{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:17:15Z","timestamp":1785428235744,"version":"3.56.0"},"reference-count":40,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Stryker Inc."},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"crossref","award":["RGPIN-2019-06407"],"award-info":[{"award-number":["RGPIN-2019-06407"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"crossref"}]},{"award":["RGPIN-2019-06407"],"award-info":[{"award-number":["RGPIN-2019-06407"]}],"id":[{"id":"https:\/\/ror.org\/01h531d29","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Accurate spinal cord segmentation is important for quantitative analysis of spinal cord magnetic resonance imaging, including measurement of cross-sectional area and diffusion-based microstructural characterization. In pathological conditions like cervical myelopathy, the shape deformation induced by cord compression is extreme, rendering automated segmentation particularly challenging. While deep learning-based methods yield good results in healthy or mildly pathological cases, their reliability suffers when anatomical assumptions fail under compression. In this work, we introduce a pathology-aware, boundary-focused preprocessing framework that directly aims to mitigate failure modes imposed by cord compression. Instead of generic preprocessing, each component aims to enhance intensity homogeneity, suppress noise and improve boundary visibility. At the core of this approach is a multi-representation input derived from a single T2*-weighted scan, whereby complementary intensity-, contrast- and edge-enhanced representations are fed to the U-Net model. The proposed framework is evaluated on spinal cord MRI data from three clinical centers (194 cervical myelopathy cases). The results demonstrate that the proposed preprocessing framework improves segmentation accuracy, robustness, and stability, particularly in anatomically challenging regions affected by compression. These findings highlight the importance of pathology-aware preprocessing for reliable spinal cord segmentation in cervical myelopathy.<\/jats:p>","DOI":"10.3390\/jimaging12070323","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T06:09:09Z","timestamp":1784527749000},"page":"323","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Magnetic Resonance Imaging Preprocessing for Robust Spinal Cord Segmentation in Cervical Myelopathy"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5341-8281","authenticated-orcid":false,"given":"Hediyeh","family":"Toufani","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, University of Ottawa, Ottawa, ON K1N 1A2, Canada"},{"name":"Neuroscience Program, Ottawa Hospital Research Institute, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3512-3647","authenticated-orcid":false,"given":"Richard M.","family":"Dansereau","sequence":"additional","affiliation":[{"name":"Department of Systems and Computer Engineering, Carleton University, Ottawa, ON K1S 5B6, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philippe","family":"Phan","sequence":"additional","affiliation":[{"name":"Division of Orthopedics, Department of Surgery, Faculty of Medicine, University of Ottawa, Ottawa, ON K1H 8M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jefferson R.","family":"Wilson","sequence":"additional","affiliation":[{"name":"Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, ON M5S 1A1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eve C.","family":"Tsai","sequence":"additional","affiliation":[{"name":"Neuroscience Program, Ottawa Hospital Research Institute, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada"},{"name":"Division of Neurosurgery, Department of Surgery, Faculty of Medicine, University of Ottawa, Ottawa, ON K1H 8M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1007\/s00234-021-02635-9","article-title":"Spatial Correspondence of Spinal Cord White Matter Tracts Using Diffusion Tensor Imaging, Fibre Tractography, and Atlas-Based Segmentation","volume":"63","author":"McLachlin","year":"2021","journal-title":"Neuroradiology"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1093\/brain\/119.3.701","article-title":"Spinal Cord Atrophy and Disability in Multiple Sclerosis: A New Reproducible and Sensitive MRI Method with Potential to Monitor Disease Progression","volume":"119","author":"Losseff","year":"1996","journal-title":"Brain"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"319","DOI":"10.3174\/ajnr.A0813","article-title":"Comparison of Three Different Methods for Measurement of Cervical Cord Atrophy in Multiple Sclerosis","volume":"29","author":"Zivadinov","year":"2008","journal-title":"Am. J. Neuroradiol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1176","DOI":"10.1002\/mrm.10162","article-title":"Quantification of Spinal Cord Atrophy from Magnetic Resonance Images via a B-Spline Active Surface Model","volume":"47","author":"Coulon","year":"2002","journal-title":"Magn. Reson. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.neuroimage.2009.12.121","article-title":"Rapid Semi-Automatic Segmentation of the Spinal Cord from Magnetic Resonance Images: Application in Multiple Sclerosis","volume":"50","author":"Horsfield","year":"2010","journal-title":"Neuroimage"},{"key":"ref_6","unstructured":"Koh, J., Kim, T., Chaudhary, V., and Dhillon, G. (2010). Automatic Segmentation of the Spinal Cord and the Dural Sac in Lumbar MR Images Using Gradient Vector Flow Field. Proceedings of the 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC\u201910, IEEE."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1016\/j.neuroimage.2014.04.051","article-title":"Robust, Accurate and Fast Automatic Segmentation of the Spinal Cord","volume":"98","author":"Kadoury","year":"2014","journal-title":"Neuroimage"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"El Mendili, M.-M., Chen, R., Tiret, B., Villard, N., Trunet, S., P\u00e9l\u00e9grini-Issac, M., Leh\u00e9ricy, S., Pradat, P.-F., and Benali, H. (2015). Fast and Accurate Semi-Automated Segmentation Method of Spinal Cord MR Images at 3T Applied to the Construction of a Cervical Spinal Cord Template. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0122224"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1016\/j.neuroimage.2013.07.060","article-title":"Automatic Magnetic Resonance Spinal Cord Segmentation with Topology Constraints for Variable Fields of View","volume":"83","author":"Chen","year":"2013","journal-title":"Neuroimage"},{"key":"ref_10","first-page":"737","article-title":"Convolutional Neural Network\u2013Based Automated Segmentation of the Spinal Cord and Contusion Injury: Deep Learning Biomarker Correlates of Motor Impairment in Acute Spinal Cord Injury","volume":"40","author":"McCoy","year":"2019","journal-title":"Am. J. Neuroradiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5966","DOI":"10.1038\/s41598-018-24304-3","article-title":"Spinal Cord Gray Matter Segmentation Using Deep Dilated Convolutions","volume":"8","author":"Perone","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.mri.2019.04.009","article-title":"Open-Source Pipeline for Multi-Class Segmentation of the Spinal Cord with Deep Learning","volume":"64","author":"Paugam","year":"2019","journal-title":"Magn. Reson. Imaging"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.neuroimage.2016.10.009","article-title":"SCT: Spinal Cord Toolbox, an Open-Source Software for Processing Spinal Cord MRI Data","volume":"145","author":"Dupont","year":"2017","journal-title":"Neuroimage"},{"key":"ref_14","first-page":"1","article-title":"SCIseg: Automatic Segmentation of Intramedullary Lesions in Spinal Cord Injury on T2-Weighted MRI Scans","volume":"7","author":"Karthik","year":"2024","journal-title":"Radiol. Artif. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","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":"Phys. Medica"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1016\/j.media.2014.01.003","article-title":"Groupwise Multi-Atlas Segmentation of the Spinal Cord\u2019s Internal Structure","volume":"18","author":"Asman","year":"2014","journal-title":"Med. Image Anal."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1053\/j.sult.2016.05.007","article-title":"Imaging of Spinal Cord Injury: Acute Cervical Spinal Cord Injury, Cervical Spondylotic Myelopathy, and Cord Herniation","volume":"37","author":"Talekar","year":"2016","journal-title":"Semin. Ultrasound CT MRI"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s11548-022-02783-0","article-title":"Magnetic Resonance Image Segmentation of the Compressed Spinal Cord in Patients with Degenerative Cervical Myelopathy Using Convolutional Neural Networks","volume":"18","author":"Nozawa","year":"2022","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1016\/j.neuroimage.2018.09.081","article-title":"Automatic Segmentation of the Spinal Cord and Intramedullary Multiple Sclerosis Lesions with Convolutional Neural Networks","volume":"184","author":"Gros","year":"2019","journal-title":"Neuroimage"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1007\/s40009-023-01372-2","article-title":"Impact of the Preprocessing Steps in Deep Learning-Based Image Classifications","volume":"47","author":"Koresh","year":"2024","journal-title":"Natl. Acad. Sci. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"104211","DOI":"10.1016\/j.bas.2025.104211","article-title":"Cerebrospinal Fluid Pressure Dynamics as a Biomechanical Marker for Quantification of Spinal Cord Compression: Conceptual Framework and Systematic Review of Clinical Trials","volume":"5","author":"Kheram","year":"2025","journal-title":"Brain Spine"},{"key":"ref_22","first-page":"20200133","article-title":"MRI Findings in Cervical Spondylotic Myelopathy with Gadolinium Enhancement: Review of Seven Cases","volume":"7","author":"Ferreira","year":"2021","journal-title":"BJR Case Rep."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hallinan, J.T.P.D., Zhu, L., Zhang, W., Lim, D.S.W., Baskar, S., Low, X.Z., Yeong, K.Y., Teo, E.C., Kumarakulasinghe, N.B., and Yap, Q.V. (2022). Deep Learning Model for Classifying Metastatic Epidural Spinal Cord Compression on MRI. Front. Oncol., 12.","DOI":"10.3389\/fonc.2022.849447"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.3174\/ajnr.A7221","article-title":"Atlas-Based Quantification of DTI Measures in a Typically Developing Pediatric Spinal Cord","volume":"42","author":"Shahrampour","year":"2021","journal-title":"Am. J. Neuroradiol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1302\/0301-620X.71B3.2722928","article-title":"The Prognosis of Surgery for Cervical Compression Myelopathy. An Analysis of the Factors Involved","volume":"71","author":"Fujiwara","year":"1989","journal-title":"J. Bone Jt. Surg.-Ser. B"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"119868","DOI":"10.1016\/j.neuroimage.2023.119868","article-title":"Improving T2*-Weighted Human Cortico-Spinal Acquisitions with a Dedicated Algorithm for Region-Wise Shimming","volume":"268","author":"Chu","year":"2023","journal-title":"Neuroimage"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1007\/s00234-023-03187-w","article-title":"Automated Signal Intensity Analysis of the Spinal Cord for Detection of Degenerative Cervical Myelopathy\u2014A Matched-Pair MRI Study","volume":"65","author":"Hohenhaus","year":"2023","journal-title":"Neuroradiology"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1007\/s10278-022-00721-9","article-title":"Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging\u2014State-of-the-Art and Challenges","volume":"36","author":"Chen","year":"2022","journal-title":"J. Digit. Imaging"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: Improved N3 Bias Correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/s11045-021-00802-y","article-title":"Two-Step Non-Local Means Method for Image Denoising","volume":"33","author":"Zhang","year":"2021","journal-title":"Multidimens. Syst. Signal Process."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1186\/s12938-024-01280-6","article-title":"Deep Learning for the Harmonization of Structural MRI Scans: A Survey","volume":"23","author":"Abbasi","year":"2024","journal-title":"Biomed. Eng. OnLine"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Fei, N., Gao, Y., Lu, Z., and Xiang, T. (2022). Z-Score Normalization, Hubness, and Few-Shot Learning. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 10\u201317 October 2021, IEEE.","DOI":"10.1109\/ICCV48922.2021.00021"},{"key":"ref_33","first-page":"20","article-title":"Normalization: A Preprocessing Stage","volume":"2","author":"Gopal","year":"2015","journal-title":"IARJSET"},{"key":"ref_34","first-page":"2782","article-title":"Impact of Signal Intensity Normalization of MRI on the Generalizability of Radiomic-Based Prediction of Molecular Glioma Subtypes","volume":"34","author":"Schell","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"105407","DOI":"10.1016\/j.imavis.2024.105407","article-title":"Cross-Set Data Augmentation for Semi-Supervised Medical Image Segmentation","volume":"154","author":"Wu","year":"2025","journal-title":"Image Vis. Comput."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zuiderveld, K. (1994). Contrast Limited Adaptive Histogram Equalization. Graphics Gems IV, Academic Press. Available online: https:\/\/dl.acm.org\/doi\/abs\/10.5555\/180895.180940.","DOI":"10.1016\/B978-0-12-336156-1.50061-6"},{"key":"ref_37","first-page":"96","article-title":"A Comparison Study of Image Edge Segmentation Methods Using Prewitt, Sobel and Laplacian of Gaussian for Medical Images","volume":"12","author":"Naseir","year":"2022","journal-title":"J. Educ. Pure Sci."},{"key":"ref_38","unstructured":"Cardoso, M.J., Li, W., Brown, R., Ma, N., Kerfoot, E., Wang, Y., Murrey, B., Myronenko, A., Zhao, C., and Yang, D. (2022). MONAI: An Open-Source Framework for Deep Learning in Healthcare. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"5129","DOI":"10.1364\/BOE.9.005129","article-title":"Speckle Noise Reduction in Optical Coherence Tomography Images Based on Edge-Sensitive CGAN","volume":"9","author":"Ma","year":"2018","journal-title":"Biomed. Opt. Express"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"58","DOI":"10.2174\/1573405612666160609131149","article-title":"An Edge Preservation Index for Evaluating Nonlinear Spatial Restoration in MR Images","volume":"13","author":"Joseph","year":"2016","journal-title":"Curr. Med. Imaging Rev."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/7\/323\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:22:21Z","timestamp":1784607741000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/7\/323"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"references-count":40,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["jimaging12070323"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12070323","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]}}}