CNN-based real-time 2D-3D deformable registration from a single X-ray projection

Purpose: The purpose of this paper is to present a method for realtime 2D-3D non-rigid registration using a single fluoroscopic image. Such a method can find applications in surgery, interventional radiology and radiotherapy. By estimating a three-dimensional displacement field from a 2D X-ray image...

Full description

Bibliographic Details

Published in:	Journal of clinical medicine Vol. 11; no. 7
Main Authors:	Lecomte, Francois, Dillenseger, Jean-Louis, Cotin, Stéphane
Format:	Journal Article
Language:	English
Published:	MDPI 01.03.2024
Subjects:	Computer Science Image Processing Image and Video Processing (eess.IV) FOS: Electrical engineering 2D-3D registration 2D-3D registration deformation deep learning real-time fluoroscopy diffeomorphism diffeomorphism deep learning electronic engineering Computer Vision and Pattern Recognition (cs.CV) FOS: Computer and information sciences real-time deformation fluoroscopy information engineering
ISSN:	2077-0383, 2077-0383
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!