Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

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

DOI QR Code

Classification of Anteroposterior/Lateral Images and Segmentation of the Radius Using Deep Learning in Wrist X-rays Images

손목 관절 단순 방사선 영상에서 딥 러닝을 이용한 전후방 및 측면 영상 분류와 요골 영역 분할

  • Lee, Gi Pyo (Department of Biomedical Engineering, College of Health Science, Gachon University) ;
  • Kim, Young Jae (Department of Biomedical Engineering, College of Health Science, Gachon University) ;
  • Lee, Sanglim (Department of Orthopedic Surgery, Inje University Sanggye Paik Hospital) ;
  • Kim, Kwang Gi (Department of Biomedical Engineering, College of Health Science, Gachon University)
  • 이기표 (가천대학교 보건과학대학 의용생체공학과) ;
  • 김영재 (가천대학교 보건과학대학 의용생체공학과) ;
  • 이상림 (인제대학교 상계백병원 정형외과) ;
  • 김광기 (가천대학교 보건과학대학 의용생체공학과)
  • Received : 2020.01.29
  • Accepted : 2020.04.13
  • Published : 2020.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study was to present the models for classifying the wrist X-ray images by types and for segmenting the radius automatically in each image using deep learning and to verify the learned models. The data were a total of 904 wrist X-rays with the distal radius fracture, consisting of 472 anteroposterior (AP) and 432 lateral images. The learning model was the ResNet50 model for AP/lateral image classification, and the U-Net model for segmentation of the radius. In the model for AP/lateral image classification, 100.0% was showed in precision, recall, and F1 score and area under curve (AUC) was 1.0. The model for segmentation of the radius showed an accuracy of 99.46%, a sensitivity of 89.68%, a specificity of 99.72%, and a Dice similarity coefficient of 90.05% in AP images and an accuracy of 99.37%, a sensitivity of 88.65%, a specificity of 99.69%, and a Dice similarity coefficient of 86.05% in lateral images. The model for AP/lateral classification and the segmentation model of the radius learned through deep learning showed favorable performances to expect clinical application.

Keywords

References

  1. Brudvik C, Hove LM. Childhood fractures in Bergen, Norway: identifying high-risk groups and activities. J Pediatr Orthop. 2003;23:629-34. https://doi.org/10.1097/01241398-200309000-00010
  2. Owen RA, Melton LJ 3rd, Johnson KA, Ilstrup DM, Riggs BL. Incidence of Colles' fracture in a North American community. Am J Public Health. 1982;72:605-7. https://doi.org/10.2105/AJPH.72.6.605
  3. http://www.wheelessonline.com/ortho/posterior_anterior_view_of_the_wrist. Accessed on 27 Oct 2019.
  4. http://www.wheelessonline.com/ortho/posterior_anterior_view_of_the_wrist. Accessed on 27 Oct 2019.
  5. Kiuru MJ, Haapamaki VV, Koivikko MP, Koskinen SK. Wrist injuries; diagnosis with multidetector CT. Emerg Radiol. 2004;10(4):182-5. https://doi.org/10.1007/s10140-003-0321-4
  6. Cho SU, Yang JI, Han KH, Cho YC, Yoo IS, Kim SW, Lee JW, Ryu S, You YH, Han SG, Park SS, Jung WJ, Jung WJ, Lee WS. The Accuracy of a Simple Radiologic Study for Diagnosing Intra-articular Fractures of the Distal Radius. J Korean Soc Emerg Med. 2010;21(5):569-74.
  7. Lee JG, Jun S, Cho YW, Lee H, Kim GB, Seo JB, Kim N. Deep Learning in Medical Imaging: General Overview. Korean J Radiol. 2017;18(4):570-84. https://doi.org/10.3348/kjr.2017.18.4.570
  8. A. Raj, S. Vishwanathan, B. Ajani, K. Krishnan, H. Agarwal. Automatic knee cartilage segmentation using fully volumetric convolutional neural networks for evaluation of osteoarthritis. 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC. 2018; 851-4.
  9. Kim BS, Lee IH, Retinal Blood Vessel Segmentation using Deep Learning. Korean Institute of Information Technology. 2019;17(5):77-82.
  10. Kim YJ, Park SJ, Kim KR, Kim KG. Automated Ulna and Radius Segmentation model based on Deep Learning on DEXA. Journal of Korea Multimedia Society. 2018;21(12):1407-16. https://doi.org/10.9717/KMMS.2018.21.12.1407
  11. DiBenedetto MR, Lubbers LM, Ruff ME, Nappi JF, Coleman CR. Quantification of error in measurement of radial inclination angle and radial-carpal distance. J Hand Surg Am. 1991;16(3):399-400. https://doi.org/10.1016/0363-5023(91)90004-U
  12. Jafari D, Najd Mazhar F, Jalili A, Zare S, Hoseini Teshnizi S. The Inter and intraobserver reliability of measurements of the distal radius radiographic indices. J. Res. Orthop. Sci.. 2014;1(2):22-5.
  13. Hossain, M., Andrew, J.G. Reliability of a digital radiographic system in measuring distal radial fracture displacement parameters. Eur J Orthop Surg Traumatol. 2008;18:565-9. https://doi.org/10.1007/s00590-008-0354-1
  14. M. Attia, M. Hossny, S. Nahavandi, and H. Asadi, Surgical tool segmentation using a hybrid deep CNN-RNN auto encoderdecoder. 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Banff, AB. 2017; 3373-78.
  15. Schneider CA, Rasband WS, and Eliceiri KW. NIH Image to ImageJ: 25 years of image analysis. Nature methods. 2012;9(7):671-5. https://doi.org/10.1038/nmeth.2089
  16. K. He, X. Zhang, S. Ren, J. Sun. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016; 770-8.
  17. Park SJ, Kim YG, Park DK, Chung JW, Kim KG. Evaluation of Transfer Learning in Gastroscopy Image Classification using Convolutional Neural Network. Journal of biomedical Engineering Research. 2018;39(5):213-9. https://doi.org/10.9718/JBER.2018.39.5.213
  18. O. Ronneberger, P. Fischer, T. Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical image computing and computer-assisted intervention. 2015; 234-41.
  19. D. Giavarina. Understanding Bland Altman analysis. Biochemia medica. 2015;25(2):141-51. https://doi.org/10.11613/BM.2015.015