Paper Info
Title
Model-based fusion of CT and non-contrasted 3D C-arm CT: Application to transcatheter valve therapies.
Abstract
In recent years transcatheter valve therapies are beginning to replace invasive surgical procedures. As there is no direct view and access to the affected anatomy advanced imaging techniques such as 3D rotational angiography (C-arm CT) and real-time fluoroscopy are used for intra-operative guidance. However, intra-operative modalities have limited image quality of the soft tissue and a reliable assessment of the cardiac anatomy can only be made by injecting contrast agent, which is harmful to the patient and requires complex acquisition pro-tocols. We propose a novel method to align pre-operative and intra-operative data by using surrogate anatomical structures which are visible in both modalities without adding contrast agent. The trachea bifurcation model is used as a surrogate structure and the model parameters are estimated using robust machine learning algorithms. High quality patient specific models can be extracted from the pre-operative CT and mapped to the intra-operative 3D C-arm CT for guidance. In addition we learn a weighted mapping function for the trachea bifurcation model extracted from the pre-operative and intra-operative images which minimizes the mapping error in respect to the anatomy of interest. Experiments performed on 28 patient pairs of CT and contrasted 3D C-arm CT data sets assure an accuracy of the mapped aortic valve model of 9.08 +/- 7.31deg and 7.57 +/- 3.22mm.
Year
DOI
Venue
2012
10.1109/ISBI.2012.6235774
ISBI
Keywords
Field
DocType
bifurcation,biological tissues,cellular biophysics,computerised tomography,diagnostic radiography,image fusion,learning (artificial intelligence),medical image processing,physiological models,prosthetics,3D rotational angiography,anatomical structures,anatomy advanced imaging techniques,aortic valve model,cardiac anatomy,complex acquisition protocols,contrast agent,high quality patient specific models,intraoperative 3D C-arm CT,intraoperative imaging,invasive surgical procedures,mapping error,model parameters,model-based fusion CT,noncontrasted 3D C-arm CT,preoperative imaging,real-time fluoroscopy,robust machine learning algorithms,soft tissue,trachea bifurcation,trachea bifurcation model,transcatheter valve therapies,weighted mapping function
Modalities,Rotational angiography,Data set,Image fusion,Computer science,Image quality,Fluoroscopy,Aortic valve,Radiology,Soft tissue
Conference
Citations 
PageRank 
References 
0
0.34
0
Authors
8
Name
Order
Citations
PageRank
Sasa Grbic18213.77
Christian Gesell200.34
Razvan Ioan Ionasec321326.71
Matthias John411911.36
Jan M. Boese5536.15
Joachim Hornegger61734190.62
Nassir Navab76594578.60
Dorin Comaniciu88389601.83