Open AccessAn Efficient Clustering Approach for Automatic Detection of Calcification in Low Dose Chest CT
Author(s) -
P. Tamijiselvy,
N. Kavitha,
K. Keerthana,
D. Menakha
Publication year - 2019
Publication title -
international journal of scientific research in computer science, engineering and information technology
Language(s) - English
Resource type - Journals
ISSN - 2456-3307
DOI - 10.32628/cseit195231
Subject(s) - cluster analysis , segmentation , fuzzy clustering , calcification , medicine , radiology , computer science , pattern recognition (psychology) , data mining , artificial intelligence
The degree of aortic calcification has been appeared to be a risk pointer for vascular occasions including cardiovascular events. The created strategy is fully automated data mining algorithm to segment and measure calcification using Low-dose Chest CT in smokers of age 50 to 70 .The identification of subjects with increased cardiovascular risk can be detected by using data mining algorithms. This paper presents a method for automatic detection of coronary artery calcifications in low-dose chest CT scans using effective clustering algorithms with three phases as Pre-Processing, Segmentation and clustering. Fuzzy C Means algorithm provides accuracy of 80.23% demonstrate that Fuzzy C means detects the Cardio Vascular Disease at early stage.