Primerjalna analiza postopkov projekcije 3D medicinskih slik

OSREDKAR, JAN (author), Špiclin, Žiga (mentor)

Invazivnost kirurških posegov lahko zmanjšamo na podlagi načrtovanja na predoperativnih 3D medicinskih slikah in z realnočasovnim povratno-zančnim slikovnim vodenjem na osnovih žive 2D slike. Če želimo predoperativne načrte prenesti v prostor bolnika na operacijski mizi, potem je potrebno predoperativno 3D sliko prostorsko poravnati na medoperativno 2D sliko. V magistrski nalogi kvantitativno ovrednotite in medsebojno primerjajte lastnosti različnih uveljavljenih postopkov projekcije 3D slik za namen poravnave pred- in med-operativno zajetih 3D in 2D medicinskih slik.

• Language: Slovenian
• Keywords: projekcijski algoritmi, slikovno voden klinični poseg, pospešitev algoritmov na GPE
• Work type: Master's thesis/paper
• Organization: FE - Faculty of Electrical Engineering
• Year: 2020
• PID: 20.500.12556/RUL-116838
• Publication date in RUL: 12.06.2020

Secondary language

• Language: English
• Title: Comparative analysis of 3D image projection algorithms

Abstract

Invasiveness of surgical interventions can be mitigated by planning on preoperative 3D medical images and by real-time closed-loop visual guidance based on live 2D image during the intervention. Mapping the information extracted from 3D image into patient space requires spatial alignment of pre-interventional 3D and intra-interventional 2D images. The aim of this thesis is to quantitatively assess and comparatively evaluate the performances of several state-of-the-art 3D-to-2D image projection methods.

• Keywords: projection algorithms, image guided surgery, algotihm acceleration on GPU