, the model achieved 83% accuracy, 100% sensitivity, 75% positive predictive value (PPV), and 99% negative predictive value (NPV) on the internal test set. For the external test set, the accuracy was 76%, sensitivity 100%, PPV 68%, and NPV 100%. Voxel-level segmentation showed a Dice Similarity Coefficient (DSC) of 70% for the internal set and 75% for the external set. The CNN-based system with nnU-Net architecture demonstrated high accuracy and reliability in segmenting MS lesions, highlighting its potential for enhancing clinical decision-making.<\/jats:p>","DOI":"10.1038\/s41598-025-14112-x","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T09:24:05Z","timestamp":1760606645000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Convolutional neural network based system for fully automatic FLAIR MRI segmentation in multiple sclerosis diagnosis"],"prefix":"10.1038","volume":"15","author":[{"given":"Ali Arian","family":"Darestani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahsa Naeeni","family":"Davarani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Virginia Guillen","family":"-Ca\u00f1as","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hasan","family":"Hashemi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amin","family":"Zarei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanaz Heydari","family":"Havadaragh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad Hossein","family":"Harirchian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"14112_CR1","doi-asserted-by":"crossref","unstructured":"Tauseef, A. & Hayee, S. Multiple Sclerosis: A Neurological Disorder. THE THERAPIST (Journal of Therapies & Rehabilitation Sciences), 02\u201303 (2020).","DOI":"10.54393\/tt.v1i1.1"},{"key":"14112_CR2","doi-asserted-by":"publisher","first-page":"19560","DOI":"10.1038\/s41598-020-76420-8","volume":"10","author":"DT Okuda","year":"2020","unstructured":"Okuda, D. T. et al. Utility of shape evolution and displacement in the classification of chronic multiple sclerosis lesions. Sci. Rep. 10, 19560. https:\/\/doi.org\/10.1038\/s41598-020-76420-8 (2020).","journal-title":"Sci. Rep."},{"key":"14112_CR3","doi-asserted-by":"crossref","unstructured":"Ontaneda, D., Ross, L. A. & Hohlfeld, R. Vol. 97 975\u2013976 (AAN Enterprises, 2021).","DOI":"10.1212\/WNL.0000000000012883"},{"key":"14112_CR4","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3390\/diagnostics12010077","volume":"12","author":"EM Haacke","year":"2021","unstructured":"Haacke, E. M. et al. A comparison of magnetic resonance imaging methods to assess multiple sclerosis lesions: Implications for patient characterization and clinical trial design. Diagnostics 12, 77 (2021).","journal-title":"Diagnostics"},{"key":"14112_CR5","doi-asserted-by":"publisher","first-page":"102445","DOI":"10.1016\/j.nicl.2020.102445","volume":"28","author":"J Kr\u00fcger","year":"2020","unstructured":"Kr\u00fcger, J. et al. Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks. NeuroImage: Clin. 28, 102445 (2020).","journal-title":"NeuroImage: Clin."},{"key":"14112_CR6","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.compmedimag.2018.10.002","volume":"70","author":"A Danelakis","year":"2018","unstructured":"Danelakis, A., Theoharis, T. & Verganelakis, D. A. Survey of automated multiple sclerosis lesion segmentation techniques on magnetic resonance imaging. Comput. Med. Imag. Graph. 70, 83\u2013100. https:\/\/doi.org\/10.1016\/j.compmedimag.2018.10.002 (2018).","journal-title":"Comput. Med. Imag. Graph."},{"key":"14112_CR7","unstructured":"Roy, S., Butman, J. A., Reich, D. S., Calabresi, P. A. & Pham, D. L. Multiple Sclerosis Lesion Segmentation from Brain MRI via fully convolutional neural networks. ArXivabs\/1803.09172 (2018)."},{"key":"14112_CR8","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1093\/postmj\/qgad095","volume":"99","author":"G Kourounis","year":"2023","unstructured":"Kourounis, G. et al. Computer image analysis with artificial intelligence: a practical introduction to convolutional neural networks for medical professionals. Postgrad. Med. J. 99, 1287\u20131294 (2023).","journal-title":"Postgrad. Med. J."},{"key":"14112_CR9","doi-asserted-by":"publisher","first-page":"4411","DOI":"10.3390\/electronics12214411","volume":"12","author":"I Gali\u0107","year":"2023","unstructured":"Gali\u0107, I., Habijan, M., Leventi\u0107, H. & Romi\u0107, K. Machine learning empowering personalized medicine: A comprehensive review of medical image analysis methods. Electronics 12, 4411 (2023).","journal-title":"Electronics"},{"key":"14112_CR10","first-page":"e209039","volume":"3","author":"R Savjani","year":"2021","unstructured":"Savjani, R. nnU-Net: further automating biomedical image autosegmentation. Radiol: Imag. Cancer 3, e209039 (2021).","journal-title":"Radiol: Imag. Cancer"},{"key":"14112_CR11","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J. & Maier-Hein, K. H. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203\u2013211 (2021).","journal-title":"Nat. Methods"},{"key":"14112_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.media.2012.09.004","volume":"17","author":"D Garc\u00eda-Lorenzo","year":"2013","unstructured":"Garc\u00eda-Lorenzo, D., Francis, S., Narayanan, S., Arnold, D. L. & Collins, D. L. Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging. Med. Image Anal. 17, 1\u201318 (2013).","journal-title":"Med. Image Anal."},{"key":"14112_CR13","doi-asserted-by":"publisher","first-page":"39","DOI":"10.7575\/aiac.abcmed.v.7n.2p.39","volume":"7","author":"AD Almutairi","year":"2019","unstructured":"Almutairi, A. D., Mahmud, R., Suppiah, S. & Hassan, H. A. Accuracy of MRI sequences in detecting multiple sclerosis (MS) lesions: A systematic review. Adv. Biosci. Clin. Med. 7, 39\u201343 (2019).","journal-title":"Adv. Biosci. Clin. Med."},{"key":"14112_CR14","doi-asserted-by":"publisher","first-page":"1637","DOI":"10.1007\/s00234-020-02481-1","volume":"62","author":"K Gau","year":"2020","unstructured":"Gau, K. et al. Accuracy and practical aspects of semi-and fully automatic segmentation methods for resected brain areas. Neuroradiology 62, 1637\u20131648 (2020).","journal-title":"Neuroradiology"},{"key":"14112_CR15","doi-asserted-by":"publisher","first-page":"16304","DOI":"10.1038\/s41598-024-67130-6","volume":"14","author":"M NaeeniDavarani","year":"2024","unstructured":"NaeeniDavarani, M. et al. Efficient segmentation of active and inactive plaques in FLAIR-images using DeepLabV3Plus SE with efficientnetb0 backbone in multiple sclerosis. Sci Rep 14, 16304. https:\/\/doi.org\/10.1038\/s41598-024-67130-6 (2024).","journal-title":"Sci Rep"},{"key":"14112_CR16","unstructured":"Roy, S., Butman, J. A., Reich, D. S., Calabresi, P. A. & Pham, D. L. Multiple sclerosis lesion segmentation from brain MRI via fully convolutional neural networks. arXiv preprint arXiv:1803.09172 (2018)."},{"key":"14112_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.116442","volume":"208","author":"RA Brown","year":"2020","unstructured":"Brown, R. A. et al. Deep learning segmentation of orbital fat to calibrate conventional MRI for longitudinal studies. Neuroimage 208, 116442 (2020).","journal-title":"Neuroimage"},{"key":"14112_CR18","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1177\/1352458520921364","volume":"27","author":"I Coronado","year":"2021","unstructured":"Coronado, I., Gabr, R. E. & Narayana, P. A. Deep learning segmentation of gadolinium-enhancing lesions in multiple sclerosis. Mult. Scler. J. 27, 519\u2013527 (2021).","journal-title":"Mult. Scler. J."},{"key":"14112_CR19","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.1007\/s11517-020-02225-6","volume":"58","author":"E Essa","year":"2020","unstructured":"Essa, E., Aldesouky, D., Hussein, S. E. & Rashad, M. Z. Neuro-fuzzy patch-wise R-CNN for multiple sclerosis segmentation. Med Biol Eng Comput 58, 2161\u20132175. https:\/\/doi.org\/10.1007\/s11517-020-02225-6 (2020).","journal-title":"Med Biol Eng Comput"},{"key":"14112_CR20","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.engappai.2017.06.006","volume":"65","author":"A Birenbaum","year":"2017","unstructured":"Birenbaum, A. & Greenspan, H. Multi-view longitudinal CNN for multiple sclerosis lesion segmentation. Eng. Appl. Artif. Intell. 65, 111\u2013118 (2017).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"14112_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neuroimage.2019.03.068","volume":"196","author":"S Aslani","year":"2019","unstructured":"Aslani, S. et al. Multi-branch convolutional neural network for multiple sclerosis lesion segmentation. Neuroimage 196, 1\u201315 (2019).","journal-title":"Neuroimage"},{"key":"14112_CR22","doi-asserted-by":"crossref","unstructured":"Nichyporuk, B. et al. Rethinking generalization: the impact of annotation style on medical image segmentation. arXiv preprint arXiv:2210.17398 (2022).","DOI":"10.59275\/j.melba.2022-2d93"},{"key":"14112_CR23","doi-asserted-by":"publisher","first-page":"103611","DOI":"10.1016\/j.nicl.2024.103611","volume":"42","author":"T Wiltgen","year":"2024","unstructured":"Wiltgen, T. et al. LST-AI: a deep learning ensemble for accurate MS lesion segmentation. NeuroImage: Clin. 42, 103611 (2024).","journal-title":"NeuroImage: Clin."},{"key":"14112_CR24","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1177\/1352458519856843","volume":"26","author":"RE Gabr","year":"2020","unstructured":"Gabr, R. E. et al. Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks: A large-scale study. Mult. Scler. J. 26, 1217\u20131226 (2020).","journal-title":"Mult. Scler. J."},{"key":"14112_CR25","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.3174\/ajnr.A6138","volume":"40","author":"MT Duong","year":"2019","unstructured":"Duong, M. T. et al. Convolutional neural network for automated FLAIR lesion segmentation on clinical brain MR imaging. Am. J. Neuroradiol. 40, 1282\u20131290 (2019).","journal-title":"Am. J. Neuroradiol."},{"key":"14112_CR26","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2020.012448","author":"H Afzal","year":"2021","unstructured":"Afzal, H. et al. Automatic and robust segmentation of multiple sclerosis lesions with convolutional neural networks. Comput, Mater. Cont. https:\/\/doi.org\/10.32604\/cmc.2020.012448 (2021).","journal-title":"Comput, Mater. Cont."},{"key":"14112_CR27","unstructured":"de Oliveira, M. et al. in 2020 IEEE international conference on bioinformatics and biomedicine (BIBM). 2045\u20132048 (IEEE)."},{"key":"14112_CR28","doi-asserted-by":"publisher","first-page":"1476","DOI":"10.1007\/s00259-023-06555-z","volume":"51","author":"E Jafari","year":"2024","unstructured":"Jafari, E. et al. A convolutional neural network\u2013based system for fully automatic segmentation of whole-body [68Ga] Ga-PSMA PET images in prostate cancer. Eur. J. Nucl. Med. Mol. Imaging 51, 1476\u20131487 (2024).","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14112-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14112-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14112-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T09:24:09Z","timestamp":1760606649000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14112-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["14112"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-14112-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]},"assertion":[{"value":"9 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that there are no competing interests associated with this research. No financial, personal, or professional relationships exist that could influence the objectivity or integrity of the reported findings. This includes, but is not limited to, any affiliations with organizations or entities that may have a direct or indirect interest in the subject matter discussed in this manuscript. We affirm that there are no conflicts of interest that might affect the impartiality of the study or the interpretation of its results.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This research adheres to all ethical considerations relevant to the content of this article. The study was conducted in compliance with established ethical standards, specifically in accordance with the Declaration of Helsinki. All necessary approvals and permissions were obtained from the appropriate ethical review boards. Informed consent was obtained from all participants involved in the study, ensuring their willingness to participate. The confidentiality and anonymity of participants have been rigorously protected throughout the research process. Furthermore, the research design and procedures were ethically reviewed to ensure they met the highest standards of integrity and transparency. Any potential conflicts of interest were appropriately disclosed, and steps were taken to mitigate and manage them. This article discusses the ethical implications of the research, addressing key considerations such as the treatment of human or animal subjects, data confidentiality, and potential biases. The methodology employed in this study aligns with ethical principles, and any deviations from standard ethical practices are explicitly justified. In summary, this research article upholds a commitment to ethical conduct in all aspects of the study. The following sections elaborate on specific ethical considerations within the context of the presented research. Ethics approval was obtained from the ethics committee of Tehran University of Medical Sciences (Imam Khomeini Hospital) in Tehran: IR.TUMS.NI.REC.1401.038.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"36146"}}