Fuzzy entropy based optimization of clusters for the segmentation of lungs in CT scanned images
- 327 Downloads
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.
KeywordsComputer aided diagnosis Mathematical morphology Segmentation Thresholding
Unable to display preview. Download preview PDF.
- 1.Cilva AC, Cezar P, Gattas M (2004) Diagnosis of Lung Nodule using Gini Coefficient and skeletoniz in computerized Tomography images. In: ACM symposium on applied computing, Nicosia, Cyprus, pp 243–248Google Scholar
- 2.Dhawan AP (2003) Medical image analysis IEEE press series in biomedical engineering. Wiley, LondonGoogle Scholar
- 3.El-Baz A, Farag AA, Falk R, La Rocca R (2002) Detection, visualization and identification of lung abnormalities in chest spiral CT scan: Phase-I. In: International conference on biomedical engineering, Cairo, EgyptGoogle Scholar
- 4.El-Baz A, Farag AA, Falk R, La Rocca R (2003) A unified approach for detection, visualization and identification of lung abnormalities in chest spiral CT scan. In: Proceedings of computer assisted radiology and surgery, LondonGoogle Scholar
- 5.Zhao B, Gamsu G, Ginsberg MS (2003) Automatic detection of small lung nodules on CT utilizing a local density maximum algorithm. J Appl Clin Med Phys 4(3)Google Scholar
- 14.Antonelli M, Lazzerini B, Marcelloni F (2005) Segmentation and reconstruction of the lung volume in CT images. In: 20th annual ACM symposium on applied computing, vol I. Santa Fe, New Mexico, pp 255–259, 13–17 MarchGoogle Scholar
- 15.Memon NA, Mirza AM, Gilani SAM (2006) Deficiencies of Lung segmentation techniques using CT scan images for CAD. In: Proceedings of world academy of science, engineering and technology, vol 14Google Scholar
- 16.Memon NA, Mirza AM, Gilani SAM (2006) Segmentation of lungs from CT scan imges for early diagnosis of lung cancer. In: Proceedings of world academy of science, engineering and technology, vol 14Google Scholar
- 20.Armato SG III, Giger ML, Moran CJ (1999) Computerized detection of pulmonary nodules on CT scans. RadioGraphics 19: 1303–1311Google Scholar
- 21.Hu S, Huffman EA, Reinhardt JM (2001) Automatic Lung Segementation for Accurate Quantitiation of Volumetric X-Ray CT images. IEEE Trans Med Imaging 20(6)Google Scholar
- 24.Yu-qian Z, Wei-hua G, Zhen-cheng1 C, Jing-tian1 T, Ling-yun L (1997) Medical Images Edge Detection Based on Mathematical Morphology. In: Proceedings of the IEEE engineering in medicine and biology 27th annual conference Shanghai, ChinaGoogle Scholar