{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:31:46Z","timestamp":1772137906275,"version":"3.50.1"},"reference-count":37,"publisher":"IOP Publishing","issue":"5","license":[{"start":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T00:00:00Z","timestamp":1724716800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/page\/copyright"},{"start":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T00:00:00Z","timestamp":1724716800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100031258","name":"UCSI University","doi-asserted-by":"crossref","award":["REIG-FETBE-2022-024"],"award-info":[{"award-number":["REIG-FETBE-2022-024"]}],"id":[{"id":"10.13039\/100031258","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Neuromyelitis optica spectrum disorder (NMOSD), also known as Devic disease, is an autoimmune central nervous system disorder in humans that commonly causes inflammatory demyelination in the optic nerves and spinal cord. Inflammation in the optic nerves is termed optic neuritis (ON). ON is a common clinical presentation; however, it is not necessarily present in all NMOSD patients. ON in NMOSD can be relapsing and result in severe vision loss. To the best of our knowledge, no study utilises deep learning to classify ON changes on MRI among patients with NMOSD. Therefore, this study aims to deploy eight state-of-the-art CNN models (Inception-v3, Inception-ResNet-v2, ResNet-101, Xception, ShuffleNet, DenseNet-201, MobileNet-v2, and EfficientNet-B0) with transfer learning to classify NMOSD patients with and without chronic ON using optic nerve magnetic resonance imaging. This study also investigated the effects of data augmentation before and after dataset splitting on cropped and whole images. Both quantitative and qualitative assessments (with Grad-Cam) were used to evaluate the performances of the CNN models. The Inception-v3 was identified as the best CNN model for classifying ON among NMOSD patients, with accuracy of 99.5%, sensitivity of 98.9%, specificity of 93.0%, precision of 100%, NPV of 99.0%, and F1-score of 99.4%. This study also demonstrated that the application of augmentation after dataset splitting could avoid information leaking into the testing datasets, hence producing more realistic and reliable results.<\/jats:p>","DOI":"10.1088\/2057-1976\/ad6f17","type":"journal-article","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T18:48:35Z","timestamp":1723661315000},"page":"055030","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Classification of optic neuritis in neuromyelitis optica spectrum disorders (NMOSD) on MRI using CNN with transfer learning and manipulation of pre-processing on augmentation"],"prefix":"10.1088","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7338-6416","authenticated-orcid":true,"given":"Yang","family":"Feng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3877-4434","authenticated-orcid":true,"given":"Li Sze","family":"Chow","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadia Muhammad","family":"Gowdh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norlisah","family":"Ramli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li Kuo","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suhailah","family":"Abdullah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,8,27]]},"reference":[{"key":"bpexad6f17bib1","doi-asserted-by":"publisher","first-page":"169","DOI":"10.7861\/clinmedicine.19-2-169","article-title":"Neuromyelitis optica spectrum disorders","volume":"19","author":"Huda","year":"2019","journal-title":"Clinical Medicine"},{"key":"bpexad6f17bib2","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1016\/j.msard.2018.12.002","article-title":"Neuromyelitis optica spectrum disorder: pathogenesis, treatment, and experimental models","volume":"27","author":"Wu","year":"2019","journal-title":"Mult. Scler. Relat. Discord."},{"key":"bpexad6f17bib3","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.mri.2021.03.014","article-title":"Recent advances on optic nerve magnetic resonance imaging and post-processing","volume":"79","author":"Chow","year":"2021","journal-title":"Magn. Reson. Imaging"},{"key":"bpexad6f17bib4","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1148\/rg.2018170141","article-title":"Neuromyelitis optica spectrum disorders: spectrum of MR imaging findings and their differential diagnosis","volume":"38","author":"Bruna","year":"2018","journal-title":"Radio Graphics"},{"key":"bpexad6f17bib5","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.preteyeres.2013.03.001","article-title":"Optic neuritis in neuromyelitis optica","volume":"36","author":"Levin","year":"2013","journal-title":"Prog. Retin. Eye Res."},{"key":"bpexad6f17bib6","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1177\/1352458515593406","article-title":"Radiological differentiation of optic neuritis with myelin oligodendrocyte glycoprotein antibodies, aquaporin-4 antibodies, and multiple sclerosis","volume":"22","author":"Ramanathan","year":"2016","journal-title":"Multiple Sclerosis"},{"key":"bpexad6f17bib7","doi-asserted-by":"publisher","first-page":"1854","DOI":"10.1177\/1352458519893093","article-title":"MRI differences between MOG antibody disease and AQP4 NMOSD","volume":"26","author":"Salama","year":"2020","journal-title":"Multiple Sclerosis"},{"key":"bpexad6f17bib8","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1111\/cei.13630","article-title":"Magnetic resonance imaging in neuromyelitis optica spectrum disorder","volume":"206","author":"Clarke","year":"2021","journal-title":"Clin. Exp. Immunol."},{"key":"bpexad6f17bib9","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.jns.2014.07.049","article-title":"Longitudinally extensive optic neuritis in neuromyelitis optica spectrum disorder","volume":"345","author":"Pula","year":"2014","journal-title":"J. Neurol. Sci."},{"key":"bpexad6f17bib10","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.jns.2015.05.013","article-title":"Longitudinally extensive optic neuritis as an MRI biomarker distinguishes neuromyelitis optica from multiple sclerosis","volume":"355","author":"Mealy","year":"2015","journal-title":"J. Neurol. Sci."},{"key":"bpexad6f17bib11","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s13760-016-0714-2","article-title":"Combined brain and anterior visual pathways\u2019 MRIs assist in early identification of neuromyelitis optica spectrum disorder at onset of optic neuritis","volume":"117","author":"Buch","year":"2017","journal-title":"Acta. Neurol. Belg."},{"key":"bpexad6f17bib12","doi-asserted-by":"publisher","DOI":"10.1016\/j.msard.2020.102558","article-title":"Acute optic nerve lesions in first-ever NMOSD-related optic neuritis using conventional brain MRI: a Latin America multicenter study","volume":"46","author":"Contentti","year":"2020","journal-title":"Mult. Sclerosis Relat. Disord."},{"key":"bpexad6f17bib13","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2020.599042","article-title":"Deep learning-based method to differentiate neuromyelitis optica spectrum disorder from multiple sclerosis","volume":"11","author":"Kim","year":"2020","journal-title":"Frontier in Neurology"},{"key":"bpexad6f17bib14","doi-asserted-by":"publisher","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":"Scientific Report"},{"key":"bpexad6f17bib15","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.ejmp.2021.07.030","article-title":"A pipeline to quantify spinal cord atrophy with deep learning: application to differentiation of MS and NMOSD patients","volume":"89","author":"Toufani","year":"2021","journal-title":"Physica. Med."},{"key":"bpexad6f17bib16","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2022.897959","article-title":"Transformer-based deep-learning algorithm for discriminating demyelinating diseases of the central nervous system with neuroimaging","volume":"13","author":"Huang","year":"2022","journal-title":"Frontiers in Immunology"},{"key":"bpexad6f17bib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.health.2023.100270","article-title":"Transfer leraning architectures with fine-tuning for brain tumor classification using magnetic resonance imaging.","volume":"4","author":"Islam","year":"2023","journal-title":"Healthcare Analytics"},{"key":"bpexad6f17bib18","doi-asserted-by":"publisher","first-page":"7232","DOI":"10.1038\/s41598-024-57970-7","article-title":"Employing deep learning and transfer learning for accurage brain tumor detection","volume":"14","author":"Mathivanan","year":"2024","journal-title":"Scientific Report"},{"key":"bpexad6f17bib19","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1212\/WNL.0000000000001729","article-title":"International consensus diagnostic criteria for neuromyelitis optica spectrum disorders","volume":"85","author":"Wingerchuk","year":"2015","journal-title":"Neurology"},{"key":"bpexad6f17bib20","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1177\/1352458515572406","article-title":"Demographic and clinical features of neuromyelitis optica: a review","volume":"21","author":"Pandit","year":"2015","journal-title":"Multiple Sclerosis"},{"key":"bpexad6f17bib21","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvarju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"bpexad6f17bib22","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big. Data"},{"key":"bpexad6f17bib23","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s12859-023-05199-y","article-title":"Which data subset should be augmented for deep learning? a simulation study using urothelial cell carcinoma histopathology images","volume":"24","author":"Ameen","year":"2023","journal-title":"BMC Bioinf."},{"key":"bpexad6f17bib24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.00567","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2015","unstructured":"Szegedy C 2015 Rethinking the inception architecture for computer vision arXiv: 1512.00567 10.48550\/arXiv.1512.00567"},{"key":"bpexad6f17bib25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1602.07261","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"Szegedy","year":"2016","unstructured":"Szegedy C 2016 Inception-v4, inception-ResNet and the impact of residual connections on learning arXiv: 1602.07261 10.48550\/arXiv.1602.07261"},{"key":"bpexad6f17bib26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.1409.4842","article-title":"Convolutions","author":"Szegedy","year":"2014"},{"key":"bpexad6f17bib27","doi-asserted-by":"publisher","first-page":"307","DOI":"10.21037\/atm.2019.06.29","article-title":"Deep convolutional neural network Inception-v3 model for differential diagnosing of lymph node in cytological images: a pilot study","volume":"7","author":"Guan","year":"2019","journal-title":"Ann. Transl. Med."},{"key":"bpexad6f17bib28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.03385","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","unstructured":"He K Zhang X Ren S Sun J 2015 Deep residual learning for image recognition arXiv: 1512.03385v1 10.48550\/arXiv.1512.03385"},{"key":"bpexad6f17bib29","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.48550\/arXiv.1610.02357","article-title":"Xception: deep learning with depthwise separable convolutions","author":"Chollet","year":"2017"},{"key":"bpexad6f17bib30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1707.01083","article-title":"Shuffle net: an extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2017","unstructured":"Zhang X Zhou X Lin M Sun J 2017 Shuffle net: an extremely efficient convolutional neural network for mobile devices arXiv: 1707.01083 10.48550\/arXiv.1707.01083"},{"key":"bpexad6f17bib31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1608.06993","article-title":"Densely connected convolutional networks","author":"Huang","year":"2018","unstructured":"Huang G Liu Z Weinberger K Q van der Maaten L 2018 Densely connected convolutional networks arXiv: 1608.06993v5 10.48550\/arXiv.1608.06993"},{"key":"bpexad6f17bib32","doi-asserted-by":"publisher","first-page":"4510","DOI":"10.48550\/arXiv.1801.04381","article-title":"MobileNetV2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"bpexad6f17bib33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.11946","article-title":"Efficient net: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2020","unstructured":"Tan M Le Q V 2020 Efficient net: rethinking model scaling for convolutional neural networks arXiv: 1905.11946v5 10.48550\/arXiv.1905.11946"},{"key":"bpexad6f17bib34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.02685","article-title":"A comprehensive survey on transfer learning","author":"Zhuang","year":"2019","unstructured":"Zhuang F 2019 A comprehensive survey on transfer learning arXiv: 1911.02685 10.48550\/arXiv.1911.02685"},{"key":"bpexad6f17bib35","author":"ImageNet"},{"key":"bpexad6f17bib36","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/s42979-022-01545-8","article-title":"Quantitative and qualitative analysis of 18 deep convolutional neural network (CNN) models with transfer learning to diagnose COVID-19 on chest x-ray (CXR) images","volume":"4","author":"Chow","year":"2023","journal-title":"SN Computer Science"},{"key":"bpexad6f17bib37","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2023.101423","article-title":"Introducing a deep learning method for brain tumor classification using MRI data towards better performance","volume":"44","author":"Simo","year":"2024","journal-title":"Informatics in Medicine Unlocked"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ad6f17","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ad6f17\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ad6f17","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ad6f17\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ad6f17\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ad6f17\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ad6f17\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ad6f17\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T06:37:13Z","timestamp":1724740633000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ad6f17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,27]]},"references-count":37,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,8,27]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ad6f17","relation":{"has-review":[{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v4\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v3\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v4\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v3\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v3\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AD6F17\/v2\/review1","asserted-by":"object"}]},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,27]]},"assertion":[{"value":"Classification of optic neuritis in neuromyelitis optica spectrum disorders (NMOSD) on MRI using CNN with transfer learning and manipulation of pre-processing on augmentation","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2024-05-30","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}