Content Based Retrieval of Liver Images for Computer Aided Diagnosis
Aravinda H L1, Sudhamani M V2
1Mr. Aravinda H L*, Research Scholar, Jain (Deemed to be University), Asst. Professor, Department of Telecommunication Engg., Dr. Ambedkar Institute of Technology, Bengaluru, India.
2Dr. Sudhamani M V, Professor & HoD, Department of Information Science & Engg., RNS Institute of Technology, Bengaluru, India.
Manuscript received on July 20, 2019. | Revised Manuscript received on August 10, 2019. | Manuscript published on August 30, 2019. | PP: 555-562 | Volume-8 Issue-6, August 2019. | Retrieval Number: F8059088619/2019©BEIESP | DOI: 10.35940/ijeat.F8059.088619
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: Liver cancer is a serious disease caused by a variety of factors that damage the liver region. Early detection of this disease is necessary to diagnose and to cure it completely. Enormous increase in medical database images has lead to development of Content Based Image Retrieval (CBIR) system to retrieve relevant liver images from medical database consisting of abdominal Computed Tomography (CT) images. In the proposed method Content Based Medical Image Retrieval (CBMIR) system is designed to search and retrieve relevant liver images from medical image database. Adaptive Region Growing Algorithm (ARGA) and Simple Linear Iterative Clustering (SLIC) are used for liver and tumor segmentation. Features are extracted using Gray Level Co-occurrence Matrix (GLCM), Average Correction High order Local Autocorrelation Coefficients (ACHLAC) and Legendre Moments (LM). Based on the distance metric, distances between extracted features of query image and images in the database are measured. Euclidean distance metric is used to retrieve relevant medical images.
Keywords: Liver tumor, Adaptive Region Growing Algorithm (ARGA), Simple Linear Iterative Clustering (SLIC), Gray Level Co-occurrence Matrix (GLCM), Average Correction High order Local Autocorrelation Coefficient (ACHLAC) and Legendre Moments (LM), Euclidean Distance.