Vector Field Convolution for Segmentationand Measurement of Pleural Effusion

Pleural effusion is a vital biomarker for the diagnosis of many diseases. A pleural effusion is an anomalous amount of fluid around the lung that can result from many medical conditions. In this paper, an improved automated method is implemented to evaluate pleural effusion on CT scan and prohibitively time consuming when performed manually. The proposed method is based on parietal pleura extraction and visceral pleura extraction and active contour external force using vector field convolution for image segmentation along with region growing and Bezier surface fitting and deformable surface modeling .Twelve CT scans with three manual segmentation were used to evaluate the automatic segmentation method. The visceral assessment estimated 85% cases with negligible or small segmentation errors 13% with medium errors and 2% with large errors.

[1]  Scott T. Acton,et al.  Multigrid anisotropic diffusion , 1998, IEEE Trans. Image Process..

[2]  Jadwiga Rogowska,et al.  Overview and fundamentals of medical image segmentation , 2000 .

[3]  J. Ruskin,et al.  Detection of pleural effusions on supine chest radiographs. , 1987, AJR. American journal of roentgenology.

[4]  Joachim Weickert,et al.  Anisotropic diffusion in image processing , 1996 .

[5]  James S. Duncan,et al.  Deformable boundary finding in medical images by integrating gradient and region information , 1996, IEEE Trans. Medical Imaging.

[6]  Bruce Fischl,et al.  Learning an Integral Equation Approximation to Nonlinear Anisotropic Diffusion in Image Processing , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  H. Yoshida,et al.  MDCT for automated detection and measurement of pneumothoraces in trauma patients. , 2009, AJR. American journal of roentgenology.

[8]  Andrew Shearer,et al.  Constrained Region-Based Segmentation of Pleural Effusion in Thin-Slice CT , 2009, 2009 13th International Machine Vision and Image Processing Conference.

[9]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[10]  Caiming Zhang,et al.  New Method for Quantification of Pleural Effusions from CT Imagine , 2008, 2008 ISECS International Colloquium on Computing, Communication, Control, and Management.

[11]  Laurent D. Cohen,et al.  Finite-Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  J. M. Porcel,et al.  Etiology and pleural fluid characteristics of large and massive effusions. , 2003, Chest.

[13]  Scott T. Acton,et al.  Constraining active contour evolution via Lie Groups of transformation , 2004, IEEE Transactions on Image Processing.

[14]  P. Preux,et al.  Quantitative assessment of pleural effusion in critically ill patients by means of ultrasonography* , 2005, Critical care medicine.

[15]  Jerry L. Prince,et al.  Generalized gradient vector flow external forces for active contours , 1998, Signal Process..

[16]  R. Halvorsen,et al.  Ascites or pleural effusion? CT differentiation: four useful criteria. , 1986, Radiographics : a review publication of the Radiological Society of North America, Inc.