Imperial College London
Alternate

Miss Celia V Riga

Faculty of Medicine, Department of Surgery & Cancer

Honorary Clinical Senior Lecturer
 
 
 
//

Contact

 

c.riga

 
 
//

Location

 

1003Queen Elizabeth the Queen Mother Wing (QEQM)St Mary's Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Zheng:2018,
author = {Zheng, J-Q and Zhou, X-Y and Riga, C and Yang, G-Z},
publisher = {arXiv},
title = {3D path planning from a single 2D fluoroscopic image for robot assisted  fenestrated endovascular aortic repair},
url = {http://arxiv.org/abs/1809.05955v1},
year = {2018}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - The current standard of intra-operative navigation during FenestratedEndovascular Aortic Repair (FEVAR) calls for need of 3D alignments betweeninserted devices and aortic branches. The navigation commonly via 2Dfluoroscopic images, lacks anatomical information, resulting in longeroperation hours and radiation exposure. In this paper, a framework forreal-time 3D robotic path planning from a single 2D fluoroscopic image ofAbdominal Aortic Aneurysm (AAA) is introduced. A graph matching method isproposed to establish the correspondence between the 3D preoperative and 2Dintra-operative AAA skeletons, and then the two skeletons are registered byskeleton deformation and regularization in respect to skeleton length andsmoothness. Furthermore, deep learning was used to segment 3D pre-operative AAAfrom Computed Tomography (CT) scans to facilitate the framework automation.Simulation, phantom and patient AAA data sets have been used to validate theproposed framework. 3D distance error of 2mm was achieved in the phantom setup.Performance advantages were also achieved in terms of accuracy, robustness andtime-efficiency. All the code will be open source.
AU  - Zheng,J-Q
AU  - Zhou,X-Y
AU  - Riga,C
AU  - Yang,G-Z
PB  - arXiv
PY  - 2018///
TI  - 3D path planning from a single 2D fluoroscopic image for robot assisted  fenestrated endovascular aortic repair
UR  - http://arxiv.org/abs/1809.05955v1
UR  - http://hdl.handle.net/10044/1/72666
ER  -
Download