Evaluation of Semi-automatic Segmentation Methods for Persistent Ground Glass Nodules on Thin-Section CT Scans
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: This work was a comparative study that aimed to find a proper method for accurately segmenting persistent ground glass nodules (GGN) in thin-section computed tomography (CT) images after detecting them. Methods: To do this, we first applied five types of semi-automatic segmentation methods (i.e., level-set-based active contour model, localized region-based active contour model, seeded region growing, K-means clustering, and fuzzy C-means clustering) to preprocessed GGN images, respectively. Then, to measure the similarities, we calculated the Dice coefficient of the segmented area using each semiautomatic method with the result of the manually segmented area by two radiologists. Results: Comparison experiments were performed using 40 persistent GGNs. In our experiment, the mean Dice coefficient for each semiautomatic segmentation tool with manually segmented area was 0.808 for the level-set-based active contour model, 0.8001 for the localized region-based active contour model, 0.629 for seeded region growing, 0.7953 for K-means clustering, and 0.7999 for fuzzy C-means clustering, respectively. Conclusions: The level-set-based active contour model algorithm showed the best performance, which was most similar to the result of manual segmentation by two radiologists. From the differentiation between the normal parenchyma and the nodule, it was also the most efficient. Effective segmentation methods will be essential for the development of computer-aided diagnosis systems for more accurate early diagnosis and prognosis of lung cancer in thin-section CT images.
Abstract
Objectives: This work was a comparative study that aimed to find a proper method for accurately segmenting persistent ground glass nodules (GGN) in thin-section computed tomography (CT) images after detecting them. Methods: To do this, we first applied five types of semi-automatic segmentation methods (i.e., level-set-based active contour model, localized region-based active contour model, seeded region growing, K-means clustering, and fuzzy C-means clustering) to preprocessed GGN images, respectively. Then, to measure the similarities, we calculated the Dice coefficient of the segmented area using each semiautomatic method with the result of the manually segmented area by two radiologists. Results: Comparison experiments were performed using 40 persistent GGNs. In our experiment, the mean Dice coefficient for each semiautomatic segmentation tool with manually segmented area was 0.808 for the level-set-based active contour model, 0.8001 for the localized region-based active contour model, 0.629 for seeded region growing, 0.7953 for K-means clustering, and 0.7999 for fuzzy C-means clustering, respectively. Conclusions: The level-set-based active contour model algorithm showed the best performance, which was most similar to the result of manual segmentation by two radiologists. From the differentiation between the normal parenchyma and the nodule, it was also the most efficient. Effective segmentation methods will be essential for the development of computer-aided diagnosis systems for more accurate early diagnosis and prognosis of lung cancer in thin-section CT images.
참고문헌 (30)
- Siegel R, "Cancer statistics, 2011: the impact of eliminating socioeconomic and racial disparities on premature cancer deaths", CA Cancer J Clin, 61(4), pp.212~236 (2011)
- 송정섭, "원발성 폐암에서 혈장 과립구 자극인자의 암표지자로서의 역할과 의의", Tuberculosis and Respiratory Diseases, 66(6), pp.444~450 (2009), 대한결핵및호흡기학회
- Nakata M, "Focal ground-glass opacity detected by low-dose helical CT", Chest, 121(5), pp.1464~1467 (2002)
- Beasley MB, "The 2004 World Health Organization classification of lung tumors", Semin Roentgenol, 40(2), pp.90~97 (2005)
- Park CM, "Nodular ground-glass opacity at thin-section CT: histologic correlation and evaluation of change at follow-up", Radiographics, 27(2), pp.391~408 (2007)
- Lee HY, "Ground-glass opacity nodules: histopathology, imaging evaluation, and clinical implications", J Thorac Imaging, 26(2), pp.106~118 (2011)
- Godoy MC, "Subsolid pulmonary nodules and the spectrum of peripheral adenocarcinomas of the lung: recommended interim guidelines for assessment and management", Radiology, 253(3), pp.606~622 (2009)
- Bastawrous HA, "A new CAD system for detecting localized ground glass opacity nodules in lung CT images using cross and coronary section images", Proceedings of IEEE International Workshop on Medical Measurement and Applications, pp.54~57 (2006)
- Kim KG, "Computer-aided diagnosis of localized ground-glass opacity in the lung at CT: initial experience", Radiology, 237(2), pp.657~661 (2005)
- Li Q, "Computerized detection of lung nodules in thin-section CT images by use of selective enhancement filters and an automated rule-based classifier", Acad Radiol, 15(2), pp.165~175 (2008)
- Kanazawa K, "Computer assisted lung cancer diagnosis based on helical images", Proceedings of 3rd International Computer Science Conference, pp.323~330 (1995)
- Okumura T, "Image processing for computer-aided diagnosis of lung cancer screening system by CT (LSCT)", Proc SPIE Int Soc Opt Eng, 3338, pp.1314~1322 (1998)
- Zhou J, "An automatic method for ground glass opacity nodule detection and segmentation from CT studies", Conf Proc IEEE Eng Med Biol Soc, 1, pp.3062~3065 (2006)
- Kim H, "Automatic detection of GGO in CT lung images by using statistical features and neural networks", Proceedings of International Technical Conference on Circuits Systems, Computers and Communication, pp.705~708 (2009)
- Bastawrous HA, "Detection of ground glass opacities in lung CT images using Gabor filters and neural networks", Proceedings of IEEE Instrumentation and Measurement Technology Conference, pp.251~256 (2005)
- Ikeda K, "Differential diagnosis of ground-glass opacity nodules: CT number analysis by three-dimensional computerized quantification", Chest, 132(3), pp.984~990 (2007)
- Tomasi C, "Bilateral filtering for gray and color images", Proceedings of 6th International Conference on Computer Vision, pp.839~846 (1998)
- Barash D., "Bilateral filtering and anisotropic diffusion:towards a unified viewpoint", Proceedings of 3rd International Conference on Scale-Space, pp.273~280 (2001)
- Caselles V, "A geometric model for active contours in image processing", Numer Math, 66(1), pp.1~31 (1993)
- Sethian JA, "A fast marching level set method for monotonically advancing fronts", Proc Natl Acad Sci U S A, 93(4), pp.1591~1595 (1996)
- Shyu KK, "Global and local fuzzy energy-based active contours for image segmentation", Nonlinear Dyn, 67(2), pp.1559~1578 (2012)
- Li C, "Level set evolution without re-initialization: a new variational formulation", Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.430~436 (2005)
- Lankton S, "Localizing regionbased active contours", IEEE Trans Image Process, 17(11), pp.2029~2039 (2008)
- Kaur J, "Comparison of thyroid segmentation algorithms in ultrasound and scintigraphy images", Int J Comput Appl, 50(23), pp.24~27 (2012)
- Mingoti SA, "Comparing SOM neural network with fuzzy C-means, k-means and traditional hierarchical clustering algorithms", Eur J Oper Res, 174(3), pp.1742~1759 (2006)
- Zijdenbos AP, "Morphometric analysis of white matter lesions in MR images: method and validation", IEEE Trans Med Imaging, 13(4), pp.716~724 (1994)
- Fawcett T, "An introduction to ROC analysis", Pattern Recognit Lett, 27(8), pp.861~874 (2006)
- Kim HY, "Persistent pulmonary nodular ground-glass opacity at thinsection CT: histopathologic comparisons", Radiology, 245(1), pp.267~275 (2007)
- Tang L, "3D reconstruction of the optic nerve head using stereo fundus images for computer-aided diagnosis of glaucoma", Proc SPIE Int Soc Opt Eng, 7624, pp.76243~ (2010)
- Way TW, "Computer-aided diagnosis of pulmonary nodules on CT scans: segmentation and classification using 3D active contours", Med Phys, 33(7), pp.2323~2337 (2006)