Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Evaluation of Deep Learning Model for Scoliosis Pre-Screening Using Preprocessed Chest X-ray Images

  • Min Gu Jang (Department of Orthopedic Surgery, Konyang University Hospital) ;
  • Jin Woong Yi (Department of Orthopedic Surgery, Konyang University Hospital) ;
  • Hyun Ju Lee (Department of Physical Therapy, Konyang University) ;
  • Ki Sik Tae (Department of Biomedical Engineering, Konyang University)
  • Received : 2022.07.13
  • Accepted : 2023.08.21
  • Published : 2023.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Scoliosis is a three-dimensional deformation of the spine that is a deformity induced by physical or disease-related causes as the spine is rotated abnormally. Early detection has a significant influence on the possibility of nonsurgical treatment. To train a deep learning model with preprocessed images and to evaluate the results with and without data augmentation to enable the diagnosis of scoliosis based only on a chest X-ray image. The preprocessed images in which only the spine, rib contours, and some hard tissues were left from the original chest image, were used for learning along with the original images, and three CNN(Convolutional Neural Networks) models (VGG16, ResNet152, and EfficientNet) were selected to proceed with training. The results obtained by training with the preprocessed images showed a superior accuracy to those obtained by training with the original image. When the scoliosis image was added through data augmentation, the accuracy was further improved, ultimately achieving a classification accuracy of 93.56% with the ResNet152 model using test data. Through supplementation with future research, the method proposed herein is expected to allow the early diagnosis of scoliosis as well as cost reduction by reducing the burden of additional radiographic imaging for disease detection.

Keywords

References

  1. Cobb J. Outline for the study of scoliosis. instructional course lectures. 1948;5(1):261-275.
  2. Kadoury S, Labelle, H. Classification of three-dimensional thoracic deformities in adolescent idiopathic scoliosis from a multivariate analysis. Eur. Spine J. 2012;21(1):40-49. https://doi.org/10.1007/s00586-011-2004-2
  3. Sibel B, Hayriye K. Rule-based fuzzy classifier for spinal deformities. Biomed Mater Eng. 2014;24(6):3311-3119.
  4. Imaz CY. Surgical treatment of adolescent idiopathic scoliosis. M.Sc. Dissertation, Ankara University. 2001.
  5. Trobisch P, Suess O, Schwab F. Idiopathic Scoliosis. Continuing Medical Education. 2010;107(49):875-884. https://doi.org/10.3238/arztebl.2010.0875
  6. Cheng JC, Castelein RM, Chu WC, Danielsson AJ, Dobbs MB, Grivas TB. Adolescent idiopathic scoliosis. Nat. Rev. Dis. Prim. 2015;24(1):1-20.
  7. Negrini S, Donzelli S, Aulisa AG, Czaprowski D, Schreiber S, de Mauroy JC. 2016 SOSORT guidelines: orthopaedic and rehabilitation treatment of idiopathic scoliosis during growth. Scoliosis. 2018;13(3):1-48. https://doi.org/10.1186/s13013-017-0148-5
  8. Lenke LG. Lenke classification system of adolescent idiopathic scoliosis: treatment recommendations. Instr Course Lect. 2005;54:537-542.
  9. Sapountzi-Krepia DS, Valavanis J, Panteleakis GP, Zangana DT, Vlachojiannis PC, Sapkas GC. Perceptions of body image, happiness and satisfaction in adolescents wearing a Boston brace for scoliosis treatment. J Adv Nurs. 2001;35(5):683-690. https://doi.org/10.1046/j.1365-2648.2001.01900.x
  10. Reamy BV, Slakey JB. Adolescent idiopathic scoliosis: review and current concepts. Am Fam Physician. 2001;64(1):111-116.
  11. Lee MK, Lee GJ, Song YK, Lim HH. Review on conservative treatment of spinal scoliosis. The Journal of Korea CHUNA Manual Medicine for Spine and Nerves. 2009;4(1):103-117.
  12. Lonstein JE, BJorklund S, Wanninger MH. Voluntary school screening for scoliosis in Minnesota. J Bone Joint Surg Am. 1982;64(4):481-488. https://doi.org/10.2106/00004623-198264040-00002
  13. Tu Y, Wang N, Tong F, Chen H. Automatic measurement algorithm of scoliosis Cobb angle based on deep learning. Journal of Physics: Conference Series. 2019;1187(4):042100
  14. Zhou GQ, Jiang WW, Lai KL, Zheng YP. Automatic Measurement of Spine Curvature on 3-D Ultrasound Volume Projection Image with Phase Features. IEEE Transactions on Medical Imaging. 2017;36(6):1250-1262. https://doi.org/10.1109/TMI.2017.2674681
  15. Sugita K. Epidemiological study on idiopathic scoliosis in high school students. Prevalence and relation to physique, physical strength and motor ability. Nihon Koshu Eisei Zasshi. 2000;47(4):320-325.
  16. Oh CH, Kim CG, Lee MS, Yoon SH, Park HC, Park CO. Usefulness of chest radiographs for scoliosis screening: A comparison with thoraco-lumbar standing radiographs. Yonsei Med J. 2012;53(6):1183-1189. https://doi.org/10.3349/ymj.2012.53.6.1183
  17. Vollmer S, Mateen BA, Bohner G, Kiraly FJ, Ghani R, Jonsson P, et al. Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness. BMJ. 2020;368:l6927.
  18. Gstoettner M, Sekyra K, Walochnik N, Winter P, Wachter R, Bach CM. Inter- and intraobserver reliability assessment of the Cobb angle: manual versus digital measurement tools. Eur Spine J. 2007;16(10):1587-1592. https://doi.org/10.1007/s00586-007-0401-3
  19. Yang J, Zhang K, Fan H, Huang Z, Xiang Y, Yang J. Development and validation of deep learning algorithms for scoliosis screening using back images. Commun Biol. 2019;25(2):390.
  20. Wang H, Zhang T, Cheung KMC, Shea GKH. Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit. EClinicalMedicine. 2021;29(42):101220.
  21. Wang J, Zhu H, Wang SH, Zhang YD. A review of deep learning on medical image analysis. International Journal of Multimedia Information Retrieval. 2021;26(2):19-38.
  22. Wua H, Bailey C, Rasoulinejad P, Li S. Automated comprehensive adolescent idiopathic scoliosis assessment using MVCNet. Med Image Anal. 2018;48:1-11. https://doi.org/10.1016/j.media.2018.05.005
  23. Song TR, Wei Z. The research of X-ray bone fracture image enhancement algorithms. International Conference on Computer, Mechatronics, Control and Electronic Engineering. 2010;24-26.
  24. Calderon S, Fallas F, Zumbado M, Tyrrell PN, Stark H, Emersic Z, et al. Assessing the impact of the deceived non local means filter as a preprocessing stage in a convolutional neural network based approach for age estimation using digital hand X-Ray images. IEEE International Conference on Image Processing (ICIP). 2018;7-10.
  25. Sreenivasulu N, Kishore RM. Color image enhancement using adaptive sigmoid function with bi-histogram equalization. NCICCT. 2015;3(12):1-7.
  26. Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data. 2019;6(60):1-48. https://doi.org/10.1186/s40537-018-0162-3
  27. Gu S, Pednekar M, Slater R. Improve Image Classification Using Data Augmentation and Neural Networks. SMU Data Science Review. 2019;2(2):1-44.
  28. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. ICLR 2015.
  29. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Computer Vision and Pattern Recognition. 2015.
  30. Tan M, Le QV. EfficientNet: Rethinking model scaling for convolutional neural networks. ICML 2019.
  31. Zhang H, Zhang L, Jiang Y. Overfitting and underfitting analysis for deep learning based end-to-end communication systems. International Conference on Wireless Communications and Signal Processing (WCSP). 2019;23-25.
  32. Nguyen QH, Ly HB, Ho LS, Al-Ansari N, Le HV, Tran VQ, et al. Influence of data splitting on performance of machine learning models in prediction of shear strength of soil. Mathematical Problems in Engineering. 2021;2021(6):1-15. https://doi.org/10.1155/2021/4832864