This thesis deals with advances in groupwise image registration. Image registration remains an important task in medical image analysis. Whereas most methods are designed for the registration of two images (pairwise registration), there is an increasing interest in simultaneously aligning more than two images using groupwise registration given the increasing availability of medical imaging data, both at the individual and the population level. Groupwise image registration has shown promise in a number of applications dealing with large quantities of data, among others to increase registration accuracy and robustness, to improve the transformation smoothness and to reduce the methodological bias compared to pairwise registrations. However, directly comparing groupwise registrations to conventional repeated pairwise registrations is difficult due to several confounding factors impacting the algorithm. In this thesis, as a first contribution, we rigorously evaluate two registration methodologies in several experiments and investigate the differences in performance. Secondly, we fill a gap in current literature on efficient (dis)similarity measures for multimodal groupwise image registration. These two contributions are distributed over four chapters. In Chapter 3, we investigate several registration approaches for the alignment of CT and MRI acquisitions of the mandible in patients with oral squamous cell carcinoma. A comparison is made between rigid and non-rigid approaches with symmetric and asymmetric transformation strategies. The results suggest improved performance in terms of registration accuracy for a symmetric transformation strategy compared to an asymmetric approach, however, the differences were not statistically significant (p=0.054). For this clinical application, we conclude that a rigid registration method is the recommended approach. In Chapter 4, an investigation is performed on different template images for groupwise registrations based on mutual information. Here, template images are employed as a representative image to compare every image in the group to (in terms of its (dis)similarity). We show that the entropy of the template image can have a counter-intuitive contribution to the global dissimilarity value. Additionally, we show that equivalent performance in terms of registration accuracy can be achieved between groupwise and repeated pairwise approaches. In Chapter 5, a novel similarity measure is introduced for multimodal groupwise registration. The conditional template entropy measures the negated average of the pairwise conditional entropy of each image of the group and a template image, which is constructed based on principal component analysis. We show improved or equivalent performance in terms of accuracy compared to other state-of-the-art (dis)similarity measures for multimodal groupwise registration and repeated pairwise registration. Furthermore, groupwise registration vastly outperform repeated pairwise registration in terms of transitive error, a measure which can be interpreted as a measure for the consistency of the transformations in a groupwise setting. In Chapter 6, to further improve on the efficiency of multimodal groupwise registration, we propose a novel dissimilarity measure which is especially adept at registering large groups of images. The dissimilarity measure is formulated as the second smallest eigenvalue of the generalized eigenvalue problem posed in the description of Laplacian eigenmaps. We show little dependence of the measure in terms of computation time with respect to the number of images in the group, and equivalent or improved performance in terms of registration accuracy compared to state-of-the-art groupwise (dis)similarity measures. To summarize, in this work we evaluate groupwise approaches compared to repeated pairwise approaches and show mostly equivalent performance in terms of registration accuracy and robustness and an improved transitivity for groupwise registration. Furthermore, we recommend to use the proposed dissimilarity measure based on Laplacian eigenmaps for large groups of images given its superior or equivalent registration accuracy compared to other measures but superior scaling in terms of execution time with respect to the number of images in the group.
Polfliet, M 2022, ' ADVANCES IN GROUPWISE IMAGE REGISTRATION ', Doctor of Engineering Sciences, Vrije Universiteit Brussel.
Polfliet, M. (2022). ADVANCES IN GROUPWISE IMAGE REGISTRATION .
@phdthesis{219df700864b4935bea36794011a52eb,
title = " ADVANCES IN GROUPWISE IMAGE REGISTRATION " ,
abstract = " This thesis deals with advances in groupwise image registration. Image registration remainsan important task in medical image analysis. Whereas most methods are designed for theregistration of two images (pairwise registration), there is an increasing interest insimultaneously aligning more than two images using groupwise registration given theincreasing availability of medical imaging data, both at the individual and the populationlevel. Groupwise image registration has shown promise in a number of applications dealingwith large quantities of data, among others to increase registration accuracy and robustness,to improve the transformation smoothness and to reduce the methodological bias comparedto pairwise registrations. However, directly comparing groupwise registrations toconventional repeated pairwise registrations is difficult due to several confounding factorsimpacting the algorithm. In this thesis, as a first contribution, we rigorously evaluate tworegistration methodologies in several experiments and investigate the differences inperformance. Secondly, we fill a gap in current literature on efficient (dis)similarity measuresfor multimodal groupwise image registration. These two contributions are distributed overfour chapters.In Chapter 3, we investigate several registration approaches for the alignment of CT and MRIacquisitions of the mandible in patients with oral squamous cell carcinoma. A comparison ismade between rigid and non-rigid approaches with symmetric and asymmetrictransformation strategies. The results suggest improved performance in terms of registrationaccuracy for a symmetric transformation strategy compared to an asymmetric approach,however, the differences were not statistically significant (p=0.054). For this clinicalapplication, we conclude that a rigid registration method is the recommended approach.In Chapter 4, an investigation is performed on different template images for groupwiseregistrations based on mutual information. Here, template images are employed as arepresentative image to compare every image in the group to (in terms of its (dis)similarity).We show that the entropy of the template image can have a counter-intuitive contribution tothe global dissimilarity value. Additionally, we show that equivalent performance in terms ofregistration accuracy can be achieved between groupwise and repeated pairwiseapproaches.In Chapter 5, a novel similarity measure is introduced for multimodal groupwise registration.The conditional template entropy measures the negated average of the pairwise conditionalentropy of each image of the group and a template image, which is constructed based onprincipal component analysis. We show improved or equivalent performance in terms ofaccuracy compared to other state-of-the-art (dis)similarity measures for multimodalgroupwise registration and repeated pairwise registration. Furthermore, groupwiseregistration vastly outperform repeated pairwise registration in terms of transitive error, ameasure which can be interpreted as a measure for the consistency of the transformations ina groupwise setting.In Chapter 6, to further improve on the efficiency of multimodal groupwise registration, wepropose a novel dissimilarity measure which is especially adept at registering large groups ofimages. The dissimilarity measure is formulated as the second smallest eigenvalue of thegeneralized eigenvalue problem posed in the description of Laplacian eigenmaps. We showlittle dependence of the measure in terms of computation time with respect to the number ofimages in the group, and equivalent or improved performance in terms of registrationaccuracy compared to state-of-the-art groupwise (dis)similarity measures.To summarize, in this work we evaluate groupwise approaches compared to repeatedpairwise approaches and show mostly equivalent performance in terms of registrationaccuracy and robustness and an improved transitivity for groupwise registration.Furthermore, we recommend to use the proposed dissimilarity measure based on Laplacianeigenmaps for large groups of images given its superior or equivalent registration accuracycompared to other measures but superior scaling in terms of execution time with respect tothe number of images in the group. " ,
author = " Mathias Polfliet " ,
year = " 2022 " ,
month = may,
day = " 25 " ,
language = " English " ,
school = " Vrije Universiteit Brussel, Erasmus University Rotterdam " ,
}