20.500.12556/RUL-147080 Avtomatska segmentacija maternice v 3D ultrazvočnih podatkih Automatic uterine segmentation in 3D ultrasound data Magistrska naloga predstavlja metodo za avtomatsko segmentacijo maternic v 3D ultrazvočnih podatkih ter izdelavo referenčnega modela zdrave maternice. Delo je nastalo v okviru raziskave NURSE, katere cilj je določiti merila za normalno maternico ter ugotoviti morebitna odstopanja pri ženskah z neplodnostjo in spontanimi splavi. V tej nalogi so predstavljeni globoki nevronski model za avtomatsko segmentacijo maternic, ki dosega natančnost $0.899$ (Diceov koeficient), algoritem za poravnavo segmentiranih 3D modelov maternic ter vizualizacija povprečnega modela maternice. S to nalogo prav tako objavljamo javno podatkovno zbirko označenih volumetričnih ultrazvočnih posnetkov maternic. Predlagane metode in ugotovitve zagotavljajo dragocen vpogled v analizo oblike maternice in prispevajo k razvoju področja ginekologije. This master's thesis presents a method for the automatic segmentation of uteri in 3D ultrasound data and a reference model of a healthy uterus. The work is part of the NURSE research, which aims to determine the criteria for a normal uterus and identify possible deviations in women with infertility and repeated miscarriages. In this work, we present a deep neural model for the automatic segmentation of the uterus, which achieved a Dice score of 0.899, an algorithm for the alignment of segmented 3D shapes, and visualization of the average model of the uterus obtained with the presented methods. We will also publish a public database of annotated volumetric ultrasound data. The proposed methods and findings provide valuable insights into the analysis of uterine shape and contribute to the field of gynecology. ultrazvok maternica segmentacija poravnava ultrasound uterus segmentation alignment true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2023-06-22 16:25:00 2023-06-22 16:25:08 2023-07-14 05:55:53 0000-00-00 00:00:00 2023 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 158061827 35342 158061827 Bones_Eva_-_Avtomatska_segmentacija_maternice_v_3D_ultrazvocnih_podatkih.pdf Bones_Eva_-_Avtomatska_segmentacija_maternice_v_3D_ultrazvocnih_podatkih.pdf 1 8AA7FF62A81183490F3F9EB0723B81BA 291dd8f281db919563566e2b4b531614cace826e3d473c438755a817e3ee6bb6 37a61114-1108-11ee-a314-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=170438 Fakulteta za računalništvo in informatiko 0 0 0