Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/4304
Title: Efficient and automated echocardiographic image analysis through data mining techniques
Researcher: Nandagopalan, S
Guide(s): Sudarshan, T S B
Adiga, B S
Keywords: Engineering
Echo Image Analysis System
Ultrasound
Echocardiographic Image
Upload Date: 17-Aug-2012
University: Amrita Vishwa Vidyapeetham (University)
Completed Date: April 2012
Abstract: The main purpose of this research work is to provide bioinformatics way of support to reduce the heart diseases globally. The four most prominent noncommunicable diseases (NCDs) are cardiovascular diseases, diabetes, cancer, and chronic obstructive pulmonary diseases. The most common cause of death in the United States is the heart disease with 28.5% based on CDC/NHS, National Vital Statistics System [Roger, 2011]. In Jayadeva Cardiological Hospital, Bangalore, India alone approximately 10000 heart patients are treated every month, whereas about every 25 seconds, an American will have a coronary event. Echocardiography is one of the popular techniques in human heart diagnosis for the study of heart abnormalities. Generally, these images provide a wealth of clinically relevant and useful information, including the size and shape of the heart, its pumping capacity and the location and extent of any damage to its tissues. It is especially useful for assessing stenosis and regurgitation diseases of the heart. However, the current clinical practice requires manual intervention in both imaging and in interpretation. The ultrasound operator has to manually demarcate major anatomical structures like Left Ventricle (LV), Right Ventricle (RV), Left Atrium (LA), and Right Atrium (RA) and computes numerical quantities such as length, diameter, area, fractional shortening, stroke volume, ejection fraction, etc., from these images. Because of the fact that the image is analyzed manually it purely depends on the expertise of the operator in detecting the heart cavities accurately. Any error caused in the image quantification will lead to incorrect diagnosis. The current thesis aims at developing an implementable model that can analyze the echo images of a particular patient automatically and offer clinically relevant data for making appropriate decisions. For this, a series of steps need to be accomplished starting from acquiring proper echo images of the patient and up to complex data mining and image processing tasks.
Pagination: 304p.
URI: http://hdl.handle.net/10603/4304
Appears in Departments:Department of Computer Science and Engineering (Amrita School of Engineering)

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File48.95 kBAdobe PDFView/Open
02_certificate.pdf32.85 kBAdobe PDFView/Open
03_declaration.pdf10.48 kBAdobe PDFView/Open
04_contents.pdf147.59 kBAdobe PDFView/Open
05_acknowledgements.pdf55.37 kBAdobe PDFView/Open
06_list of figures.pdf125.91 kBAdobe PDFView/Open
07_list of tables.pdf77.84 kBAdobe PDFView/Open
08_list of symbols.pdf81.84 kBAdobe PDFView/Open
09_list of abbreviations.pdf57.67 kBAdobe PDFView/Open
10_abstract.pdf59.46 kBAdobe PDFView/Open
11_chapter 1.pdf501.84 kBAdobe PDFView/Open
12_chapter 2.pdf1.15 MBAdobe PDFView/Open
13_chapter 3.pdf985.18 kBAdobe PDFView/Open
14_chapter 4.pdf1.03 MBAdobe PDFView/Open
15_chapter 5.pdf1.13 MBAdobe PDFView/Open
16_chapter 6.pdf694.23 kBAdobe PDFView/Open
17_chapter 7.pdf649.08 kBAdobe PDFView/Open
18_chapter 8.pdf533.57 kBAdobe PDFView/Open
19_chapter 9.pdf901.65 kBAdobe PDFView/Open
20_chapter 10.pdf2.28 MBAdobe PDFView/Open
21_appendix.pdf150.34 kBAdobe PDFView/Open
22_references.pdf214.71 kBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.