master's thesis
Cardiac CT heart segmentation with ITK

Marija Habijan (2015)
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing
Metadata
TitleSegmentacija srca iz CT snimaka pomoću ITK
AuthorMarija Habijan
Mentor(s)Irena Galić (thesis advisor)
Hrvoje Leventić (thesis advisor)
Abstract
Osnovni cilj rada je predstaviti sustav za segmentaciju srca iz CT slika kardiovaskularnog sustava. Predstavljena je implementacija triju metoda za segmentaciju medicinskih slika. Implementirani sustav sastoji se od dva osnovna dijela. Prvi dio je predobrada kojim se slike pripremaju za drugi dio: korak segmentacije. Opisane su teorijske osnove geometrijski deformabilnih modela, sa naglaskom na fast marching metodu, metodu detekcije oblika te metodu geodetskih aktivnih kontura. Implementacija navedenih metoda provedena je u programskom jeziku C++ uz pomoć biblioteka iz alata Insight Toolkit. Prikazani su dobiveni rezultati predobrade i segmentacije za svaku od navedenih metoda. Na kraju je prikazana usporedba dobivenih rezultata segmentacije.
Keywordsdigital image analysis heart segmentation fast marching level-set method shape detection levelset method geodesic active contours
Parallel title (English)Cardiac CT heart segmentation with ITK
Committee MembersIrena Galić (committee chairperson)
Josip Job (committee member)
Hrvoje Leventić (committee member)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Lower level organizational unitsDepartment of Software Engineering
Chair of Visual Computing
PlaceOsijek
StateCroatia
Scientific field, discipline, subdisciplineTECHNICAL SCIENCES
Computing
Process Computing
Study programme typeuniversity
Study levelgraduate
Study programmeGraduate University Study Programme in Computer Engineering
Academic title abbreviationmag.ing.comp.
Genremaster's thesis
Language Croatian
Defense date2015-10-12
Parallel abstract (English)
The main goal of this paper is segmentation of the heart from cardiac CT images. The implementation of three methods for medical images segmentation is introduced in the paper. The action of implemented system is based on two main stages. First stage is preprocessing of the input images in which images are prepared for second stage: segmentation. Theoretical fundamentals of geometrical deformable models, with the emphasis on fast marching, shape detection and geodesic active contours are given. The system is implemented in programming language C++ with the help of libraries from Insight Toolkit. The results of efficiency are processed and displayed on actual images. Finally, comparison of obtained results is shown.
Parallel keywords (Croatian)digitalna analiza slike segmentacija srca fast marching level-set metoda metoda detekcije oblika geodetske aktivne konture
Resource typetext
Access conditionOpen access
Terms of usehttp://rightsstatements.org/vocab/InC/1.0/
URN:NBNhttps://urn.nsk.hr/urn:nbn:hr:200:473515
CommitterAnka Ovničević