Abstract
Spinal cord magnetic resonance images (MRIs) consists of 7 levels of cervical vertebrae, 12 levels of thoracic vertebrae, 5 levels of lumbar vertebrae, one level each of sacrum and coccyx components. Segmentation of these components is essential for effective classification and post-processing analysis of spinal cord images. In order to perform this task, separate algorithms are needed for each of the components. Due to which, their segmentation performance is not uniform, which limits their integration capabilities. Moreover, performance for each type of segmentation has scalability issues, which must be improved via augmentation, aggregation, and machine learning for better clinical use. To resolve these issues, this text proposes design of a novel spinal cord image segmentation model using transfer learning inspired mask region-based augmented convolutional neural network (MRACNN). The proposed model utilizes initial weights from the pre-trained COCO mask RCNN model, and modifies them to incorporate spine, torso, and \({\text{L}}_{1}\) to \({\text{L}}_{5}\) spinal cord components. When compared to several state-of-the-art models, it is found that the suggested model has improved region of interest (RoI) extraction and an accuracy of 91% for segmenting these components. Moreover, the proposed model was evaluated on multiple datasets, and a consistent performance was observed. Furthermore, the model was fused with a XRAI-based convolutional neural network which assisted in further improving overall efficiency of segmentation. Fusion of XRAI CNN with MRACNN is capable of achieving segmentation accuracy of 94%, along with better RoI performance when compared with individual models. Delay requirement of the fused model is high, and requires large dataset for training & validation, thus, this text also recommends selective ensembling techniques for redundancy reduction, which assists in improving segmentation speed, while maintaining high segmentation quality.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Garg S, Bhagyashree SR (2019) Detection and classification of tumors using medical imaging techniques: a survey. In: Balaji S, Rocha Á, Chung YN (eds) Intelligent communication technologies, and virtual mobile networks. ICICV 2019. Lecture notes on data engineering and communications technologies, vol 33
Garg S, Bhagyashree SR (2021) Spinal cord MRI segmentation techniques, and algorithms: a survey. SN Comput Sci 2:229
Sabaghian S, Dehghani H, Batouli SA, Khatibi A, Oghabian M (2020) Fully automatic 3D segmentation of the thoracolumbar spinal cord and the vertebral canal from T2-weighted MRI using K-means clustering algorithm. Spinal Cord 58:1–10. https://doi.org/10.1038/s41393-020-0429-3
Chen M, Carass A, Oh J et al (2013) Automatic magnetic resonance spinal cord segmentation with topology constraints for variable fields of view. Neuroimage 83:1051–1062. https://doi.org/10.1016/j.neuroimage.2013.07.060
Chun-Chih Liao, Hsien-Wei Ting, Furen Xiao (2017) Atlas-free cervical spinal cord segmentation on midsagittal T2-weighted magnetic resonance images. J Healthc Eng 2017:12, Article ID 8691505. https://doi.org/10.1155/2017/8691505
Gros C, De Leener B, Badji A, Maranzano J, Eden D, Dupont S, Talbott J, Zhuoquiong R, Liu Y, Granberg T, Ouellette R, Tachibana Y, Hori M, Kamiya K, Chougar L, Stawiarz L, Hillert J, Bannier E, Kerbrat A, Cohen-Adad J (2018) Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks
Ahammad SH, Ur Rahman MZ, Lay-Ekuakille A, Giannoccaro NI (2020) An efficient optimal threshold-based segmentation and classification model for multi-level spinal cord injury detection. 2020 IEEE international symposium on medical measurements and applications (MeMeA), pp 1–6. https://doi.org/10.1109/MeMeA49120.2020.9137122
Saenz-Gamboa JJ, de la Iglesia-Vayá M, Gómez JA (2021) Automatic semantic segmentation of structural elements related to the spinal cord in the lumbar region by using convolutional neural networks. 2020 25th international conference on pattern recognition (ICPR), pp 5214–5221. https://doi.org/10.1109/ICPR48806.2021.9412934
Mnassri B, Sahnoun M, Hamida AB (2020) Comparison study for spinal cord segmentation methods aiming to detect SC atrophy in MRI images: case of multiple sclerosis. 2020 5th international conference on advanced technologies for signal and image processing (ATSIP), pp 1–6. https://doi.org/10.1109/ATSIP49331.2020.9231790
Ahammad SH, Rajesh V, Rahman MZU, Lay-Ekuakille A (2020) A hybrid CNN-based segmentation and boosting classifier for real time sensor spinal cord injury data. IEEE Sens J 20(17):10092–10101. https://doi.org/10.1109/JSEN.2020.2992879
Lemay A, Gros C, Zhuo Z et al (2021) Automatic multiclass intramedullary spinal cord tumor segmentation on MRI with deep learning. Neuroimage Clin 31:102766. https://doi.org/10.1016/j.nicl.2021.102766
Yiannakas MC, Liechti MD, Budtarad N et al (2019) Gray versus white matter segmentation of the conus medullaris: reliability and variability in healthy volunteers. J Neuroimaging 29(3):410–417. https://doi.org/10.1111/jon.12591
Couedic TL, Caillon R, Rossant F, Joutel A, Urien H, Rajani RM (2020) Deep-learning based segmentation of challenging myelin sheaths. 2020 tenth international conference on image processing theory, tools and applications (IPTA), pp 1–6. https://doi.org/10.1109/IPTA50016.2020.9286715
Alsiddiky A, Fouad H, Soliman AM, Altinawi A, Mahmoud NM (2020) Vertebral tumor detection and segmentation using analytical transform assisted statistical characteristic decomposition model. IEEE Access 8:145278–145289. https://doi.org/10.1109/ACCESS.2020.3012719
Moccia M, Prados F, Filippi M, Rocca MA, Valsasina P, Brownlee WJ, Zecca C, Gallo A, Rovira A, Gass A, Palace J, Lukas C, Vrenken H, Ourselin S, Gandini Wheeler-Kingshott CAM, Ciccarelli O, Barkhof F (2019) Longitudinal spinal cord atrophy in multiple sclerosis using the generalized boundary shift integral. Ann Neurol 86:704–713. https://doi.org/10.1002/ana.25571
Ma S, Huang Y, Che X, Gu R (2020) Faster RCNN-based detection of cervical spinal cord injury and disc degeneration. J Appl Clin Med Phys 21. https://doi.org/10.1002/acm2.13001
Pai SA, Zhang H, Shewchuk JR et al (2020) Quantitative identification and segmentation repeatability of thoracic spinal muscle morphology. JOR Spine 3(3):e1103. Published 2020 Jul 1. https://doi.org/10.1002/jsp2.1103
Azzarito M, Kyathanahally SP, Balbastre Y et al (2021) Simultaneous voxel-wise analysis of brain and spinal cord morphometry and microstructure within the SPM framework. Hum Brain Mapp 42:220–232. https://doi.org/10.1002/hbm.25218
Majidpoor J, Mortezaee K, Khezri Z et al (2021) The effect of the segment of spinal cord injury on the activity of the nucleotide-binding domain-like receptor protein 3 inflammasome and response to hormonal therapy. Cell Biochem Funct 39(2):267–276. https://doi.org/10.1002/cbf.3574
Maidawa SM, Ali MN, Imam J, Salami SO, Hassan AZ, Ojo SA (2021) Morphology of the spinal nerves from the cervical segments of the spinal cord of the African giant rat (Cricetomys Gambianus). Anat Histol Embryol 50(2):300–306. https://doi.org/10.1111/ahe.12630
Malathy V, Anand M, Dayanand Lal N et al (2020) Segmentation of spinal cord from computed tomography images based on level set method with Gaussian kernel. Soft Comput 24:18811–18820. https://doi.org/10.1007/s00500-020-05113-1
Sabaghian S, Dehghani H, Batouli SAH et al (2020) Fully automatic 3D segmentation of the thoracolumbar spinal cord and the vertebral canal from T2-weighted MRI using K-means clustering algorithm. Spinal Cord 58:811–820. https://doi.org/10.1038/s41393-020-0429-3
Zhang X, Li Y, Liu Y et al (2021) Automatic spinal cord segmentation from axial-view MRI slices using CNN with grayscale regularized active contour propagation. Comput Biol Med 132:104345. https://doi.org/10.1016/j.compbiomed.2021.104345
A deep learning method with residual blocks for automatic spinal cord segmentation in planning CT. https://www.sciencedirect.com/science/article/abs/pii/S1746809421006716
Subramanya Jois SP, Sridhar H, Harish Kumar JR (2018) A fully automated spinal cord segmentation. 2018 IEEE global conference on signal and information processing (GlobalSIP), pp 524–528. https://doi.org/10.1109/GlobalSIP.2018.8646682
Hasane S, Rajesh V, Rahman MZU (2019) Fast and accurate feature extraction-based segmentation framework for spinal cord injury severity classification. IEEE Access 7:46092–46103. https://doi.org/10.1109/ACCESS.2019.2909583
Rehman F, Ali Shah SI, Riaz N, Gilani SO (2019) A robust scheme of vertebrae segmentation for medical diagnosis. IEEE Access 7:120387–120398. https://doi.org/10.1109/ACCESS.2019.2936492
Kim DH, Jeong JG, Kim YJ et al (2021) Automated vertebral segmentation and measurement of vertebral compression ratio based on deep learning in X-ray images. J Digit Imaging 34:853–861. https://doi.org/10.1007/s10278-021-00471-0
Perone C, Calabrese E, Cohen-Adad J (2018) Spinal cord gray matter segmentation using deep dilated convolutions. Sci Rep 8. https://doi.org/10.1038/s41598-018-24304-3
Ahammad SH, Rajesh V, Rahman MZU (2019) Fast and accurate feature extraction-based segmentation framework for spinal cord injury severity classification. IEEE Access 7:46092–46103. https://doi.org/10.1109/ACCESS.2019.2909583
Valarmathi G, Devi S (2021) Human vertebral spine segmentation using particle swarm optimization algorithm. https://doi.org/10.1007/978-981-16-0669-4_7
Punarselvam E, Suresh P (2019) Investigation on human lumbar spine MRI image using finite element method and soft computing techniques. Cluster Computing 22. https://doi.org/10.1007/s10586-018-2019-0
Acknowledgements
We would like to thank the management and Principal of ATME College of Engineering, Mysore, for their ongoing assistance and support.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Garg, S., Bhagyashree, S.R. (2024). Improving Efficiency of Spinal Cord Image Segmentation Using Transfer Learning Inspired Mask Region-Based Augmented Convolutional Neural Network. In: Swaroop, A., Polkowski, Z., Correia, S.D., Virdee, B. (eds) Proceedings of Data Analytics and Management. ICDAM 2023. Lecture Notes in Networks and Systems, vol 785. Springer, Singapore. https://doi.org/10.1007/978-981-99-6544-1_19
Download citation
DOI: https://doi.org/10.1007/978-981-99-6544-1_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6543-4
Online ISBN: 978-981-99-6544-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)