Information-Theoretic Registration with Explicit Reorientation of Diffusion-Weighted Images
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Information-Theoretic Registration with Explicit Reorientation of Diffusion-Weighted Images. / Jensen, Henrik G.; Lauze, François; Darkner, Sune.
In: Journal of Mathematical Imaging and Vision, Vol. 64, 2022, p. 1-16.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Information-Theoretic Registration with Explicit Reorientation of Diffusion-Weighted Images
AU - Jensen, Henrik G.
AU - Lauze, François
AU - Darkner, Sune
N1 - Publisher Copyright: © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2022
Y1 - 2022
N2 - We present an information-theoretic approach to the registration of images with directional information, especially for diffusion-weighted images (DWIs), with explicit optimization over the directional scale. We call it locally orderless registration with directions (LORDs). We focus on normalized mutual information as a robust information-theoretic similarity measure for DWI. The framework is an extension of the LOR-DWI density-based hierarchical scale-space model that varies and optimizes the integration, spatial, directional and intensity scales. As affine transformations are insufficient for inter-subject registration, we extend the model to nonrigid deformations. We illustrate that the proposed model deforms orientation distribution functions (ODFs) correctly and is capable of handling the classic complex challenges in DWI registrations, such as the registration of fiber crossings along with kissing, fanning, and interleaving fibers. Our experimental results clearly illustrate a novel promising regularizing effect, which comes from the nonlinear orientation-based cost function. We show the properties of the different image scales, and we show that including orientational information in our model makes the model better at retrieving deformations in contrast to standard scalar-based registration.
AB - We present an information-theoretic approach to the registration of images with directional information, especially for diffusion-weighted images (DWIs), with explicit optimization over the directional scale. We call it locally orderless registration with directions (LORDs). We focus on normalized mutual information as a robust information-theoretic similarity measure for DWI. The framework is an extension of the LOR-DWI density-based hierarchical scale-space model that varies and optimizes the integration, spatial, directional and intensity scales. As affine transformations are insufficient for inter-subject registration, we extend the model to nonrigid deformations. We illustrate that the proposed model deforms orientation distribution functions (ODFs) correctly and is capable of handling the classic complex challenges in DWI registrations, such as the registration of fiber crossings along with kissing, fanning, and interleaving fibers. Our experimental results clearly illustrate a novel promising regularizing effect, which comes from the nonlinear orientation-based cost function. We show the properties of the different image scales, and we show that including orientational information in our model makes the model better at retrieving deformations in contrast to standard scalar-based registration.
KW - Diffusion weighted imaging
KW - Locally orderless imaging
KW - Normalized mutual information
KW - Orientation information
KW - Registration
UR - http://www.scopus.com/inward/record.url?scp=85112549208&partnerID=8YFLogxK
U2 - 10.1007/s10851-021-01050-2
DO - 10.1007/s10851-021-01050-2
M3 - Journal article
AN - SCOPUS:85112549208
VL - 64
SP - 1
EP - 16
JO - Journal of Mathematical Imaging and Vision
JF - Journal of Mathematical Imaging and Vision
SN - 0924-9907
ER -
ID: 282746164