Locally Orderless Registration for Diffusion Weighted Images

Jensen, H. G.; Lauze, François; Nielsen, Mads; Darkner, Sune

doi:10.1007/978-3-319-24571-3_37

Cited by 7 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of the groundwork for LOR as well as the properties of the density estimators used for images in image registration where investigated in [3], revealing a 'scale imbalance' in the partial volume density estimator. The idea of marginalizing over more complex geometries than R n was proposed in [9].…”

Section: Related Workmentioning

confidence: 99%

“…Locally Orderless Registration (LOR) [9] explored its application for Magnetic Resonance Diffusion-Weighted Imaging (DWI), which are images containing complicated geometries. Indeed, DWI images can be seen as functions I : Ω × SS 2 → R, with Ω an open subset of R 3 , where SS 2 is seen as the space of directions (with orientation) in R 3 .…”

Section: Introductionmentioning

confidence: 99%

“…In this work we extend the LOI and LOR [5,3,9] framework for images I : Ω → R, by lifting these images to images I : Ω × SS 2 → R, where SS 2 this time parametrizes the local orientations of the image I. This is performed through directional responses of derivatives of Gaussian.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

First Order Locally Orderless Registration

Darkner¹,

D²,

Lauze³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

First Order Locally Orderless Registration (FLOR) is a scalespace framework for image density estimation used for defining image similarity, mainly for Image Registration. The Locally Orderless Registration framework was designed in principle to use zeroth-order information, providing image density estimates over three scales: image scale, intensity scale, and integration scale. We extend it to take firstorder information into account and hint at higher-order information. We show how standard similarity measures extend into the framework. We study especially Sum of Squared Differences (SSD) and Normalized Cross-Correlation (NCC) but present the theory of how Normalised Mutual Information (NMI) can be included.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

First Order Locally Orderless Registration

Darkner¹,

D²,

Lauze³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, they do not use the whole diffusion information especially in crossing regions where the DT is limited. On the other end, some approaches [8] consider DWI registration. However, these algorithms are yet limited to singleshell DWI while the complete study of WM microstructure requires multiple b-values [11].…”

Section: Introductionmentioning

confidence: 99%

$$\ell _2$$ Similarity Metrics for Diffusion Multi-Compartment Model Images Registration

Commowick

Hédouin

Caruyer

et al. 2017

Medical Image Computing and Computer Assisted Intervention − MICCAI 2017

View full text Add to dashboard Cite

Diffusion multi-compartment models (MCM) allow for a fine and comprehensive study of the white matter microstructure. Non linear registration of MCM images may provide valuable information on the brain e.g. through population comparison. State-of-the-art MCM registration however relies on pairing-based similarity measures where the one-to-one mapping of MCM compartments is required. This approach leads to non differentiabilties or discontinuities, which may turn into poorer registration. Moreover, these measures are often specific to one MCM compartment model. We propose two new MCM similarity measures based on the space of square integrable functions, applied to MCM characteristic functions. These measures are pairing-free and agnostic to compartment types. We derive their analytic expressions for multi-tensor models and propose a spherical approximation for more complex models. Evaluation is performed on synthetic deformations and inter-subject registration, demonstrating the robustness of the proposed measures.

show abstract

“…However, accurate kidney segmentation is a challenging task for many reasons, including: kidney motion due to breathing and heart beating; kidney shape changes due to inter-patient anatomical differences; low contrast between the kidney and other abdominal structures, especially, at the higher gradient strengths and duration, or b-values ( Figure 10); low SNR and artifacts that complicate image alignment [149,150]; and geometric distortions due to long acquisition time [130]. The function Φ(p, t) evolves in discrete time t = nτ with a fixed step, τ > 0, as [154]:…”

Section: D Kidney Segmentationmentioning

confidence: 99%

A non-invasive diagnostic system for early assessment of acute renal transplant rejection.

Shehata¹

View full text Add to dashboard Cite

show abstract

Locally Orderless Registration for Diffusion Weighted Images

Cited by 7 publications

References 14 publications

First Order Locally Orderless Registration

First Order Locally Orderless Registration

$$\ell _2$$ Similarity Metrics for Diffusion Multi-Compartment Model Images Registration

A non-invasive diagnostic system for early assessment of acute renal transplant rejection.

Contact Info

Product

Resources

About