Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections

01/16/2018
by   Juan Eugenio Iglesias, et al.
0

Nonlinear registration of 2D histological sections with corresponding slices of MRI data is a critical step of 3D histology reconstruction. This task is difficult due to the large differences in image contrast and resolution, as well as the complex nonrigid distortions produced when sectioning the sample and mounting it on the glass slide. It has been shown in brain MRI registration that better spatial alignment across modalities can be obtained by synthesizing one modality from the other and then using intra-modality registration metrics, rather than by using mutual information (MI) as metric. However, such an approach typically requires a database of aligned images from the two modalities, which is very difficult to obtain for histology/MRI. Here, we overcome this limitation with a probabilistic method that simultaneously solves for registration and synthesis directly on the target images, without any training data. In our model, the MRI slice is assumed to be a contrast-warped, spatially deformed version of the histological section. We use approximate Bayesian inference to iteratively refine the probabilistic estimate of the synthesis and the registration, while accounting for each other's uncertainty. Moreover, manually placed landmarks can be seamlessly integrated in the framework for increased performance. Experiments on a synthetic dataset show that, compared with MI, the proposed method makes it possible to use a much more flexible deformation model in the registration to improve its accuracy, without compromising robustness. Moreover, our framework also exploits information in manually placed landmarks more efficiently than MI, since landmarks inform both synthesis and registration - as opposed to registration alone. Finally, we show qualitative results on the public Allen atlas, in which the proposed method provides a clear improvement over MI based registration.

READ FULL TEXT

page 6

page 12

page 14

page 15

research
07/30/2021

Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired images

Nonlinear inter-modality registration is often challenging due to the la...
research
08/22/2019

Motion correction of dynamic contrast enhanced MRI of the liver

Motion correction of dynamic contrast enhanced magnetic resonance images...
research
06/12/2018

Initialize globally before acting locally: Enabling Landmark-free 3D US to MRI Registration

Registration of partial-view 3D US volumes with MRI data is influenced b...
research
08/27/2017

Part-to-whole Registration of Histology and MRI using Shape Elements

Image registration between histology and magnetic resonance imaging (MRI...
research
03/22/2013

Cortical Surface Co-Registration based on MRI Images and Photos

Brain shift, i.e. the change in configuration of the brain after opening...
research
07/29/2018

Towards ultra-high resolution 3D reconstruction of a whole rat brain from 3D-PLI data

3D reconstruction of the fiber connectivity of the rat brain at microsco...

Please sign up or login with your details

Forgot password? Click here to reset