DOI QR코드

DOI QR Code

Data Augmentation Method for Deep Learning based Medical Image Segmentation Model

딥러닝 기반의 대퇴골 영역 분할을 위한 훈련 데이터 증강 연구

  • Received : 2019.06.11
  • Accepted : 2019.06.23
  • Published : 2019.07.14

Abstract

In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

본 연구에서는 CT 영상의 대퇴골 부위를 해부학적으로 의미 있게 변형하여 CT 영상의 대퇴골 영역을 분할하기 위한 컨벌루션 신경망(CNN)의 훈련 데이터를 증강하는 방법을 제안한다. 먼저 CT 영상으로부터 삼차원 삼각형 대퇴골 메쉬를 얻는다. 그 후 메쉬의 국소부위에 대한 기하학적 특성을 계산하고, 군집화하여 메쉬를 의미 있는 부분들로 분할한다. 마지막으로, 분할한 부분들을 적절한 알고리즘으로 변형한 뒤, 이를 바탕으로 CT 영상을 와핑하여 새로운 CT영상을 생성하였다. 본 연구의 데이터 증강 방법을 이용하여 학습시킨 딥러닝 모델은 기하학적 변환이나 색상 변환 같이 일반적으로 사용되는 데이터 증강법과 비교하여 더 나은 영상분할 성능을 보인다.

Keywords

References

  1. C. Rich, S. Lawrence, and C. -L. Giles, "Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping", Advances in neural information processing systems, 2001.
  2. O. Cicek, et al, "3D U-Net: learning dense volumetric segmentation from sparse annotation", International conference on medical image computing and computer-assisted intervention. Springer, Cham, 2016.
  3. P. -F. Christ, et al, "Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields", International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2016.
  4. J. -Y. Zhu, et al, "Unpaired image-to-image translation using cycleconsistent adversarial networks", IEEE Transactions on computer vision, 2017.
  5. S. -C. Wong, et al, "Understanding data augmentation for classification: when to warp?", IEEE Transactions on digital image computing: techniques and applications (DICTA), 2016.
  6. W. -E. Lorensen, and H. -E. Cline, "Marching cubes: A high resolution 3D surface construction algorithm", ACM siggraph computer graphics. Vol. 21. No. 4, 1987.
  7. P. Yves, et al, "Interactive graph-cut segmentation for fast creation of finite element models from clinical ct data for hip fracture prediction", Computer methods in biomechanics and biomedical engineering 19.16, pp. 1693-1703, 2016. https://doi.org/10.1080/10255842.2016.1181173
  8. L.Wang, K. He, and Z. Chen, "Statistical Analyses of Femur Parameters for Designing Anatomical Plates," Computational and Mathematical Methods in Medicine, pp. 12, 2016.
  9. Y. -J. Lee, "Mesh Scissoring: Contour-Based Mesh Segmentation. PhD dissertation", Postech, 2005.
  10. J. J-. Koenderink, and A. -J. Doorn, "Surface shape and curvature scales", Image and Vision Computing 10, pp. 557-565, 1992. https://doi.org/10.1016/0262-8856(92)90076-F
  11. D. Comaniciu, and P. Meer, "Mean shift: A robust approach toward feature space analysis", IEEE Transactions on Pattern Analysis & Machine Intelligence 5, pp. 603-619, 2002. https://doi.org/10.1109/34.1000236
  12. M. Garland, A Willmott, and P. Heckbert, "Hierarchical face clustering on polygonal surfaces", ACM Symposium on Interactive 3D Graphics 2001, pp. 49-58, 2001.
  13. S. Wold, K. Esbensen, and P. Geladi, "Principal component analysis", Chemometrics and intelligent laboratory systems 2.1-3, pp. 37-52, 1987. https://doi.org/10.1016/0169-7439(87)80084-9
  14. T. -W. Sederberg, and, S. -R. Parry, "Free-form deformation of solid geometric models", Annual conference on Computer graphics and interactive techniques 13th (SIGGRAPH '86), 1986.
  15. O. Sorkine, et al, "Laplacian surface editing", Eurographics/ACM SIGGRAPH symposium on Geometry processing 2004 (SGP '04), pp. 175-184, 2004.
  16. S. Lee, G. Wolberg, and S. -Y. Shin, "Scattered data interpolation with multilevel B- splines", IEEE Transactions on Visualization and Computer Graphics, vol. 3, no. 3, pp. 228-244, 1997. https://doi.org/10.1109/2945.620490
  17. M. Kistler, et al, "The virtual skeleton database: an open access repository for biomedical research and collaboration", medical Internet research, e. 245, 2013.
  18. K. Zuiderveld. "Contrast limited adaptive histogram equalization", Graphics gems IV. Academic Press Professional, 1994.
  19. P. Jaccard, "Etude comparative de la distribution florale dans une portion des Alpes et des Jura", Bull Soc Vaudoise Sci Nat 37, pp. 547-579, 1901.
  20. Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-net: Convolutional networks for biomedical image segmentation." International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015.