Deep Learning-Based Lumbar Spinal Canal Stenosis Classification Using MRI Scans

Main Article Content

Guillermo Garcia de Celis Wisam Bukaita, Ph.D1

Abstract

Spinal Canal Stenosis is a prevalent condition that occurs as the spaces within the spinal canal gradually narrow over time due to degenerative changes in the ligaments, joints, and bones. This can lead to chronic pain, stiffness, and limited movement, significantly affecting a person's daily activities and overall well-being. Traditional methods for classifying Spinal Canal Stenosis can be slow and prone to errors. To address these challenges, this study proposes a deep learning-based approach utilizing Convolutional Neural Networks (CNNs) to classify Spinal Canal Stenosis into three severity levels: Normal/Mild, Moderate, and Severe. Using the RSNA 2024 Lumbar Spine Degenerative Classification Challenge dataset, which consists of a set of different types of Lumbar MRIs, axial T2, Sagittal T1, and Sagittal T2/STIR. For this study, we decided to use axial T2-weighted MRI scans. We implemented a series of preprocessing techniques including DICOM-to-PNG conversion, K-Means clustering for slice selection, and data augmentation to address class imbalance. The CNN model, designed with five convolutional blocks and enhanced with batch normalization, dropout regularization, and an early stopping mechanism, achieved an overall classification of 89% with a high recall of 97% for the Severe category. These findings indicate that deep learning models can substantially enhance the accuracy and efficiency of diagnosing lumbar spinal canal stenosis and other degenerative spine conditions, offering valuable support to radiologists. Also, we will explore the integration of Vision Transformers (ViTs) and multimodal learning techniques to further enhance the model’s performance and clinical applicability.

Article Details

How to Cite
GARCIA DE CELIS, Guillermo; BUKAITA, Wisam. Deep Learning-Based Lumbar Spinal Canal Stenosis Classification Using MRI Scans. Medical Research Archives, [S.l.], v. 13, n. 7, july 2025. ISSN 2375-1924. Available at: <https://esmed.org/MRA/mra/article/view/6660>. Date accessed: 06 dec. 2025. doi: https://doi.org/10.18103/mra.v13i7.6660.
Section
Research Articles

References

Buda, Mateusz, Atsuto Maki, and Maciej A. Mazurowski. 2018. "A systematic study of the class imbalance problem in convolutional neural networks." Neural Networks 106: 249–259.
https://doi.org/10.1016/j.neunet.2018.07.011

Chmelik, Jiri, Roman Jakubicek, Petr Walek, Jiri Jan, Petr Ourednicek, Lukas Lambert, Elena Amadori, and Giampaolo Gavelli. 2018. "Deep convolutional neural network-based segmentation and classification of difficult to define metastatic spinal lesions in 3D CT data." Medical Image Analysis 49: 76–88.
https://doi.org/10.1016/j.media.2018.07.008

Farooq, Muhammad, and Abdul Hafeez. 2020. "Covid-ResNet: A deep learning framework for screening of COVID-19 from radiographs." arXiv preprint arXiv:2003.14395.

Li, Hao, Gopi Krishnan Rajbahadur, Dayi Lin, Cor-Paul Bezemer, and Zhen Ming Jiang. 2024. "Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting." IEEE Access 12: 70676–70689.
https://doi.org/10.1109/ACCESS.2024.3402543

Lim, Desmond Shi, Andrew Makmur, Lei Zhu, Wenqiao Zhang, Amanda J. Cheng, David Soon Sia, Sterling Ellis Eide, et al. 2022. "Improved productivity using deep learning–assisted reporting for lumbar spine MRI." Radiology 305 (1): 160–66. https://doi.org/10.1148/radiol.220076

Munadi, Khairul, Kahlil Muchtar, Novi Maulina, and Biswajeet Pradhan. 2020. "Image enhancement for tuberculosis detection using deep learning." IEEE Access 8: 217897–907.
https://doi.org/10.1109/ACCESS.2020.3041867

Neubert, A., J. Fripp, C. Engstrom, R. Schwarz, L. Lauer, O. Salvado, and S. Crozier. 2012. "Automated detection, 3D segmentation and analysis of high resolution spine MR images using statistical shape models." Physics in Medicine and Biology 57 (24): 8357–76. https://doi.org/10.1088/0031-9155/57/24/8357

Ng, H.P., S.H. Ong, K.W.C. Foong, P.S. Goh, and W.L. Nowinski. 2006. "Medical Image Segmentation Using K-Means Clustering and Improved Watershed Algorithm." In Proceedings of the IEEE International Conference on Image Processing, 611-614. https://doi.org/10.1109/ICIP.2006.312517

Özkaraca, Osman, Okan İhsan Bağrıaçık, Hüseyin Gürüler, Faheem Khan, Jamil Hussain, Jawad Khan, and Umm e Laila. 2023. "Multiple brain tumor classification with dense CNN architecture using brain MRI images." Life 13 (2): 349. https://doi.org/10.3390/life13020349

Processing of MR images for efficient quantitative image analysis using deep learning techniques." In Proceedings of the 2017 International Conference on Recent Advances in Electronics and Communication Technology (ICRAECT), 191–95. https://doi.org/10.1109/icraect.2017.43

Ruiz-España, Silvia, Estanislao Arana, and David Moratal. 2015. "Semiautomatic computer-aided classification of degenerative lumbar spine disease in magnetic resonance imaging." Computers in Biology and Medicine 62: 196–205. https://doi.org/10.1016/j.compbiomed.2015.04.028

Scannell, Cian M., Mitko Veta, Adriana D.M. Villa, Eva C. Sammut, Jack Lee, Marcel Breeuwer, and Amedeo Chiribiri. 2020. "Deep-Learning-Based Preprocessing for Quantitative Myocardial Perfusion MRI." Journal of Magnetic Resonance Imaging 51: 1689–1696. https://doi.org/10.1002/jmri.26983

Seo, Hyunseok, Lequan Yu, Hongyi Ren, Xiaomeng Li, Liyue Shen, and Lei Xing. 2021. "Deep neural network with consistency regularization of multi-output channels for improved tumor detection and delineation." IEEE Transactions on Medical Imaging 40 (12): 3369–78. https://doi.org/10.1109/tmi.2021.3084748

Villmann, Thomas, Marika Kaden, Mandy Lange, and Paul Stürmer. 2014. "Precision-Recall-Optimization in Learning Vector Quantization Classifiers for Improved Medical Classification Systems." In Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN), 195–202. https://doi.org/10.1109/IJCNN.2014.6889664

Suzuki, Hisataka, Terufumi Kokabu, Katsuhisa Yamada, Yoko Ishikawa, Akito Yabu, Yasushi Yanagihashi, Takahiko Hyakumachi, et al. 2024. “Deep Learning-Based Detection of Lumbar Spinal Canal Stenosis Using Convolutional Neural Networks.” The Spine Journal 24 (11): 2086–2101. https://doi.org/10.1016/j.spinee.2024.06.009.

Zhou, Zhiyi, Shenjun Wang, Shujun Zhang, Xiang Pan, Haoxia Yang, Yin Zhuang, and Zhengfeng Lu. 2024. “Deep Learning-Based Spinal Canal Segmentation of Computed Tomography Image for Disease Diagnosis: A Proposed System for Spinal Stenosis Diagnosis.” Medicine 103 (18): e37943. https://doi.org/10.1097/MD.0000000000037943.

Yoo, Hyunsuk, Roh-Eul Yoo, Seung Hong Choi, Inpyeong Hwang, Ji Ye Lee, June Young Seo, Seok Young Koh, Kyu Sung Choi, Koung Mi Kang, and Tae Jin Yun. 2023. “Deep Learning-Based Reconstruction for Acceleration of Lumbar Spine MRI: A Prospective Comparison with Standard MRI.” European Radiology 33 (12): 8656–68.
https://doi.org/10.1007/s00330-023-09918-0.

Jeon, Yejin, Bo Ram Kim, Hyoung In Choi, Eugene Lee, Da-Wit Kim, Boorym Choi, and Joon Woo Lee. 2025. “Feasibility of Deep Learning Algorithm in Diagnosing Lumbar Central Canal Stenosis Using Abdominal CT.” Skeletal Radiology 54 (5): 947–57. https://doi.org/10.1007/s00256-024-04796-z.

Hokamura, Masamichi, Takeshi Nakaura, Naofumi Yoshida, Hiroyuki Uetani, Kaori Shiraishi, Naoki Kobayashi, Kensei Matsuo, et al. 2024. “Super-Resolution Deep Learning Reconstruction Approach for Enhanced Visualization in Lumbar Spine MR Bone Imaging.” European Journal of Radiology 178. https://doi.org/10.1016/j.ejrad.2024.111587.