A fast intensity based non-rigid 2D-3D registration using statistical shape models with application in radiotherapy

Christoph Bodensteiner, Cristina Darolti, Achim Schweikard

Abstract

In this paper we present a novel fast method for the non-rigid registration of a few X-ray projections with CT data. The method involves non-parametric non-rigid registration techniques for the difficult 2D-3D case, combined with knowledge of probable deformations modeled as active shape models (ASMs). ASMs allow us to cope with as few as two projections by regularizing the registration process. The model is learned from deformations observed during respiration in a 4D-CT. This method can be applied in motion compensated radiation therapy to eliminate the need for fiducial implantation. We designed a fast C++ implementation for our method in order to make it practicable. Our tests on real 4D-CT data achieved registration times of 2-4 minutes using a desktop PC*.

Original languageEnglish
Title of host publicationImage Processing: Algorithms and Systems VII
Number of pages7
PublisherSPIE
Publication date16.06.2009
Article number72450G
ISBN (Print)978-081947495-7
DOIs
Publication statusPublished - 16.06.2009
EventImage Processing: Algorithms and Systems VII - San Jose, United States
Duration: 19.01.200922.01.2009
Conference number: 76102

Fingerprint

Dive into the research topics of 'A fast intensity based non-rigid 2D-3D registration using statistical shape models with application in radiotherapy'. Together they form a unique fingerprint.

Cite this