Fuzzy entropy based optimization of clusters for the segmentation of lungs in CT scanned images

In this paper, we have proposed a method for segmentation of lungs from Computed Tomography (CT)-scanned images using spatial Fuzzy C-Mean and morphological techniques known as Fuzzy Entropy and Morphology based Segmentation. To determine dynamic and adaptive optimal threshold, we have incorporated Fuzzy Entropy. We have proposed a novel histogram-based background removal operator. The proposed system is capable to perform fully automatic segmentation of CT Scan Lung images, based solely on information contained by the image itself. We have used different cluster validity functions to find out optimal number of clusters. The proposed system can be used as a basic building block for Computer-Aided Diagnosis. The technique was tested against the 25 datasets of different patients received from Aga Khan Medical University, Pakistan. The results confirm the validity of technique as well as enhanced performance.

[1]  Beatrice Lazzerini,et al.  Segmentation and reconstruction of the lung volume in CT images , 2005, SAC '05.

[2]  Gerardo Beni,et al.  A Validity Measure for Fuzzy Clustering , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Nisar Ahmed Memon,et al.  Deficiencies Of Lung Segmentation Techniques Using Ct Scan Images For Cad , 2008 .

[4]  Marcelo Gattass,et al.  Diagnosis of lung nodule using Gini coefficient and skeletonization in computerized tomography images , 2004, SAC '04.

[5]  Eugenio Cesario,et al.  Boosting text segmentation via progressive classification , 2008, Knowledge and Information Systems.

[6]  Atam P. Dhawan.  Medical Image Analysis , 2003 .

[7]  Sérgio Shiguemi Furuie,et al.  Multiscale representation for automatic identification of structures in medical images , 2007, Comput. Biol. Medicine.

[8]  Tzong-Jer Chen,et al.  Fuzzy c-means clustering with spatial information for image segmentation , 2006, Comput. Medical Imaging Graph..

[9]  Aly A. Farag,et al.  A unified approach for detection, visualization, and identification of lung abnormalities in chest spiral CT scans , 2003, CARS.

[10]  Stephen M. Smith,et al.  SUSAN—A New Approach to Low Level Image Processing , 1997, International Journal of Computer Vision.

[11]  L. Schwartz,et al.  Automatic detection of small lung nodules on CT utilizing a local density maximum algorithm , 2003, Journal of applied clinical medical physics.

[12]  S. M. Steve.  SUSAN - a new approach to low level image processing , 1997 .

[13]  Hugo Guterman,et al.  An adaptive neuro-fuzzy system for automatic image segmentation and edge detection , 2002, IEEE Trans. Fuzzy Syst..

[14]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[15]  Nisar Ahmed Memon,et al.  Segmentation of Lungs from CT Scan Images for Early Diagnosis of Lung Cancer , 2008 .

[16]  Robert Gwadera,et al.  Optimal segmentation using tree models , 2006, Sixth International Conference on Data Mining (ICDM'06).

[17]  E. Hoffman,et al.  Assessment of the pulmonary structure-function relationship and clinical outcomes measures: quantitative volumetric CT of the lung. , 1997, Academic radiology.

[18]  Gui Wei-hua,et al.  Medical Images Edge Detection Based on Mathematical Morphology , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[19]  Eric A. Hoffman,et al.  Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images , 2001, IEEE Transactions on Medical Imaging.

[20]  S. Armato,et al.  Computerized detection of pulmonary nodules on CT scans. , 1999, Radiographics : a review publication of the Radiological Society of North America, Inc.

[21]  Aristides Gionis,et al.  Algorithms for unimodal segmentation with applications to unimodality detection , 2006, Knowledge and Information Systems.

[22]  Jamshid Dehmeshki,et al.  Automated detection of lung nodules in CT images using shape-based genetic algorithm , 2007, Comput. Medical Imaging Graph..