Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

AUTOMATED IDENTIFICATION OF CALCIUM IN MITRAL AND AORTIC VALVES

Wikman, Lisa LU (2020) In Master's Theses in Mathematical Sciences FMAM05 20201
Mathematics (Faculty of Engineering)
Abstract (Swedish)
Calcification of the mitral and aortic valves is one of the main precursors to heart valve diseases. Calcified valves and coronary vessels is also an indication of risk for future cardiac events such as cardiac infarct(1)(2).
During this master thesis project, a program for automatic identification and quantification of calcium in the mitral and aortic valves in CT image stacks was implemented. The program can differentiate between the aorta valve and the mitral valve and give separate scores for the valves as well as a total score which is the sum of the mitral and aorta score. The program is based on image analysis and reached a sensitivity of 100 % and a specificity of 85.4 % when the limit ≥ 100 Agatston units was used for identifying... (More)
Calcification of the mitral and aortic valves is one of the main precursors to heart valve diseases. Calcified valves and coronary vessels is also an indication of risk for future cardiac events such as cardiac infarct(1)(2).
During this master thesis project, a program for automatic identification and quantification of calcium in the mitral and aortic valves in CT image stacks was implemented. The program can differentiate between the aorta valve and the mitral valve and give separate scores for the valves as well as a total score which is the sum of the mitral and aorta score. The program is based on image analysis and reached a sensitivity of 100 % and a specificity of 85.4 % when the limit ≥ 100 Agatston units was used for identifying patients at risk in a comparison of 49 cases with the existing manual program syngo.via. The program can automatically go through and identify calcium in a large amount of data, and due to the high prevalence of noise it is also possible to manually go back and check and rescore images if desired. (Less)
Please use this url to cite or link to this publication:
author
Wikman, Lisa LU
supervisor
organization
course
FMAM05 20201
year
type
H2 - Master's Degree (Two Years)
subject
publication/series
Master's Theses in Mathematical Sciences
report number
LUTFMA-3424-2020
ISSN
1404-6342
other publication id
2020:E52
language
English
id
9009981
date added to LUP
2020-06-29 14:30:06
date last changed
2020-06-29 14:30:06
@misc{9009981,
  abstract     = {{Calcification of the mitral and aortic valves is one of the main precursors to heart valve diseases. Calcified valves and coronary vessels is also an indication of risk for future cardiac events such as cardiac infarct(1)(2).
During this master thesis project, a program for automatic identification and quantification of calcium in the mitral and aortic valves in CT image stacks was implemented. The program can differentiate between the aorta valve and the mitral valve and give separate scores for the valves as well as a total score which is the sum of the mitral and aorta score. The program is based on image analysis and reached a sensitivity of 100 % and a specificity of 85.4 % when the limit ≥ 100 Agatston units was used for identifying patients at risk in a comparison of 49 cases with the existing manual program syngo.via. The program can automatically go through and identify calcium in a large amount of data, and due to the high prevalence of noise it is also possible to manually go back and check and rescore images if desired.}},
  author       = {{Wikman, Lisa}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master's Theses in Mathematical Sciences}},
  title        = {{AUTOMATED IDENTIFICATION OF CALCIUM IN MITRAL AND AORTIC VALVES}},
  year         = {{2020}},
}