Title: SQL based cardiovascular ultrasound image classification

Authors: S. Nandagopalan; Adiga B. Suryanarayana; T.S.B. Sudarshan; Dhanalakshmi Chandrashekar; C.N. Manjunath

Addresses: Department of Computer Science and Engineering, Amrita Vishwa Vidyapeetham, Amrita School of Engineering, Bangalore 560 004, India ' Tata Consultancy Services, Bangalore 560 066, India ' Department of Computer Science and Engineering, Amrita Vishwa Vidyapeetham, Amrita School of Engineering, Bangalore 560 035, India ' Sri Jayadeva Institute of Cardiovascular Sciences and Research, Bangalore 560 069, India ' Sri Jayadeva Institute of Cardiovascular Sciences and Research, Bangalore 560 069, India

Abstract: This paper proposes a novel method to analyze and classify the cardiovascular ultrasound echocardiographic images using Naïve-Bayesian model via database OLAP-SQL. Efficient data mining algorithms based on tightly-coupled model is used to extract features. Three algorithms are proposed for classification namely Naïve-Bayesian Classifier for Discrete variables (NBCD) with SQL, NBCD with OLAP-SQL, and Naïve-Bayesian Classifier for Continuous variables (NBCC) using OLAP-SQL. The proposed model is trained with 207 patient images containing normal and abnormal categories. Out of the three proposed algorithms, a high classification accuracy of 96.59% was achieved from NBCC which is better than the earlier methods.

Keywords: echocardiographic images; naive Bayesian classification; K-means; OLAP-SQL; active contour; SQL; cardiovascular images; ultrasound images; image classification; echocardiogram; data mining.

DOI: 10.1504/IJDMB.2013.053308

International Journal of Data Mining and Bioinformatics, 2013 Vol.7 No.3, pp.266 - 283

Received: 14 Sep 2011
Accepted: 14 Sep 2011

Published online: 12 Jun 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article