| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document

Title:SEGMENTIRANJE ULTRAZVOČNIH VOLUMNOV JAJČNIKOV S 3D SEGMENTACIJSKO METODO RASTI REGIJ
Authors:Klančnik, Maja (Author)
Potočnik, Božidar (Mentor) More about this mentor... New window
Files:.pdf UNI_Klancnik_Maja_2013.pdf (19,54 MB)
 
Language:Slovenian
Work type:Bachelor thesis/paper (mb11)
Typology:2.11 - Undergraduate Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V diplomski nalogi je predstavljena nova 3D segmentacijska metoda rasti regij za prepoznavanje jajčnih mešičkov na 3D ultrazvočnih posnetkih jajčnikov. Primarni cilj diplomske naloge je izdelava aplikacije za obdelavo 3D ultrazvočnih volumnov jajčnikov in vizualizacijo dobljenih rezultatov. Algoritem je povsem samodejen in sestavljen iz štirih faz. Najprej se identificirajo začetne homogene regije. Nato se izgradi osmiško drevo, ki vsebuje ustrezne podatke o ultrazvočnih posnetkih. Temu sledi faza rasti regij v 3D s semeni, ki se uravnava s statistiko sivinskih vrednosti vokslov in uteženim gradientom. V zadnji fazi, ekstrakciji jajčnih mešičkov, se določijo regije, ki najverjetneje ustrezajo dejanskim jajčnim mešičkom. Algoritem smo preizkusili na petih 3D ultrazvočnih posnetkih jajčnih mešičkov. Odstotek pravilno prepoznanih jajčnih mešičkov znaša 72,3 %.
Keywords:rast regij v 3D, 3D ultrazvočni posnetki, segmentacija jajčnih mešičkov, osmiško drevo, ultrazvok v ginekologiji
Year of publishing:2013
Publisher:[M. Klančnik]
Source:Maribor
UDC:004.932(043.2)
COBISS_ID:17149974 Link is opened in a new window
NUK URN:URN:SI:UM:DK:V8V8W7WJ
Views:973
Downloads:65
Metadata:XML RDF-CHPDL DC-XML DC-RDF
Categories:KTFMB - FERI
:
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:SEGMENTATION OF OVARIAN ULTRASOUND VOLUMES USING 3D REGION GROWING SEGMENTATION
Abstract:A new 3D region growing segmentation method for detecting ovarian follicles in ovarian ultrasound volumes is presented in this diploma work. The primary goal of the diploma work is to create an application for processing ultrasound volumes of ovarian follicles and for visualizing obtained results. The algorithm is fully automated and comprises four stages. First, initial homogenous regions are identified. Then, an octree which holds all relevant information about the ultrasound volumes is generated. Following is the 3D seeded region growing stage controlled by voxel grey-level statistics and a weighted gradient. In the last stage, ovarian follicle extraction, regions most likely corresponding to actual ovarian follicles are determined. The algorithm was tested on five ovarian ultrasound volumes. The percentage of correctly recognized ovarian follicles amounts to 72.3%.
Keywords:3D region growing, ultrasound images, ovarian follicle segmentation, octree, ultrasound in gynecology


Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica