Affine image registration of arterial spin labeling MRI using deep learning networks.

Convolutional neural networks (CNN) have demonstrated good accuracy and speed in spatially registering high signal-to-noise ratio (SNR) structural magnetic resonance imaging (sMRI) images. However, some functional magnetic resonance imaging (fMRI) images, e.g., those acquired from arterial spin labeling (ASL) perfusion fMRI, are of intrinsically low SNR and therefore the quality of registering ASL images using CNN is not clear. In this work, we aimed to explore the feasibility of a CNN-based affine registration network (ARN) for registration of low-SNR three-dimensional ASL perfusion image time series and compare its performance with that from the state-of-the-art statistical parametric mapping (SPM) algorithm. The six affine parameters were learned from the ARN using both simulated motion and real acquisitions from ASL perfusion fMRI data and the registered images were generated by applying the transformation derived from the affine parameters. The speed and registration accuracy were compared between ARN and SPM. Several independent datasets, including meditation study (10 subjects × 2), bipolar disorder study (26 controls, 19 bipolar disorder subjects), and aging study (27 young subjects, 33 older subjects), were used to validate the generality of the trained ARN model. The ARN method achieves superior image affine registration accuracy (total translation/total rotation errors of ARN vs. SPM: 1.17 mm/1.23° vs. 6.09 mm/12.90° for simulated images and reduced MSE/L1/DSSIM/Total errors of 18.07% / 19.02% / 0.04% / 29.59% for real ASL test images) and 4.4 times (ARN vs. SPM: 0.50 s vs. 2.21 s) faster speed compared to SPM. The trained ARN can be generalized to align ASL perfusion image time series acquired with different scanners, and from different image resolutions, and from healthy or diseased populations. The results demonstrated that our ARN markedly outperforms the iteration-based SPM both for simulated motion and real acquisitions in terms of registration accuracy, speed, and generalization.

Increased frontocerebellar activation in alcoholics during verbal working memory: an fMRI study.

Although there is clear evidence of alcoholism-related damage to the frontal lobes and cerebellum from neuroimaging, neuropathological, and neuropsychological studies, the functional role of the cerebellum and cerebrocerebellar circuits related to verbal working memory deficits of alcoholics have not been well studied. Alcoholic and nonalcoholic subjects performed a Sternberg verbal working memory task while receiving an fMRI scan in a 3T magnet. This task has been found in previous studies to reliably activate the articulatory control and phonological storage components of the phonological loop (left frontal, left temporal/parietal structures, right superior cerebellar regions) in young healthy controls. We hypothesized that the alcoholics would show a different pattern of activation from the controls, based on the regions of interest (ROIs) identified from a previous study of healthy subjects. Behavioral results showed the alcoholics to be performing at a comparable level to the matched controls in terms of accuracy and median reaction time, with no statistically significant differences. However, analysis of the functional data revealed that the alcoholics exhibited greater activation in the left frontal (BA44/45) and right superior cerebellum (HVI) regions relative to the matched controls. These findings suggest that brain activation in left frontal and right cerebellar regions that support the articulatory control system of verbal working memory may require a compensatory increase in alcoholics in order to maintain the same level of performance as controls.