DOI QR코드

DOI QR Code

A Novel Method for Automated Honeycomb Segmentation in HRCT Using Pathology-specific Morphological Analysis

병리특이적 형태분석 기법을 이용한 HRCT 영상에서의 새로운 봉와양폐 자동 분할 방법

  • 김영재 (광운대학교 플라즈마 바이오 디스플레이학과) ;
  • 김태윤 (국립암센터 의공학연구과) ;
  • 이승현 (광운대학교 정보콘텐츠대학원) ;
  • 김광기 (국립암센터 의공학연구과) ;
  • 김종효 (서울대학교 융합과학기술대학원 방사선의생명융합전공/의과대학 영상의학교실)
  • Received : 2012.05.21
  • Accepted : 2012.09.03
  • Published : 2012.11.30

Abstract

Honeycombs are dense structures that small cysts, which generally have about 2~10 mm in diameter, are surrounded by the wall of fibrosis. When honeycomb is found in the patients, the incidence of acute exacerbation is generally very high. Thus, the observation and quantitative measurement of honeycomb are considered as a significant marker for clinical diagnosis. In this point of view, we propose an automatic segmentation method using morphological image processing and assessment of the degree of clustering techniques. Firstly, image noises were removed by the Gaussian filtering and then a morphological dilation method was applied to segment lung regions. Secondly, honeycomb cyst candidates were detected through the 8-neighborhood pixel exploration, and then non-cyst regions were removed using the region growing method and wall pattern testing. Lastly, final honeycomb regions were segmented through the extraction of dense regions which are consisted of two or more cysts using cluster analysis. The proposed method applied to 80 High resolution computed tomography (HRCT) images and achieved a sensitivity of 89.4% and PPV (Positive Predictive Value) of 72.2%.

봉와양폐(Honeycomb)는 직경 2~10mm 정도의 크기가 같지 않은 낭포(Cyst)가 경계가 명확한 섬유질(Fibrosis)로 이루어진 벽에 둘러싸여 밀집된 형태로 이루어져 있다. 봉와양폐가 발견될 경우 급성악화의 발생 빈도가 높으며 따라서 봉와양폐의 관찰 여부와 측정은 임상에서 중요한 지표가 된다. 따라서 본 논문에서는 봉와양폐 영역의 정량적 측정을 위하여 봉와양폐의 특징을 이용한 형태학적 기법과 군집성 평가 기법을 통해 자동 구획 방법을 제안하였다. 첫 번째로 영상의 잡음을 제거하기 위하여 가우시안 필터링을 적용하고, 모폴로지 기법 중 팽창 기법을 이용하여 폐 영역을 구획하였다. 두번째로, 주변 8방향 검사를 통해 봉와양폐를 구성하는 낭포의 후보군을 찾고, 영역 확장과 외곽선 검사를 통해 비 낭포들을 제거하였다. 마지막으로 군집화 검사를 통해 최종적으로 봉와양폐를 구획하였다. 제안한 방법은 80장의 고해상도 컴퓨터 단층촬영 영상에서 실험한 결과, 89.4%의 민감도와, 72.2%의 양성 예측도를 보였다.

Keywords

References

  1. K.-N. Lee, "DILD; Radiologic Diagnostic Approach According to High-Resolution CT Pattern," Tuberculosis and Respiratory Diseases, Vol.58, pp.111-119, 2005. https://doi.org/10.4046/trd.2005.58.2.111
  2. L. Bessis, et al., "High-resolution CT of parenchymal lung disease: precise correlation with histologic findings," Radiographics, Vol.12, pp.45, 1992. https://doi.org/10.1148/radiographics.12.1.1734481
  3. E.-Y. Kang, et al., "Radiologic Approach to Diffuse Infiltrative Lung Disease," J Korean Radiol Soc, Vol.54, pp.503-513, 2006. https://doi.org/10.3348/jkrs.2006.54.6.503
  4. R. Shojaii, et al., "Automatic Segmentation of Abnormal Lung Parenchyma Utilizing Wavelet Transform," ICASSP IEEE International Conference, Vol.1, pp.I-1217-1220, 2007.
  5. R. Shojaii, et al., "Automatic honeycomb lung segmentation in pediatric ct images," ISSPA. 9th International Symposium, pp.1-4, 2007.
  6. C. M. J. Wang., et al., "Lung Disease Detection Using Frequency Spectrum Analysis," in ICVGIP, pp.485-490, 2004.
  7. J. S. J. Wong and T. Zrimec, "Automatic honeycombing detection using texture and structure analysis," Computational Intelligence Methods and Applications, pp.4, 2005.
  8. T. Zrimec and J. Wong, "Methods for Automatic Honeycombing Detection in HRCT images of the Lung," IFMBE 2007, Vol.16, pp.830-833, 2007.
  9. M. S. Nixon and A. S. Aguado, "Feature extraction and image processing", Academic Press, 2008.
  10. T. M. Deserno, "Biomedical Image Processing", Springer, 2011.
  11. S. Hu, et al., "Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images," Medical Imaging, IEEE Transactions on, Vol.20, pp.490-498, 2001. https://doi.org/10.1109/42.929615
  12. R. Fabbri, et al., "2D Euclidean distance transform algorithms: A comparative survey," ACM Computing Surverys, Vol.40, pp.2, 2008.
  13. B. Vidakovic, "Statistics for Bioengineering Sciences: With Matlab and Winbugs Support", Springer Verlag, 2011.
  14. J. Beutel, "Handbook of medical imaging: Physics and psychophysics Vol.1", Spie Press, 2000.