ntvНаучно-технический вестник информационных технологий, механики и оптикиScientific and Technical Journal of Information Technologies, Mechanics and Optics2226-14942500-0373Университет ИТМО10.17586/2226-1494-2024-24-5-824-833ntv-153Research ArticleКОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИCOMPUTER SCIENCEКлассификация поражений рассеянным склерозом посредством анализа изображений магнитно-резонансной томографии методом глубокого обученияClassification of multiple sclerosis lesion through Deep Learning analysis of MRI imageshttps://orcid.org/0000-0002-9960-8061ДивьяМ.DivyaM.

Дивья Матаван - PhD, исследователь

Кампус Рамапурам, Ченнаи, 600089

Mathavan Divya - PhD, Researcher

Ramapuram Campus, Chennai, 600089

divyam1@srmist.edu.inhttps://orcid.org/0000-0003-2122-5076ДхилипанДж.DhilipanJ.

Дхилипан Джаесилан - PhD, профессор, руководитель

Кампус Рамапурам, Ченнаи, 600089

Jayeseelan Dhilipan - PhD, Professor, Header

Ramapuram Campus, Chennai, 600089

hod.mca.rmp@srmist.edu.inhttps://orcid.org/0000-0003-2093-900XСаравананА.SaravananA.

Сараванан Аппу - PhD, профессор

Кампус Рамапурам, Ченнаи, 600089

Appu Saravanan - PhD, Professor

Ramapuram Campus, Chennai

dean.academic@srmrmp.edu.inИнститут науки и технологий SRMИндияSRM Institute of Science and TechnologyIndiaИнженерный колледж ИасвариИндияEaswari Engineering CollegeIndia202414122024245824833Copyright © Дивья М., Дхилипан Д., Сараванан А., 20242024Дивья М., Дхилипан Д., Сараванан А.Divya M., Dhilipan J., Saravanan A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://ntv.elpub.ru/jour/article/view/153

Рассеянный склероз (РС) представляет собой прогрессирующее аутоиммунное заболевание, поражающее центральную нервную систему. Раннее и точное обнаружение поражений РС на снимках магнитно-резонансной томографии (МРТ) головного мозга имеет решающее значение для эффективного лечения. В работе предлагается классификация на основе глубокого обучения для автоматического обнаружения и диагностики поражений РС на снимках МРТ, использующий сверточные нейронные сети (Convolutional Neural Network, CNNs) для точной идентификации и классификации поражений. Классификация включает в себя всесторонний анализ наборов данных МРТ и этапы их предварительной обработки, такие как нормализация и сегментация поражений. Предложенная архитектура CNN, разработанная для обнаружения поражений РС, достигает точности 98,2 % на тестовом наборе данных. Благодаря внедрению передовых методов распознавания изображений, представленный метод глубокого обучения классифицирует поражения РС среди различных патологий мозга, присутствующих на снимках МРТ. Метод выделяет поражения РС на снимках МРТ, помогая нейрорадиологам в точной диагностике и планировании лечения. Исследование вносит вклад в улучшение диагностики РС, предоставляя надежный и автоматизированный инструмент обнаружения и классификации поражений.

Multiple Sclerosis (MS) is a progressive autoimmune disease affecting the central nervous system, causing communication disruptions between the brain and the body. Early and accurate detection of MS lesions in brain Magnetic Resonance Imaging (MRI) scans is crucial for effective treatment. This paper proposes MSNet, a deep learning-based approach for automatic detection and diagnosis of MS lesions from MRI images, leveraging Convolutional Neural Networks (CNNs) for precise lesion identification and classification. Our methodology involves a comprehensive analysis of MRI datasets, including preprocessing steps such as normalization and lesion segmentation. We propose a novel CNN architecture tailored for MS lesion detection, achieving an accuracy rate of 98.2 % on the test dataset. By incorporating advanced image recognition techniques, our system classifies MS lesions from diverse brain pathologies present in MRI images. The model also highlights MS lesions within the MRI images, aiding neuroradiologists in accurate diagnosis and treatment planning. This study contributes significantly to improving MS diagnosis by providing a reliable and automated tool for lesion detection and classification.

рассеянный склерозмашинное обучениеМРТmultiple sclerosismachine learningMRIReferencesLópez-Dorado A., Pérez J., Rodrigo M.J., Miguel-Jiménez J.M., Ortiz M., de Santiago L., López-Guillén E., Blanco R., Cavalliere C., Morla E.M.S., Boquete L., Garcia-Martin E. Diagnosis of multiple sclerosis using multifocal ERG data feature fusion. Information Fusion, 2021, vol. 76, pp. 157–167. https://doi.org/10.1016/j.inffus.2021.05.006López-Dorado A., Pérez J., Rodrigo M.J., Miguel-Jiménez J.M., Ortiz M., de Santiago L., López-Guillén E., Blanco R., Cavalliere C., Morla E.M.S., Boquete L., Garcia-Martin E. Diagnosis of multiple sclerosis using multifocal ERG data feature fusion // Information Fusion. 2021. V. 76. P. 157–167. https://doi.org/10.1016/j.inffus.2021.05.006Mohseni E., Moghaddasi S.M. A hybrid approach for MS diagnosis through nonlinear EEG descriptors and metaheuristic optimized classification learning. Computational Intelligence and Neuroscience, 2022, vol. 2022, pp. 5430528. https://doi.org/10.1155/2022/5430528Mohseni E., Moghaddasi S.M. A hybrid approach for MS diagnosis through nonlinear EEG descriptors and metaheuristic optimized classification learning // Computational Intelligence and Neuroscience. 2022. V. 2022. P. 5430528. https://doi.org/10.1155/2022/5430528Ahmadi A., Davoudi S., Daliri M.R. Computer Aided Diagnosis System for multiple sclerosis disease based on phase to amplitude coupling in covert visual attention. Computer Methods and Programs in Biomedicine, 2019, vol. 169, pp. 9–18. https://doi.org/10.1016/j.cmpb.2018.11.006Ahmadi A., Davoudi S., Daliri M.R. Computer Aided Diagnosis System for multiple sclerosis disease based on phase to amplitude coupling in covert visual attention // Computer Methods and Programs in Biomedicine. 2019. V. 169. P. 9–18. https://doi.org/10.1016/j.cmpb.2018.11.006Karaca B.K., Akşahin M.F., Öcal R. Detection of multiple sclerosis from photic stimulation EEG signals. Biomedical Signal Processing and Control, 2021, vol. 67, pp. 102571. https://doi.org/10.1016/j.bspc.2021.102571Karaca B.K., Akşahin M.F., Öcal R. Detection of multiple sclerosis from photic stimulation EEG signals // Biomedical Signal Processing and Control. 2021. V. 67. P. 102571. https://doi.org/10.1016/j.bspc.2021.102571De Santiago L., Morla E.M.S., Ortiz M., López E., Usanos C.A., Alonso-Rodríguez M.C., Barea R., Cavaliere-Ballesta C., Fernández A., Boquete L. A computer-aided diagnosis of multiple sclerosis based on mfVEP recordings. PLoS ONE, 2019, vol. 14, no. 4, pp. e0214662. https://doi.org/10.1371/journal.pone.0214662De Santiago L., Morla E.M.S., Ortiz M., López E., Usanos C.A., Alonso-Rodríguez M.C., Barea R., Cavaliere-Ballesta C., Fernández A., Boquete L. A computer-aided diagnosis of multiple sclerosis based on mfVEP recordings // PLoS ONE. 2019. V. 14. N 4. P. e0214662. https://doi.org/10.1371/journal.pone.0214662Yperman J., Becker T., Valkenborg D., Popescu V., Hellings N., Van Wijmeersch B., Peeters L.M. Machine learning analysis of motor evoked potential time series to predict disability progression in multiple sclerosis. BMC Neurology, 2020, vol. 20, no. 1, pp. 105. https://doi.org/10.1186/s12883-020-01672-wYperman J., Becker T., Valkenborg D., Popescu V., Hellings N., Van Wijmeersch B., Peeters L.M. Machine learning analysis of motor evoked potential time series to predict disability progression in multiple sclerosis // BMC Neurology. 2020. V. 20. N 1. P. 105. https:// doi.org/10.1186/s12883-020-01672-wSolana E., Martinez-Heras E., Casas-Roma J., Calvet L., Lopez-Soley E., Sepulveda M., Sola-Valls N., Montejo C., Blanco Y., Pulido-Valdeolivas I., Andorra M., Saiz A., Prados F., Llufriu S. Modified connectivity of vulnerable brain nodes in multiple sclerosis, their impact on cognition and their discriminative value. Scientific Reports, 2019, vol. 9, pp. 20172. https://doi.org/10.1038/s41598-019-56806-zSolana E., Martinez-Heras E., Casas-Roma J., Calvet L., Lopez-Soley E., Sepulveda M., Sola-Valls N., Montejo C., Blanco Y., PulidoValdeolivas I., Andorra M., Saiz A., Prados F., Llufriu S. Modified connectivity of vulnerable brain nodes in multiple sclerosis, their impact on cognition and their discriminative value // Scientific Reports. 2019. V. 9. P. 20172. https://doi.org/10.1038/s41598-019-56806-zKawahara J. Spinal Cord Segmentation and Disability Prediction in Multiple Sclerosis Using Novel Optimization and Machine Learning Methods: Ph.D. Dissertation. Vancouver Island University, Nanaimo, BC, Canada. 2013, 57 p.Kawahara J. Spinal Cord Segmentation and Disability Prediction in Multiple Sclerosis Using Novel Optimization and Machine Learning Methods: Ph.D. Dissertation. Vancouver Island University, Nanaimo, BC, Canada. 2013. 57 p.Zhang H., Alberts E., Pongratz V., Mühlau M., Zimmer C., Wiestler B., Eichinger P. Predicting conversion from clinically isolated syndrome to multiple sclerosis–An imaging-based machine learning approach. NeuroImage Clinical, 2019, vol. 21, pp. 101593. https://doi.org/10.1016/j.nicl.2018.11.003Zhang H., Alberts E., Pongratz V., Mühlau M., Zimmer C., Wiestler B., Eichinger P. Predicting conversion from clinically isolated syndrome to multiple sclerosis–An imaging-based machine learning approach // NeuroImage Clinical. 2019. V. 21. P. 101593. https://doi.org/10.1016/j.nicl.2018.11.003Rezaee A., Rezaee K., Haddadnia J., Gorji H.T. Supervised metaheuristic extreme learning machine for multiple sclerosis detection based on multiple feature descriptors in MR images. SN Applied Sciences, 2020, vol. 2, no. 5, pp. 866. https://doi.org/10.1007/s42452-020-2699-yRezaee A., Rezaee K., Haddadnia J., Gorji H.T. Supervised metaheuristic extreme learning machine for multiple sclerosis detection based on multiple feature descriptors in MR images // SN Applied Sciences. 2020. V. 2. N 5. P. 866. https://doi.org/10.1007/s42452-020-2699-yEkşi Z., Özcan E.M., Çakıroğlu M., Öz C., Aralaşmak A. Differentiation of multiple sclerosis lesions and low-grade brain tumors on MRS data: Machine learning approaches. Neurological Sciences, 2021, vol. 42, no. 8, pp. 3389–3395. https://doi.org/10.1007/s10072-020-04950-0Ekşi Z., Özcan E.M., Çakıroğlu M., Öz C., Aralaşmak A. Differentiation of multiple sclerosis lesions and low-grade brain tumors on MRS data: Machine learning approaches // Neurological Sciences. 2021. V. 42. N 8. P. 3389–3395. https://doi.org/10.1007/s10072-020-04950-0Peng Y., Zheng Y., Tan Z., Liu J., Xiang Y., Liu H., Dai L., Xie Y., Wang J., Zeng C., Li Y. Prediction of unenhanced lesion evolution in multiple sclerosis using radiomics-based models: A machine learning approach. Multiple Sclerosis and Related Disorders, 2021, vol. 53, pp. 102989. https://doi.org/10.1016/j.msard.2021.102989Peng Y., Zheng Y., Tan Z., Liu J., Xiang Y., Liu H., Dai L., Xie Y., Wang J., Zeng C., Li Y. Prediction of unenhanced lesion evolution in multiple sclerosis using radiomics-based models: A machine learning approach // Multiple Sclerosis and Related Disorders. 2021. V. 53. P. 102989. https://doi.org/10.1016/j.msard.2021.102989Eshaghi A., Young A.L., Wijeratne P.A., Prados F., Arnold D.L., Narayanan S., Guttmann C.R.G., Barkhof F., Alexander D.C., Thompson A.J., Chard D., Ciccarelli O. Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data. Nature Communications, 2021, vol. 12, no. 1, pp. 2078. https://doi.org/10.1038/s41467-021-22265-2Eshaghi A., Young A.L., Wijeratne P.A., Prados F., Arnold D.L., Narayanan S., Guttmann C.R.G., Barkhof F., Alexander D.C., Thompson A.J., Chard D., Ciccarelli O. Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data // Nature Communications. 2021. V. 12. N 1. P. 2078. https://doi.org/10.1038/s41467-021-22265-2Bonanno L., Mammone N., De Salvo S., Bramanti A., Rifici C., Sessa E., Bramanti P., Marino S., Ciurleo R. Multiple Sclerosis lesions detection by a hybrid Watershed-Clustering algorithm. Clinical Imaging, 2021, vol. 72, pp. 162–167. https://doi.org/10.1016/j.clinimag.2020.11.006Bonanno L., Mammone N., De Salvo S., Bramanti A., Rifici C., Sessa E., Bramanti P., Marino S., Ciurleo R. Multiple Sclerosis lesions detection by a hybrid Watershed-Clustering algorithm // Clinical Imaging. 2021. V. 72. P. 162–167. https://doi.org/10.1016/j.clinimag.2020.11.006Iswisi A.F.A., Karan O., Rahebi J. Diagnosis of Multiple Sclerosis Disease in Brain Magnetic Resonance Imaging Based on the Harris Hawks Optimization Algorithm. BioMed Research International, 2021, pp. 3248834. https://doi.org/10.1155/2021/3248834Iswisi A.F.A., Karan O., Rahebi J. Diagnosis of Multiple Sclerosis Disease in Brain Magnetic Resonance Imaging Based on the Harris Hawks Optimization Algorithm // BioMed Research International. 2021. P. 3248834. https://doi.org/10.1155/2021/3248834Jain S., Rajpal N., Yadav J. Supervised and unsupervised machine learning techniques for multiple sclerosis identification: A performance comparative analysis. Advances in Intelligent Systems and Computing, 2022, vol. 1374, pp. 369–381. https://doi.org/10.1007/978-981-16-3346-1_30Jain S., Rajpal N., Yadav J. Supervised and unsupervised machine learning techniques for multiple sclerosis identification: A performance comparative analysis // Advances in Intelligent Systems and Computing. 2022. V. 1374. P. 369–381. https://doi.org/10.1007/978-981-16-3346-1_30Garcia-Martin E., Ortiz M., Boquete L., Sánchez-Morla E.M., Barea R., Cavaliere C., Vilades E., Orduna E., Rodrigo M.J. Early diagnosis of multiple sclerosis by OCT analysis using Cohen’s d method and a neural network as classifier. Computers in Biology and Medicine, 2021, vol. 129, pp. 104165. https://doi.org/10.1016/j.compbiomed.2020.104165Garcia-Martin E., Ortiz M., Boquete L., Sánchez-Morla E.M., Barea R., Cavaliere C., Vilades E., Orduna E., Rodrigo M.J. Early diagnosis of multiple sclerosis by OCT analysis using Cohen’s d method and a neural network as classifier // Computers in Biology and Medicine. 2021. V. 129. P. 104165. https://doi.org/10.1016/j.compbiomed.2020.104165Montolío A., Cegoñino J., Garcia-Martin E., Pérez del Palomar A. Comparison of machine learning methods using spectralis OCT for diagnosis and disability progression prognosis in multiple sclerosis. Annals of Biomedical Engineering, 2022, vol. 50, no. 5, pp. 507–528. https://doi.org/10.1007/s10439-022-02930-3Montolío A., Cegoñino J., Garcia-Martin E., Pérez del Palomar A. Comparison of machine learning methods using spectralis OCT for diagnosis and disability progression prognosis in multiple sclerosis // Annals of Biomedical Engineering. 2022. V. 50. N 5. P. 507–528. https://doi.org/10.1007/s10439-022-02930-3

The authors declare that there are no conflicts of interest present.