{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T01:48:01Z","timestamp":1772761681542,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:00:00Z","timestamp":1768435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>In light of the growing prevalence of the autoimmune disease multiple sclerosis (MS), accurate detection of MS lesions in brain magnetic resonance imaging (MRI) images plays a critical role in assisting neurologists with timely diagnosis. The high similarity between MS lesions and normal brain tissues, however, makes this task particularly challenging. Although numerous deep-learning-based approaches have been proposed for the automatic segmentation of MS lesions, the method presented in this study has achieved superior results. ZechariahNet is a U-Net-based architecture that integrates transition down blocks, squeeze-attention (SA) blocks, dense blocks, and Convolutional LSTM (C-LSTM) blocks within a 3D CNN framework. By jointly exploiting spatial\u2013temporal information from three consecutive MRI slices (previous, current, and subsequent) and strategically applying C-LSTM modules across the encoder and decoder paths, the proposed model effectively captures the neighborhood dependencies for enhanced feature extraction and reconstruction. These architectural innovations significantly improve segmentation accuracy, enabling ZechariahNet to achieve a dice similarity coefficient (DSC) of 84.72%, outperforming existing state-of-the-art methods.<\/jats:p>","DOI":"10.3390\/a19010072","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T12:31:41Z","timestamp":1768480301000},"page":"72","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ZechariahNet: A Novel Method of MS Lesion Diagnosis Through MRI Images by the Combination of C-LSTM and 3D CNN Algorithms"],"prefix":"10.3390","volume":"19","author":[{"given":"Mahshid","family":"Dehghanpour","sequence":"first","affiliation":[{"name":"Faculty of Computer Engineering, Shahrood University of Technology, Shahrood 3619995161, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2133-3480","authenticated-orcid":false,"given":"Mansoor","family":"Fateh","sequence":"additional","affiliation":[{"name":"Faculty of Computer Engineering, Shahrood University of Technology, Shahrood 3619995161, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeynab","family":"Mohammadpoory","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering, Shahrood University of Technology, Shahrood 3619995161, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8887-0339","authenticated-orcid":false,"given":"Saideh","family":"Ferdowsi","sequence":"additional","affiliation":[{"name":"School of Mathematics, Statistics and Actuarial Science, University of Essex, Colchester CO4 3SQ, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kamraoui, R.A., Mansencal, B., Manj\u00f3n, J.V., and Coup\u00e9, P. (2022). Longitudinal detection of new multiple sclerosis lesions using deep learning. Front. Neuroimaging, 1.","DOI":"10.3389\/fnimg.2022.948235"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Alsahanova, N., Bartenev, P., Sharaev, M., Ljubisavljevic, M., Mansoori, T.A., and Statsenko, Y. (2025). Integrating radiomics with deep learning enhances multiple sclerosis lesion delineation. arXiv.","DOI":"10.1007\/978-3-032-13977-1_4"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e12866","DOI":"10.1002\/eng2.12866","article-title":"Diagnosis of glaucoma using multi-scale attention block in convolutional neural networks and data augmentation techniques","volume":"6","author":"Khajeha","year":"2024","journal-title":"Eng. Rep."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Saber, A., Fateh, A., Parhami, P., Siahkarzadeh, A., Fateh, M., and Ferdowsi, S. (2025). Efficient and accurate pneumonia detection using a novel multi-scale transformer approach. Sensors, 25.","DOI":"10.3390\/s25237233"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Alrabai, A., Echtioui, A., and Hamida, A.B. (2022, January 24\u201327). Multiple sclerosis segmentation using deep learning models: Comparative study. Proceedings of the 6th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), Sfax, Tunisia.","DOI":"10.1109\/ATSIP55956.2022.9805983"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neuroimage.2019.03.068","article-title":"Multi-branch convolutional neural network for multiple sclerosis lesion segmentation","volume":"196","author":"Aslani","year":"2019","journal-title":"NeuroImage"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"102854","DOI":"10.1016\/j.nicl.2021.102854","article-title":"ALL-Net: Anatomical information lesion-wise loss function integrated into neural network for multiple sclerosis lesion segmentation","volume":"32","author":"Zhang","year":"2021","journal-title":"NeuroImage Clin."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"105402","DOI":"10.1016\/j.compbiomed.2022.105402","article-title":"Delve into multiple sclerosis lesion exploration: A modified attention U-Net for MS lesion segmentation in brain MRI","volume":"145","author":"Hashemi","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"104965","DOI":"10.1016\/j.ijmedinf.2022.104965","article-title":"A dense residual U-Net for multiple sclerosis lesion segmentation from multi-sequence 3D MR images","volume":"170","author":"Sarica","year":"2023","journal-title":"Int. J. Med. Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"107021","DOI":"10.1016\/j.compbiomed.2023.107021","article-title":"Boosting multiple sclerosis lesion segmentation through an attention mechanism","volume":"161","author":"Rondinella","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wahlig, S.G., Nedelec, P., Weiss, D.A., Rudie, J.D., Sugrue, L.P., and Rauschecker, A.M. (2023). 3D U-Net for automated detection of multiple sclerosis lesions: Utility of transfer learning from other pathologies. Front. Neurosci., 17.","DOI":"10.3389\/fnins.2023.1188336"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4102","DOI":"10.1038\/s41598-023-31207-5","article-title":"Multi-arm U-Net with dense input and skip connectivity for T2 lesion segmentation in clinical trials of multiple sclerosis","volume":"13","author":"Krishnan","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zuo, L., Dewey, B.E., Remedios, S.W., Pham, D.L., Carass, A., and Prince, J.L. (2024, January 27\u201330). Towards an accurate and generalizable multiple sclerosis lesion segmentation model using self-ensembled lesion fusion. Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI), Athens, Greece.","DOI":"10.1109\/ISBI56570.2024.10635877"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Grenier, T., and Revol-Muller, C. (2024, January 28\u201331). Comparative analysis of advanced deep learning algorithms for multiple sclerosis lesion segmentation in FLAIR MRI. Proceedings of the IEEE International Conference on Signal Processing (ICSP), Suzhou, China.","DOI":"10.1109\/ICSP62129.2024.10846353"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Pishvai, D.S., Rondinella, A., Guarnera, F., and Battiato, S. (2024, January 3\u20136). Advantages of brain parcellation in multiple sclerosis lesion segmentation. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Lisbon, Portugal.","DOI":"10.1109\/BIBM62325.2024.10822162"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hindawi, S., Szubstarski, B., Boernert, E., Wuerfel, J., and Tackenberg, B. (2025). Federated learning for lesion segmentation in multiple sclerosis: A real-world multi-center feasibility study. Front. Neurol., 16.","DOI":"10.3389\/fneur.2025.1620469"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"106620","DOI":"10.1016\/j.msard.2025.106620","article-title":"Automated multiple sclerosis lesion segmentation from 3D-FLAIR MRI using R2AUNet","volume":"102","author":"Andishgar","year":"2025","journal-title":"Mult. Scler. Relat. Disord."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e70024","DOI":"10.1111\/jon.70024","article-title":"Subject-based transfer learning in longitudinal multiple sclerosis lesion segmentation","volume":"35","author":"Gaj","year":"2025","journal-title":"J. Neuroimaging"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/j.procs.2025.03.229","article-title":"Multiple sclerosis lesion segmentation using MRI: A U-Net approach","volume":"260","author":"Belwal","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"ref_20","unstructured":"Zhang, J., Zuo, L., Dewey, B.E., Remedios, S.W., Liu, Y., Hays, S.P., Pham, D.L., Mowry, E.M., Newsome, S.D., and Calabresi, P.A. (2025). UNISELF: A unified network with instance normalization and self-ensembled lesion fusion for multiple sclerosis lesion segmentation. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.neuroimage.2016.12.064","article-title":"Longitudinal multiple sclerosis lesion segmentation: Resource and challenge","volume":"148","author":"Carass","year":"2017","journal-title":"NeuroImage"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"109347","DOI":"10.1016\/j.patcog.2023.109347","article-title":"A comprehensive survey of image augmentation techniques for deep learning","volume":"137","author":"Xu","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1109\/TMI.2016.2548501","article-title":"Automatic segmentation of MR brain images with a convolutional neural network","volume":"35","author":"Moeskops","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"20508-1\u201320508-11","DOI":"10.2352\/J.ImagingSci.Technol.2020.64.2.020508","article-title":"Medical image segmentation based on U-Net: A review","volume":"64","author":"Du","year":"2020","journal-title":"J. Imaging Sci. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/s42979-021-00782-7","article-title":"DenseNet convolutional neural networks application for predicting COVID-19 using CT images","volume":"2","author":"Hasan","year":"2021","journal-title":"SN Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., and He, K. (2017, January 21\u201326). Aggregated residual transformations for deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"134681","DOI":"10.1016\/j.physd.2025.134681","article-title":"Weighted visibility graph-based deep complex network features: New diagnostic spontaneous speech markers of Alzheimer\u2019s disease","volume":"476","author":"Nasrolahzadeh","year":"2025","journal-title":"Phys. D Nonlinear Phenom."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/s12559-024-10398-7","article-title":"A non-invasive approach for early Alzheimer\u2019s detection through spontaneous speech analysis using deep visibility graphs","volume":"17","author":"Mohammadpoory","year":"2025","journal-title":"Cogn. Comput."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ghonchi, H., Foulsham, T., and Ferdowsi, S. (2024, January 26\u201330). Assessing neural patterns of anxiety using deep learning: An EEG study. Proceedings of the 32nd European Signal Processing Conference (EUSIPCO), Lyon, France.","DOI":"10.23919\/EUSIPCO63174.2024.10715099"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ye, J., Dao, S.D., Wu, Y., George, Y., Nguyen-Duc, T., Schmidt, D.F., Shi, H., Chong, W., and Cai, J. (2025). New multiple sclerosis lesion segmentation via calibrated inter-patch blending. Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2025, Springer. Part XVI.","DOI":"10.1007\/978-3-032-05325-1_35"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/1\/72\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T12:46:58Z","timestamp":1768481218000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/1\/72"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,15]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["a19010072"],"URL":"https:\/\/doi.org\/10.3390\/a19010072","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,15]]}}}