Susceptibility artifact correction for sub-millimeter fMRI using inverse phase encoding registration and T1 weighted regularization

Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging-State-of-the-Art and Challenges

Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.

Effect of Phase-Encoding Direction on Gender Differences: A Resting-State Functional Magnetic Resonance Imaging Study

Aim

Neuroimaging studies have highlighted gender differences in brain functions, but conclusions are not well established. Few studies paid attention to the influence of phase-encoding (PE) direction in echo-planar imaging on gender differences, which is a commonly used technique in functional magnetic resonance imaging (fMRI). A disadvantage of echo-planar images is the geometrical distortion and signal loss due to large susceptibility effects along the PE direction. The present research aimed to clarify how PE direction can affect the outcome of a specific research on gender differences.

Methods

We collected resting-state fMRI using anterior to posterior (AP) and posterior to anterior (PA) directions from 113 healthy participants. We calculated several commonly used indices for spontaneous brain activity including amplitude of low frequency fluctuations (ALFF), fractional ALFF (fALFF), regional homogeneity (ReHo), degree centrality (DC), and functional connectivity (FC) of posterior cingulate cortex for each session, and performed three group comparisons: (i) AP versus PA; (ii) male versus female; (iii) interaction between gender and PE direction.

Results

The estimated indices differed substantially between the two PE directions, and the regions that exhibited differences were roughly similar for all the indices. In addition, we found that multiple brain regions showed gender differences in these estimated indices. Further, we observed an interaction effect between gender and PE direction in the bilateral middle frontal gyrus, right precentral gyrus, right postcentral gyrus, right lingual gyrus, and bilateral cerebellum posterior lobe.

Conclusion

These apparent findings revealed that PE direction can partially influence gender differences in spontaneous brain activity of resting-state fMRI. Therefore, future studies should document the adopted PE direction and appropriate selection of PE direction will be important in future resting-state fMRI studies.

Age Differences of the Hierarchical Cognitive Control and the Frontal Rostro-Caudal Functional Brain Activation

Age-related differences in the functional hierarchical organization of the frontal lobe remain unclear. We adopted task-related functional magnetic resonance imaging (fMRI) to investigate age differences in the functional hierarchical organization of the frontal lobe. Behavioral results report both reaction time and efficiency declined as the levels of abstraction increased in the selection of a set of stimulus–response mappings in older adults compared with young adults. fMRI findings suggest trends of the hierarchical organization along the rostro–caudal axis in both groups, and brain–behavior correlation further suggests neural dedifferentiation in older adults when performing at the highest level of control demands experiment. Behavioral performances and age difference overactivations at the highest level of control demands were both associated with working memory capacity, suggesting the working memory capacity is important for processing the highest task demands. Region-of-interest analysis revealed age differences in brain overactivation and common activation across experiments in the primary motor cortex, parietal lobule, and the fusiform gyrus may serve as shared mechanisms underlying tasks that are required for the selection of stimulus–response mapping sets. Overall, older adults reflect maladaptive overactivation in task-irrelevant regions that are detrimental to performance with the highest control demands.

Correcting Susceptibility Artifacts of MRI Sensors in Brain Scanning: A 3D Anatomy-Guided Deep Learning Approach

Echo planar imaging (EPI), a fast magnetic resonance imaging technique, is a powerful tool in functional neuroimaging studies. However, susceptibility artifacts, which cause misinterpretations of brain functions, are unavoidable distortions in EPI. This paper proposes an end-to-end deep learning framework, named TS-Net, for susceptibility artifact correction (SAC) in a pair of 3D EPI images with reversed phase-encoding directions. The proposed TS-Net comprises a deep convolutional network to predict a displacement field in three dimensions to overcome the limitation of existing methods, which only estimate the displacement field along the dominant-distortion direction. In the training phase, anatomical T1-weighted images are leveraged to regularize the correction, but they are not required during the inference phase to make TS-Net more flexible for general use. The experimental results show that TS-Net achieves favorable accuracy and speed trade-off when compared with the state-of-the-art SAC methods, i.e., TOPUP, TISAC, and S-Net. The fast inference speed (less than a second) of TS-Net makes real-time SAC during EPI image acquisition feasible and accelerates the medical image-processing pipelines.

An unsupervised deep learning technique for susceptibility artifact correction in reversed phase-encoding EPI images

Echo planar imaging (EPI) is a fast and non-invasive magnetic resonance imaging technique that supports data acquisition at high spatial and temporal resolutions. However, susceptibility artifacts, which cause the misalignment to the underlying structural image, are unavoidable distortions in EPI. Traditional susceptibility artifact correction (SAC) methods estimate the displacement field by optimizing an objective function that involves one or more pairs of reversed phase-encoding (PE) images. The estimated displacement field is then used to unwarp the distorted images and produce the corrected images. Since this conventional approach is time-consuming, we propose an end-to-end deep learning technique, named S-Net, to correct the susceptibility artifacts the reversed-PE image pair. The proposed S-Net consists of two components: (i) a convolutional neural network to map a reversed-PE image pair to the displacement field; and (ii) a spatial transform unit to unwarp the input images and produce the corrected images. The S-Net is trained using a set of reversed-PE image pairs and an unsupervised loss function, without ground-truth data. For a new image pair of reversed-PE images, the displacement field and corrected images are obtained simultaneously by evaluating the trained S-Net directly. Evaluations on three different datasets demonstrate that S-Net can correct the susceptibility artifacts in the reversed-PE images. Compared with two state-of-the-art SAC methods (TOPUP and TISAC), the proposed S-Net runs significantly faster: 20 times faster than TISAC and 369 times faster than TOPUP, while achieving a similar correction accuracy. Consequently, S-Net accelerates the medical image processing pipelines and makes the real-time correction for MRI scanners feasible. Our proposed technique also opens up a new direction in learning-based SAC.