Diagnosis of Liver Images Lesions in Mr Images Using Improved Segmentation and Classification Task
M. Babu1, G. Nanthakumar2

1M. Babu, Research Scholar, Sri Satya Sai University of Technology & Medical Sciences, (Madhya Pradesh), India.
2Dr. G. Nanthakumar, Associate Professor, Anjalai Ammal Mahalingam Engineering College, (Tamil Nadu), India.
Manuscript received on 05 June 2019 | Revised Manuscript received on 30 June 2019 | Manuscript Published on 04 July 2019 | PP: 748-752 | Volume-8 Issue-1S4 June 2019 | Retrieval Number: A11380681S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Detection of liver abnormalities is a deep study that reflects the condition of liver during the time of liver disease. The diagnosis reveals the condition of liver in human body, however earlier detection of images during medical diagnosis is still a tough task with texture analysis and classification process. Hence, in this study we reveal the condition of liver as normal or abnormal based on the analysis done using the proposed method. The proposed system identifies the condition of liver through two stages: structural and statistical analysis and classification process. The former one is carried out with Gabor Gray Level – Local Binary Patterns (GGL-LBP) that provides the structural texture representation of a liver image. The latter one uses various machine learning classifiers to test the proposed method that includes Artificial Neural Network Fuzzy Inference System (ANFIS) is used for classification process. The set of images are used for training and testing the classifier using the structural features. The proposed classification method is evaluated using 225 test records and it is tested against conventional methods in terms of accuracy, sensitivity and specificity. The experimental validation shows that proposed method with ANFIS classifier acquires improved accuracy than other classifiers, namely Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes (NB), Decision Tree (DT) and Linear Discriminant Analysis (LDA).
Keywords: Liver Abnormalities, ANFIS Classifier, Normalized Gabor Filter, Co-occurrence Matrix, Local binary Pattern.
Scope of the Article: Image Security