Analysis of radiograph and detection of cardiomegaly

Miha Ilovar (2010) Analysis of radiograph and detection of cardiomegaly. EngD thesis.

Abstract

The purpose of this graduation thesis is to develop a procedure, which would automatically and reliably determine the presence of cardiomegaly, also known as heart enlargement, from a chest radiograph. The thesis initially presents an overview of some general facts about computer graphics and certain well-established methods and operators for image processing. The presented methods and the operators are: • application of convolution masks for image processing, • segmentation of images using a threshold, • use of edge detection operators (Canny, Roberts, Prewitt, Sobel and the difference of Gaussians). X-ray and radiograms are presented along with some general facts about the structure and the function of the heart. The attention is focused on the occurrence of heart enlargement, also known as cardiomegaly. A description of the procedure, which detects heart and lung boundaries and the corresponding boundary points with help from the modified methods mentioned above and some of my own approaches, follows. The result is the confirmation or refutation of cardiomegaly, which is based on the distances between appropriate points.

Item Type:

Thesis (EngD thesis)

Keywords:

convolution mask, intensity of an image, Canny operator, Roberts operator, Prewitt operator, Sobel operator, the difference of Gaussians, X-ray, radiograph, heart, cardiomegaly, heart enlargement.

Number of Pages:

Language of Content:

Slovenian

Mentor / Comentors:

Name and Surname	ID	Function
doc. dr. Tomaž Dobravec	258	Mentor

Link to COBISS:

http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=7690324)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

1063

Date Deposited:

16 Apr 2010 08:27

Last Modified:

13 Aug 2011 00:37

URI:

http://eprints.fri.uni-lj.si/id/eprint/1063

Actions (login required)

View Item