디지털융복합연구 (Journal of Digital Convergence)

  • 제16권2호
  • /
  • Pages.19-26
  • /
  • 2018
  • /
  • 2713-6434(pISSN)
  • /
  • 2713-6442(eISSN)
한국디지털정책학회 (The Society of Digital Policy and Management)
권호 표지
DOI QR코드

DOI QR Code

흉부 CT 영상에서 개선된 폐 및 폐혈관 분할과 괴사 세포 비율의 수치적 알고리즘

Improved Lung and Pulmonary Vessels Segmentation and Numerical Algorithms of Necrosis Cell Ratio in Lung CT Image

  • 조준호 (원광대학교 전자융합공학과) ;
  • 문성룡 (원광대학교 전자공학과)
  • Cho, Joon-Ho (Department of Electronics Convergence Engineering, Wonkwang University) ;
  • Moon, Sung-Ryong (Department of Electronic Engineering, Wonkwang University)
  • 투고 : 2017.12.04
  • 심사 : 2018.02.20
  • 발행 : 2018.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

흉부 CT 영상에서 폐 질환의 진단을 위해서 폐 분할, 폐혈관 분할과 폐 질환 부위에 대한 괴사 세포 비율의 수치적 계산을 제안 하였다. 첫 번째 단계는 흉부 CT 영상에서 3차원 레이블링 기법과 3차원 영역 성장법을 적용하여 폐와 기관지를 분리한다. 두 번째 단계는 폐혈관 분할은 1차 다항식 회귀(Polynomial Regression)를 사용한 변화율을 적용하여 분할한 다음, 잡음 제거를 실시하여 최종의 폐혈관을 분할한다. 세 번째 단계는 2단계 이미지 에서 질환 예상 인자를 발견하고, 괴사 세포의 비율을 계산하는 것이다. 질환 예상인자는 폐에 대해서 3차원 레이블링 기법을 적용하였고, 각 레이블 중심 값을 관측하여 변화가 없는 레이블을 찾는다. 이렇게 찾은 질환 예상 인자는 조영제 투입 전/후 영상을 정합한 뒤, 면적을 비교하면 폐의 괴사 세포 비율을 계산할 수 있다.

We proposed a numerical calculation of the proportion of necrotic cells in pulmonary segmentation, pulmonary vessel segmentation lung disease site for diagnosis of lung disease from chest CT images. The first step is to separate the lungs and bronchi by applying a three-dimensional labeling technique from a chest CT image and a three-dimensional region growing method. The second step is to divide the pulmonary vessels by applying the rate of change using the first order polynomial regression, perform noise reduction, and divide the final pulmonary vessels. The third step is to find a disease prediction factor in a two-step image and calculate the proportion of necrotic cells.

키워드

참고문헌

  1. X1. Meng, Y. Qiang, S. Zhu, C. Fuhrman , JM. Siegfried & J. Pu.(2012). Illustration of the obstacles in computerized lung segmentation using examples. Med Phys, 39(8), 498-491. DOI: 10.1118/1.4737023
  2. M. S. Brown, M. F. McNitt-Gray, N. J. Mankovich, J. G. Goldin, J. Hiller, L. S. Wilson & D. R. Aberle.(1997). Method for segmenting chest CT image data using an anatomic model: Preliminary results. IEEE Trans. Medical Imaging. 16(6). 828-839. DOI: 10.1109/42.650879
  3. S. Hu, E. A. Hoffman & J. M. Reinhardt.(2001). Accurate Lung Segmentation for Accurate Quantitation of Volumetric X-Ray CT Images. IEEE Transactions on Medical Imaging. 20(6). 490-498. DOI: 10.1109/42.929615
  4. T. Kitasaka, K. Mori, J. Hasegawa & J. Toriwaki. (2003). Lung area extraction from 3-D chest X-ray CT images using a shape model generated bya variable Bezier surface. Syst. Comput. Jpn.. 34(4), 60-71. DOI: 10.1002/scj.1201
  5. Y.Y.Yim, H. L. Hong & Y. G. Shin. (2005). Automatic Lung Segmentation using Hybrid Approach. Journal of KIISE : Software and Applications. 32(7), 625-635. DOI: 10.1118/1.3147146
  6. D. Bartz, D. Mayer, J. Fischer & S. Ley.(2003). Hybrid Segmentation and Exploration of the Human Lungs. Proc. of IEEE Visualization, 14(3), 177-184. DOI:10.1109/VISUAL.2003.1250370
  7. Y. Masutani, H. MacMahon & K. Doi.(2002). Computerized Detection of Pulmonary Embolism in Spiral CT Angiography Based on Volumetric Image Analysis. IEEE Transactions on Medical Imaging. 21(12), 1517-1523. DOI: 10.1109/TMI.2002.806586
  8. J. Pu, D. S. Paik, X. Meng, J. E. Roos & G. D. Rubin.(2011). Shape break and-repair strategy and its application to automated medical image segmentation. IEEE Transactions on Visualization and Computer Graphics. 17(1), 115-124. DOI: 10.1109/TVCG.2010.56
  9. A. Jemal, T. Murray, E. Ward, A. Samuels, R. C. Tiwari, A. Ghafoor, E.J. Feuer & M. J. Thun. (2005). Cancer statistics 2005. A Cancer Journal for Clinicians. 55(1), 10-30. DOI: 10.3322/canjclin.55.1.10
  10. J. Wang, Q. Li & F. Li.(2009). Automated segmentation of lungs with severe interstitial lung disease in CT. Med. Phys. 36(10), 4592-4599. DOI: 10.1118/1.3222872
  11. I. Sluimer, M Prokop. & B. van Ginneken. (2005). Toward automated segmentation of the pathological lung in CT. IEEE Trans. Med. Imag. 24(8), 1025-1038. DOI: 10.1109/TMI.2005.851757
  12. Y. H. Shi, F. H. Qi, Z. Xue, L. Y. Chen, K. K Ito, H. Matsuo & D. Shen.(2008). Segmenting lung fields in serial chest radiographs using both population-based and patient-specific shape statistics. IEEE trans. Med. Imag. 27(4), 481-494. DOI: 10.1109/TMI.2007.908130
  13. A. A. Farag & J. H. Graham. (2013). A novel approach for lung nodules segmentation in chest CT using Levelsets. IEEE Trans image processing. 22(2), 5202-5213. DOI: 10.1109/TIP.2013.2282899
  14. M. Rogers & J. Graham.(2002). Robust active shape model search. Proceedings of the European Conference on Computer Vision. 1(1), 517-530. DOI : https://doi.org/10.1007/3-540-47979-1_35
  15. M. J. Shin & D. Y. Kim.(2012). Pulmonary vascular Segmentation and Refinement On the CT Scans. The Journal of the Korean Institute of Information and Communication Engineering. 16(3), 591-597. DOI : 10.6109/jkiice.2012.16.3.591
  16. S. H. Lee et al.(2014). A Study on the Usefulness of 3D Imaging in Micro-CT for Observing the Microstructure of Mice. Journal of Digital Convergence. 12(3), 367-375. DOI: 10.14400/JDC.2014.12.3.367