1. TUMOR BURDEN ANALYSIS ON CT BY AUTOMATED LIVER AND TUMOR SEGMENTATION RAMSHEEJA.RR Roll : No 19 Guide SREERAJ.R ( Head Of Department, CSE)

2. OBJECTIVE  Aim to the developments of the technique to constitute a computer-aided system for the fully automated integrated analysis of the liver  Study various methods of liver cancer detection  Develope a method to detect liver cancer in early

3. INTRODUCTION  Liver has many important functions  Liver cancer is 4 th most common malignancy in the world  Computed Tomography (CT) scans are a common tool for diagnosis

4. PROBLEM STATEMENT  Liver Segmentation is an important first step for Computer- Aided Diagnosis (CAD)  Difficulties associated with liver segmentation  Time consuming  Similarities to other organs

5. ADVANTAGES - AUTOMATED METHODS  The reproducibility of results  Not subjected to user interaction  Faster  Readily available  Reduce errors

6. iInput image Preprocessing Liver tumor segmentation Liver segmentation Classification Feature extraction Normal Abnormal SYSTEM ARCHITECTURE

7. LIVER SEGMENTATION[5] [3]A. M. Mharib, A. R. Ramli, S. Mashohor, R. B. Mahmood, “Survey on Liver CT image Segmentation Methods” in Artif Intell Rev 37: pp. 83-95 Springer 2012.  Segmentation techniques which are mainly automatic in nature.  Liver image segmentation techniques can be divided in two classes  semi-automatic  fully automatic methods  Graph Cuts segmentation algorithm is used

8. SEGMENTATION WITH GRAPH CUT

9. FEATURE EXTRACTION[4] [4]Statistical Texture Measures Computed from Gray Level Coocurrence Matrices Fritz Albregtsen Image Processing Laboratory Department of Informatics University of Oslo November 5, 2008  For feature extraction here use The GLCM Algorithm  Gray Level Co-occurrence Matrix  Way of extracting second order statistical texture features Energy, Entropy, Contrast, Homogeneity Correlation

10. FEATURE CLASSIFICATION[5]  Use Support Vector Machine (SVM)classifier  Binary classifier  Machine Learning Algorithm  Predict about the features  To improve classification SVM is trained by using weighted features for data classification [5]K. Kramer, L. Hall, D. Goldgof, “Fast Support Vector Machines for Continuous Data,” IEEE Transactions on Systems, Man and Cybernatics, vol. 39, no. 4, pp. 989-1001, 2009.

12. LIVER TUMOR SEGMENTATION[6]  An efficient fuzzy c-mean based segmentation algorithm to extract tumor region  FCM is a soft segmentation method which retains more information from input image than hard segmentation methods  Efficient than existing segmentation methods  To improve segmentation we can use Enhanced FCM [6]a International Journal of Computer Applications (0975 – 8887) Volume 59– No.5, December 2012 40 Performance Improvement of Fuzzy C-mean Algorithm for Tumor Extraction in MR Brain Images

13. CONCLUSION  The automated segmentation of liver is addressed first  Here segment the tumor and classifies about the image  The technique is improved significantly and the segmentation of large tumor  Reduce the number of false tumor detection

14. REFERENCES [1] D. Shen,W.Wong, and H.S.H. Ip, “Affine-invariant image retrieval by correspondence matching of shapes,”Image and Vision Computing, vol. 17, pp. 489– 499,1999. [2] Y. Boykov and V. Kolmogorov, “An experimental comparison of mincut/max- flow algorithms for energy minimization in vision,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 26, no. 9, pp. 1124–1137, Sep.2004 [3] P. Campadelli, E. Casiraghi, and A. Esposito, “Liver segmentation from computed tomography scans: A survey and a new algorithm,”Artif. Intell. Med., vol. 45, pp. 185– 196, 2009. [4] Shawn Lankton, Allen Tannenbaum “Localizing Region-Based Active Contours” IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 17, NO. 11, NOVEMBER 2008. Published in final edited form as:IEEE Trans Image Process. 2008 November; 17(11): 2029–2039.

15. REFERENCES [5]A. M. Mharib, A. R. Ramli, S. Mashohor, R. B. Mahmood, “Survey on Liver CT image Segmentation Methods” in Artif Intell Rev 37: pp. 83-95 Springer 2012. [6] Yueyi I. Liu “Bayesian classifier for differentiating malignant and benign nodules using sonography features” AMIA 2008 symposium proceeding page- 419. [7] M. Mignotte. Segmentation by fusion of histogram-based k-means clusters in different color spaces. IEEE Transactions on Image Pro- cessing, 17(5):780–787, 2008. [8] S. Jagannath et al., “Tumor burden assessment and its implication for a prognostic model in advanced diffuse large-cell lymphoma,” J. Clin. Oncol., vol. 4, no. 6, pp. 859–865, 1986. [9] Viet Dzung Nguyen, DucThuan Nguyen, TienDzung Nguyen and Van Thanh Pham,“An automated method to segment and classify masses in mammograms”,International Journal of Computer and Information Engineering, 52, 2009

16. THANK YOU