Optimization Based Liver Contour Extraction of Abdominal CT Images

This paper introduces computer aided analysis system for diagnosis of liver abnormality in abdominal CT images. Segmenting the liver and visualizing the region of interest is a most challenging task in the field of cancer imaging, due to small observable changes between healthy and unhealthy liver. In this paper, hybrid approach for automatic extraction of liver contour is proposed. To obtain optimal threshold, the proposed work integrates segmentation method with optimization technique in order to provide better accuracy. This method uses bilateral filter for preprocessing and Fuzzy C means clustering (FCM) for segmentation. Mean Grey Wolf Optimization technique (mGWO) has been used to get the optimal threshold. This threshold is used for segmenting the region of interest. From the segmented output, largest connected region are identified using Label Connected Component (LCC) algorithm. The effectiveness of proposed method is quantitatively evaluated by comparing with ground truth obtained from radiologists. The performance criteria like dice coefficient, true positive error and misclassification rate are taken for evaluation.

[1]  K. Mala,et al.  Neural Network based Texture Analysis of Liver Tumor from Computed Tomography Images , 2008 .

[2]  M. Jayanthi,et al.  Extracting the Liver and Tumor from Abdominal CT Images , 2014, 2014 Fifth International Conference on Signal and Image Processing.

[3]  S. S. Kumar,et al.  Automatic liver and lesion segmentation: a primary step in diagnosis of liver diseases , 2011, Signal, Image and Video Processing.

[5]  Jayanthi Muthuswamy.  Segmentation of Liver Abnormality based on Label Connected Component Algorithm , 2017 .

[6]  Andrew Lewis,et al.  Grey Wolf Optimizer , 2014, Adv. Eng. Softw..

[7]  Sonali Patil,et al.  Preprocessing To Be Considered For MR and CT Images Containing Tumors , 2012 .

[8]  J. Samuel Manoharan,et al.  A Survey on the Preprocessing Techniques of Mammogram for the Detection of Breast Cancer , 2011 .

[9]  Samuel Kadoury,et al.  Liver segmentation: indications, techniques and future directions , 2017, Insights into Imaging.

[10]  Amel Benazza-Benyahia,et al.  A Nonlinear Stein-Based Estimator for Multichannel Image Denoising , 2007, IEEE Transactions on Signal Processing.

[11]  Leandro dos Santos Coelho,et al.  Multi-objective grey wolf optimizer: A novel algorithm for multi-criterion optimization , 2016, Expert Syst. Appl..

[12]  Sakesun Suthummanon,et al.  Initial Optimal Parameters of Artificial Neural Network and Support Vector Regression , 2018, International Journal of Electrical and Computer Engineering (IJECE).

[13]  M. Jayanthi,et al.  Comparative study of different techniques used for medical image segmentation of liver from abdominal CT scan , 2016, 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET).

[14]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[15]  Fabrizio Russo.  A method for estimation and filtering of Gaussian noise in images , 2003, IEEE Trans. Instrum. Meas..

[16]  Narinder Singh,et al.  A Modified Mean Gray Wolf Optimization Approach for Benchmark and Biomedical Problems , 2017, Evolutionary bioinformatics online.

[17]  Urvinder Singh,et al.  Modified Grey Wolf Optimizer for Global Engineering Optimization , 2016, Appl. Comput. Intell. Soft Comput..