Paper Info
Title
Entropy-Based, Multiple-Portal-to-3DCT Registration for Prostate Radiotherapy Using Iteratively Estimated Segmentation
Abstract
In external beam radiotherapy (EBRT), patient setup veri- flcation over the entire course of fractionated treatment is necessary for accurate delivery of specifled dose to the tumor. We develop an informa- tion theoretic minimax entropy registration framework for patient setup veriflcation using portal images and the treatment planning 3D CT data set. Within this framework we propose to simultaneously and iteratively segment the portal images and register them to the 3D CT data set to achieve robust and accurate estimation of the pose parameters. Appropri- ate entropies are evaluated, in an iterative fashion, to segment the portal images and to flnd the registration parameters. Earlier, we reported our work using a single portal image to estimate the transformation parame- ters. In this work, we extend the algorithm to utilize dual portal images. In addition, we show the performance of the algorithm on real patient data, analyze the performance of the algorithm under difierent initializa- tions and noise conditions, and note the wide range of parameters that can be estimated. We also present a coordinate descent interpretation of the proposed algorithm to further clarify the formulation.
Year
DOI
Venue
1999
10.1007/10704282_61
MICCAI
Keywords
Field
DocType
multiple-portal-to-3dct registration,iteratively estimated segmentation,prostate radiotherapy,treatment planning
Computer vision,Minimax,Pattern recognition,Prostate radiotherapy,Segmentation,Computer science,Radiation treatment planning,Artificial intelligence,Coordinate descent,External beam radiotherapy
Conference
Volume
ISSN
ISBN
1679
0302-9743
3-540-66503-X
Citations 
PageRank 
References 
15
1.58
7
Authors
7
Name
Order
Citations
PageRank
Ravi Bansal121820.86
Lawrence H. Staib252663.63
Zhe Chen3718.05
A Rangarajan43698367.52
Jonathan Knisely5376.31
Ravinder Nath619223.43
James S. Duncan72973466.48