FMRI 3D registration based on Fourier space subsets using neural networks

Abstract

In this work, we present a neural network (NN) based method designed for 3D rigidbody registration of FMRI time series, which relies on a limited number of Fourier coefficients of the images to be aligned. These coefficients, which are comprised in a small cubic neighborhood located at the first octant of a 3D Fourier space (including the DC component), are then fed into six NN during the learning stage. Each NN yields the estimates of a registration parameter. The proposed method was assessed for 3D rigid-body transformations, using DC neighborhoods of different sizes. The mean absolute registration errors are of approximately 0.030 mm in translations and 0.030 deg in rotations, for the typical motion amplitudes encountered in FMRI studies. The construction of the training set and the learning stage are fast requiring, respectively, 90 s and 1 to 12 s, depending on the number of input and hidden units of the NN. We believe that NN-based approaches to the problem of FMRI registration can be of great interest in the future. For instance, NN relying on limited K-space data (possibly in navigation echoes) can be a valid solution to the problem of prospective (in frame) FMRI registration.

A novel framework for groupwise registration of fMRI images based on common functional networks

“…For instance, in [10], Orchard and Atkins proposed to use functional activation detection as a guidance for image registration. In [11], Freire et al trained a neural network to measure the similarity between fMRI data voxels as registration guidance. Despite these early efforts, there has been little effort in using functional brain networks as references for fMRI image registration, which is the focus on this work.…”

2D/3D image registration using regression learning

“…Their optimizations were fully-implemented on high-end GPUs and obtained sub-second speed. Other methods have used neural networks to model rigid (Banks and Hodge [10], Freire et al [11], Zhang et al [12]), or non-rigid transformations (Wachowiak et al [13]) and to achieve efficient computation at registration time. However, to the best of our knowledge, there is no general framework that supports both rigid and non-rigid 2D/3D registration.…”