Lesions Diagnosis Using Gwo-Anfis Framework
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, Thiruvarur, (Tamil Nadu), India.
Manuscript received on February 05, 2019. | Revised Manuscript received on February 14, 2019. | Manuscript published on August 30, 2019. | PP: 3692-3696 | Volume-8 Issue-6, August 2019. | Retrieval Number: F9376088619/19©BEIESP | DOI: 10.35940/ijeat.F9376.088619
Open Access | Ethics and Policies | Cite | Mendeley
© 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: In this paper, liver abnormality is detected using an improved classification model that consists of series of process. The study reveals the liver condition to be normal or abnormal using the proposed system. The study uses both structural and statistical analysis, where both these analysis is combined with the process of classification. Initially, the noises are removed using Impulse Noise Removal and then the Segmentation is carried out using Gray Wolf Optimisation (GWO) algorithm. After the segmentation, the features are extracted through Local Binary Patters (LBP) Operator and then Artificial Neural Network Fuzzy Inference System (ANFIS) classifies the liver regions as malignant or benign. Various images collected from laboratories are used in both training and testing stages. The results are validated in terms of two different texture feature extractors namely, GLCM and LBP. The result shows that the proposed classifier using GLCM classifier obtains improved classified patterns than the existing methods.
Keywords: Liver Abnormalities, ANFIS Classifier, Normalized Gabor Filter, Co-occurrence Matrix, Local binary pattern.