"Accuracy Estimation for Medical Image Registration Using Regression Forests"

Hessam Sokooti, Gorkem Saygili, Ben Glocker, Boudewijn P.F. Lelieveldt and Marius Staring


This paper reports a new automatic algorithm to estimate the misregistration in a quantitative manner. A random regression forest is constructed, predicting the local registration error. The forest is built using local and modality independent features related to the registration precision, the transformation model and intensity-based similarity after registration. The forest is trained and tested using manually annotated corresponding points between pairs of chest CT scans. The results show that the mean absolute error of regression is 0.72 ± 0.96 mm and the accuracy of classiffication in three classes (correct, poor and wrong registration) is 93.4%, comparing favorably to a competing method. In conclusion, a method was proposed that for the first time shows the feasibility of automatic registration assessment by means of regression, and promising results were obtained.



PDF (9 pages, 1221 kB) click to start download
From publisher link

Copyright © 2016 by the authors. Published version © 2016 by Springer Lecture Notes in Computer Science. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.


BibTeX entry

author = "{Hessam Sokooti and Gorkem Saygili and Ben Glocker and Boudewijn P.F. Lelieveldt and Marius Staring}",
title = "{Accuracy Estimation for Medical Image Registration Using Regression Forests}",
booktitle = "{Medical Image Computing and Computer-Assisted Intervention}",
editor = "{Sebastien Ourselin and Leo Joskowicz and Mert R. Sabuncu and Gozde Unal and William Wells}",
address = "{Athens,Greece}",
series = "{Lecture Notes in Computer Science}",
volume = "{9902}",
pages = "{107 - 115}",
month = "{October}",
year = "{2016}",

You are visitor nr. |last modified: 31-10-2016 |webmaster |Copyright 2004-2017 © by Marius Staring