Modified Deep Convolutional Neural Network for Lumbar Spine Degenerative Classification with Improved Multikernel Fuzzy C-Means Segmentation
DOI:
https://doi.org/10.29284/jyt14h85Keywords:
Gaussian Filter, Modified Multi-Kernel Fuzzy C-means algorithm, Improved Gradient Local Ternary Pattern, Modified DCNNAbstract
Nowadays back pain is the most emerging health issue which is affecting the people around the world. The main reasons causing this back pain problem is damage or deterioration of the lower part of the spine , this is referred to as the lumbar spine . The lower spine supports our body weight and helps us to stand, sit or move. As the cases of lumber spine chronic diseases are increasing at a rapid rate , it is highly important to do the correct diagnosis and that too at the correct span of time. Currently, doctors are mainly using MRI scans to diagnose these types of spine related problems , In contrast the diagnosis is followed by manual analysis of the images which takes time and can also generate errors. Doing this manually is not always consistent and also fail in detecting the issues at early stages, which in case plays a important role in proper treatment. To solve the arising problems , the reasear proposes a new deep learning based method which can detect lumber spine degenerative conditions at early stage and also classify them accordingly. This method works in four main steps .The first step includes preprocessing in which the MRI images are analysed and cleaned by the use of Gaussian filter. This step decreases the noice , increasing the overall image quality The next step is segmentation in which all the importance region of image are detached using a technique called Modified Multikernel Fuzzy C-Means (MMKFCM).This step gives better partitioning by using multiple kernels at a time and nearby pixels information.This step is then followed by feature extraction in which after the partitioning,all useful information is taken from image which includes shape, texture and positioning of spine by using methods like monogenic binary coding and improved Gradient Local Ternary Pattern (IGLTeP)The last step is classification in which all the information and features are passed by Modified Deep Convolution Neural Network (MDCNN) which uses advanced technologies like rank based average pooling and HardELiSh activateon with batch normalisation to increase the effectiveness and results in more accurate and reduced computation time. This complete system provides a reliable and efficient way for detection and classification of lumber spine degenerative diseases . In comparison to other existing methods, the proposed model works better , resulting in 93.7% accuracy , 91.1% F-measure and 95.1% specificity. According to the result , this approach is more accurate and effective than other traditional methods
References
[1] Abuhayi, B. M., Bezabh, Y. A., & Ayalew, A. M. (2024). Lumbar disease classification using an Involutional neural based VGG Nets (INVGG). IEEE Access.
[2] Tumko, V., Kim, J., Uspenskaia, N., Honig, S., Abel, F., Lebl, D. R., ... & Mourad, R. (2024). A neural network model for detection and classification of lumbar spinal stenosis on MRI. European Spine Journal, 33(3), 941-948.
[3] Masood, R. F., Taj, I. A., Khan, M. B., Qureshi, M. A., & Hassan, T. (2022). Deep learning-based vertebral body segmentation with the extraction of spinal measurements and disorder disease classification. Biomedical Signal Processing and Control, 71, 103230.
[4] Yagi, M., Michikawa, T., Yamamoto, T., Iga, T., Ogura, Y., Tachibana, A., ... & Keio Spine Research Group. (2022). Development and validation of machine learning-based predictive model for clinical outcome of decompression surgery for lumbar spinal canal stenosis. The Spine Journal, 22(11), 1768-1777.
[5] Gao, K. T., Tibrewala, R., Hess, M., Bharadwaj, U. U., Inamdar, G., Link, T. M., ... & Majumdar, S. (2022). Automatic detection and voxel‐wise mapping of lumbar spine Modic changes with deep learning. JOR spine, 5(2), e1204.
[6] Saravi, B., Zink, A., Ülkümen, S., Couillard-Despres, S., Hassel, F., & Lang, G. (2022). Performance of artificial intelligence-based algorithms to predict prolonged length of stay after lumbar decompression surgery. Journal of Clinical Medicine, 11(14), 4050.
[7] Bharadwaj, U. U., Christine, M., Li, S., Chou, D., Pedoia, V., Link, T. M., ... & Majumdar, S. (2023). Deep learning for automated, interpretable classification of lumbar spinal stenosis and facet arthropathy from axial MRI. European radiology, 33(5), 3435-3443.
[8] Natalia, F., Young, J. C., Afriliana, N., Meidia, H., Yunus, R. E., & Sudirman, S. (2022). Automated selection of mid-height intervertebral disc slice in traverse lumbar spine MRI using a combination of deep learning feature and machine learning classifier. PLoS One, 17(1), e0261659.
[9] Kim, T., Kim, Y. G., Park, S., Lee, J. K., Lee, C. H., Hyun, S. J., ... & Chung, C. K. (2022). Diagnostic triage in patients with central lumbar spinal stenosis using a deep learning system of radiographs. Journal of Neurosurgery: Spine, 37(1), 104-111.
[10] Soydan, Z., Bayramoglu, E., Karasu, R., Sayin, I., Salturk, S., & Uvet, H. (2023). An automatized deep segmentation and classification model for lumbar disk degeneration and clarification of its impact on clinical decisions. Global Spine Journal, 21925682231200783.
[11] Zheng, H. D., Sun, Y. L., Kong, D. W., Yin, M. C., Chen, J., Lin, Y. P., ... & Wang, Y. J. (2022). Deep learning-based high-accuracy quantitation for lumbar intervertebral disc degeneration from MRI. Nature communications, 13(1), 841.
[12] Dong, S., Zhu, Y., Yang, H., Tang, N., Huang, G., Li, J., & Tian, K. (2022). Evaluation of the predictors for unfavorable clinical outcomes of degenerative lumbar spondylolisthesis after lumbar Interbody fusion using machine learning. Frontiers in Public Health, 10, 835938.
[13] Shinde, J. V., Joshi, Y. V., & Manthalkar, R. R. (2022). Multidomain feature level fusion for classification of lumbar intervertebral disc using spine MR images. IETE Journal of Research, 68(6), 4346-4359.
[14] Baur, D., Bieck, R., Berger, J., Neumann, J., Henkelmann, J., Neumuth, T., ... & Voelker, A. (2022). Analysis of the paraspinal muscle morphology of the lumbar spine using a convolutional neural network (CNN). European Spine Journal, 1-9.
[15] Liu, D., Zhang, D., Sun, Z., Zhou, S., Li, W., Li, C., ... & Wang, Z. L. (2022). Active‐matrix sensing array assisted with machine‐learning approach for lumbar degenerative disease diagnosis and postoperative assessment. Advanced Functional Materials, 32(21), 2113008.
[16] André, A., Peyrou, B., Carpentier, A., & Vignaux, J. J. (2022). Feasibility and assessment of a machine learning-based predictive model of outcome after lumbar decompression surgery. Global Spine Journal, 12(5), 894-908.
[17] Chiu, P. F., Chang, R. C. H., Lai, Y. C., Wu, K. C., Wang, K. P., Chiu, Y. P., ... & Chiu, C. D. (2023). Machine learning assisting the prediction of clinical outcomes following Nucleoplasty for lumbar degenerative disc disease. Diagnostics, 13(11), 1863.
[18] Chen, Y., Huang, Q., Zhang, C., Li, J., Huang, W., Luo, P., & Diao, X. (2025). Deep learning-based computer-aided diagnostic system for lumbar degenerative diseases classification using MRI. Biomedical Signal Processing and Control, 109, 108002.
[19] Liawrungrueang, W., Kim, P., Kotheeranurak, V., Jitpakdee, K., & Sarasombath, P. (2023). Automatic detection, classification, and grading of lumbar intervertebral disc degeneration using an artificial neural network model. Diagnostics, 13(4), 663.
[20] Singh, D., Singla, J., Rahmani, M. K. I., Ahmad, S., Rehman, M. U., Jha, S., ... & Nazeer, J. (2023). Lumbar spine disease detection: enhanced CNN model with improved classification accuracy. IEEE Access, 11, 141889-141901.
[21] Abbas, J., Yousef, M., Peled, N., Hershkovitz, I., & Hamoud, K. (2023). Predictive factors for degenerative lumbar spinal stenosis: a model obtained from a machine learning algorithm technique. BMC Musculoskeletal Disorders, 24(1), 218.
[22] Zhang, W., Chen, Z., Su, Z., Wang, Z., Hai, J., Huang, C., ... & Lu, H. (2023). Deep learning‐based detection and classification of lumbar disc herniation on magnetic resonance images. JOR spine, 6(3), e1276.
[23] Yi, W., Zhao, J., Tang, W., Yin, H., Yu, L., Wang, Y., & Tian, W. (2023). Deep learning-based high-accuracy detection for lumbar and cervical degenerative disease on T2-weighted MR images. European Spine Journal, 32(11), 3807-3814.
[24] Hou, C., Li, X., Wang, H., Zhang, W., Liu, F., Liu, D., & Pan, Y. (2023). An MRI image automatic diagnosis model for lumbar disc herniation using semi-supervised learning. Complex & Intelligent Systems, 9(5), 5567-5584.
[25] Staartjes, V. E., Klukowska, A. M., Stumpo, V., Vandertop, W. P., & Schröder, M. L. (2024). Identifying clusters of objective functional impairment in patients with degenerative lumbar spinal disease using unsupervised learning. European Spine Journal, 33(4), 1320-1331.
[26] Chen, K., Zheng, L., Zhao, H., & Wang, Z. (2024). Deep Learning-Based Intelligent Diagnosis of Lumbar Diseases with Multi-Angle View of Intervertebral Disc. Mathematics, 12(13), 2062.
[27] Mbarki, W., Bouchouicha, M., Frizzi, S., Tshibasu, F., Farhat, L. B., & Sayadi, M. (2020). Lumbar spine discs classification based on deep convolutional neural networks using axial view MRI. Interdisciplinary Neurosurgery, 22, 100837.
[28] Yi, W., Zhao, J., Tang, W., Yin, H., Yu, L., Wang, Y., & Tian, W. (2023). Deep learning-based high-accuracy detection for lumbar and cervical degenerative disease on T2-weighted MR images. European Spine Journal, 32(11), 3807-3814.
[29] Abuhayi, B. M., Bezabh, Y. A., & Ayalew, A. M. (2024). Lumbar disease classification using an Involutional neural based VGG Nets (INVGG). IEEE Access, 12, 27518-27529.
[30] Dastgir, A., Bin, W., Saeed, M. U., Sheng, J., & Saleem, S. (2025). MAFMv3: An automated Multi-Scale Attention-Based Feature Fusion MobileNetv3 for spine lesion classification. Image and Vision Computing, 105440.
[31] Kusrini, K., Yudianto, M. R. A., & Al Fatta, H. (2022). The effect of Gaussian filter and data preprocessing on the classification of Punakawan puppet images with the convolutional neural network algorithm. International Journal of Electrical and Computer Engineering, 12(4), 3752.
[32] Sikka, K., Sinha, N., Singh, P. K., & Mishra, A. K. (2009). A fully automated algorithm under modified FCM framework for improved brain MR image segmentation. Magnetic Resonance Imaging, 27(7), 994-1004.
[33] Ding, Y., & Fu, X. (2016). Kernel-based fuzzy c-means clustering algorithm based on genetic algorithm. Neurocomputing, 188, 233-238.
[34] Muthumari, A., Banumathi, J., Rajasekaran, S., Vijayakarthik, P., Shankar, K., Pustokhina, I. V., & Pustokhin, D. A. (2021). High Security for De-Duplicated Big Data Using Optimal SIMON Cipher. Computers, Materials & Continua, 67(2).
[35] El Khatib, O., & Alkhatib, N. A Comprehensive Overview of Kernels in Machine Learning: Mathematical Foundations and Applications. International Journal of Computer (IJC), 53(1), 150-172.
[36] Rao, T., & Kumar, D. K. S. (2019, February). Retinal disease detection and classification using improved lbp technique. In Proceedings of International Conference on Sustainable Computing in Science, Technology and Management (SUSCOM), Amity University Rajasthan, Jaipur-India.
[37] Bavkar, D. M., Kashyap, R., & Khairnar, V. (2022). Multimodal sarcasm detection via hybrid classifier with optimistic logic. Journal of Telecommunications and Information Technology, (3), 97-114.
[38] Chen, Z. (2019). Facial Expression Recognition Based on Local Features and Monogenic Binary Coding. Informatica, 43(1).
[39] Liu, J., & Shi, Y. (2011). Image feature extraction method based on shape characteristics and its application in medical image analysis. In Applied Informatics and Communication: International Conference, ICAIC 2011, Xi’an, China, August 20-21, 2011, Proceedings, Part I (pp. 172-178). Springer Berlin Heidelberg.
[40] Khan, Z. N., & Ahmad, J. (2021). Attention-induced multi-head convolutional neural network for human activity recognition. Applied soft computing, 110, 107671.
[41] Gholamalinezhad, H., & Khosravi, H. (2020). Pooling methods in deep neural networks, a review. arXiv preprint arXiv:2009.07485.
[42] Nwankpa, C., Ijomah, W., Gachagan, A., & Marshall, S. (2018). Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378.
[43] Ioffe, S., & Szegedy, C. (2015, June). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (pp. 448-456). pmlr.
[44] https://www.kaggle.com/competitions/rsna-2024-lumbar-spine-degenerative-classification
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
