Abstract In magnetic resonance imaging (MRI), variations in scan parameters and scanner specifications can result in differences in image appearance. To minimize these differences, harmonization in MRI has been suggested as a crucial image processing technique. In this study, we developed an MR physics-based harmonization framework, Physics-Constrained Deep Neural Network for Multisite and multiscanner Harmonization (PhyCHarm). PhyCHarm includes two deep neural networks: (1) the Quantitative Maps Generator to generate T 1 - and M 0 -maps and (2) the Harmonization Network. We used an open dataset consisting of 3T MP2RAGE images from 50 healthy individuals for the Quantitative Maps Generator and a traveling dataset consisting of 3T T 1 w images from 9 healthy individuals for the Harmonization Network. PhyCHarm was evaluated using the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and normalized-root-mean square error (NRMSE) for the Quantitative Maps Generator, and using SSIM, PSNR, and volumetric analysis for the Harmonization network, respectively. PhyCHarm demonstrated increased SSIM and PSNR, the highest Dice score in the FSL FAST segmentation results for gray and white matter compared to U-Net, Pix2Pix, and CALAMITI. PhyCHarm showed a greater reduction in volume differences after harmonization for gray and white matter than U-Net, Pix2Pix, or CALAMITI. As an initial step toward developing advanced harmonization techniques, we investigated the applicability of physics-based constraints within a supervised training strategy. The proposed physics constraints could be integrated with unsupervised methods, paving the way for more sophisticated harmonization qualities.

Quantitative magnetization transfer (qMT) imaging is sensitive to myelin-related macromolecular content and brain microstructure but is limited by long scan times. We present a fast, SAR-efficient qMT technique using a segmented echo-planar imaging readout with variable power MT preparation (EP-vpMT). EP-vpMT was implemented at 3T (1.5×1.5×4.0 mm³ voxels; 9 µL) using a 3D segmented EPI readout with modulated MT RF pulses to reduce SAR while preserving contrast. Pseudo bound pool fraction (pseudo-BPF) maps were obtained from healthy participants. Consistency with pseudo-BPF derived from conventional GRE-MT and repeatability was subject to Bland-Altman analysis. Multiple sclerosis (MS) patients were examined at 3T and at 7T (2.0 mm isotropic voxels; 8 µL) to explore feasibility for assessing tissue integrity and for application at ultra-high field. EP-vpMT achieved whole-brain qMT in 6 min 25 sec, reducing scan time by 76% compared to GRE-based qMT (26 min 20 sec) while maintaining similar SAR levels. Strong agreement was observed between methods, and test-retest reliability showed minimal bias with 95% limits of agreement within a clinically negligible range. In MS patients, EP-vpMT delineated lesions at 3T and at 7T. EP-vpMT enables fast qMT imaging at 3T with strong agreement with conventional methods. Its ability to detect MS lesions and to translate to ultra-high field MRI supports future use for assessing myelin-related macromolecular content.

In MRI, researchers have long endeavored to effectively visualize myelin distribution in the brain, a pursuit with significant implications for both scientific research and clinical applications. Over time, various methods such as myelin water imaging, magnetization transfer imaging, and relaxometric imaging have been developed, each carrying distinct advantages and limitations. Recently, an innovative technique named as magnetic susceptibility source separation has emerged, introducing a novel surrogate biomarker for myelin in the form of a diamagnetic susceptibility map. This paper comprehensively reviews this cutting-edge method, providing the fundamental concepts of magnetic susceptibility, susceptibility imaging, and the validation of the diamagnetic susceptibility map as a myelin biomarker that indirectly measures myelin content. Additionally, the paper explores essential aspects of data acquisition and processing, offering practical insights for readers. A comparison with established myelin imaging methods is also presented, and both current and prospective clinical and scientific applications are discussed to provide a holistic understanding of the technique. This work aims to serve as a foundational resource for newcomers entering this dynamic and rapidly expanding field.

MRI is an imaging technology that non-invasively obtains high-quality medical images for diagnosis. However, MRI has the major disadvantage of long scan times which cause patient discomfort and image artifacts. As one of the methods for reducing the long scan time of MRI, the parallel MRI method for reconstructing a high-fidelity MR image from under-sampled multi-coil k-space data is widely used. In this study, we propose a method to reconstruct a high-fidelity MR image from under-sampled multi-coil k-space data using deep-learning. The proposed multi-domain Neumann network with sensitivity maps (MDNNSM) is based on the Neumann network and uses a forward model including coil sensitivity maps for parallel MRI reconstruction. The MDNNSM consists of three main structures: the CNN-based sensitivity reconstruction block estimates coil sensitivity maps from multi-coil under-sampled k-space data; the recursive MR image reconstruction block reconstructs the MR image; and the skip connection accumulates each output and produces the final result. Experiments using the fastMRI T1-weighted brain image dataset were conducted at acceleration factors of 2, 4, and 8. Qualitative and quantitative experimental results show that the proposed MDNNSM method reconstructs MR images more accurately than other methods, including the generalized autocalibrating partially parallel acquisitions (GRAPPA) method and the original Neumann network.

Despite the unprecedented success of deep learning in various fields, it has been recognized that clinical diagnosis requires extra caution when applying recent deep learning techniques because false prediction can result in severe consequences. In this study, we proposed a reliable deep learning framework that could minimize incorrect segmentation by quantifying and exploiting uncertainty measures. The proposed framework demonstrated the effectiveness of a public dataset: Multimodal Brain Tumor Segmentation Challenge 2018. By using this framework, segmentation performances, particularly for small lesions, were improved. Since the segmentation of small lesions is difficult but also clinically significant, this framework could be effectively applied to the medical imaging field.

Motivation: Methods to assess the activity of the glymphatic system are required to illustrate an association between glymphatic dysfunction and neurodegenerative diseases. Goal(s): Our aim is to develop a deep neural network-based method to assess glymphatic activity in the human brain. Approach: We trained a deep neural network to generate T2map and CSF fraction map, which is a quantitative CSF measurement. We then compared the predicted CSFF across 60 OASIS-3 subjects, which include both healthy controls and patients with Alzheimer's disease (AD). Results: Significant differences in CSFF were observed in the frontal, temporal, and posterior cingulate cortex and precuneus. Impact: Our method reduces the requirements to acquire additional multi-echo spin-echo T2w images for CSFF analysis. This may enhance the utility of CSFF analysis for assessing the dysfunction in the glymphatic system.

Motivation: Loss of neuromelanin (NM) in brainstem structures is evident in pathology in early neurodegenerative disease. In-vivo neuromelanin imaging is a potential biomarker, but previously-developed approaches can be too lengthy for routine clinical use. Goal(s): To optimize the contrast of locus coeruleus (LC) and substantia nigra (SN) in a fast, segmented EPI readout variable flip-angle magnetization transfer (EP-vfMT) acquisition. Approach: Contrast of LC and SN were optimized as a function of echo time (TE), repetition time (TR), and MT flip-angle while limiting scan time to 5 minutes. Results: Optimal contrast was found by minimizing TE and maximizing MT flip-angle. Contrast was insensitive to TR. Impact: The speed of the proposed acquisition will enable examination of EP-vfMT as an imaging biomarker for early-stage neurodegeneration in Parkinson's disease, Alzheimer's disease and other neurogenerative disorders.

Motivation: To improve outcomes of deep brain stimulation treatment of Parkinson's Disease (PD) by improving visualization of the subthalamic nucleus (STN) in the presence of motion during MRI. Goal(s): To evaluate an accelerated gradient recalled echo (aGRE) at 7T. Approach: In two PD patients, aGRE was compared against conventional GRE and turbo spin echo (TSE) acquisitions. STN delineation was rated by an experienced researcher and a neurosurgeon. Results: In one subject with low motion, GRE and aGRE image quality was better than that of TSE. In the subject with high motion, GRE was unusable but aGRE and TSE were acceptable. Impact: Accelerated GRE at 7T offers improved delineation of the STN despite subject motion during MRI. Motion robustness is crucial, as PD patients are prone to movement, and MRI guides lead placement for effective deep brain stimulation treatment.

Purpose: This study proposes a novel method to reduce N/2 ghosting artifacts and eddy current-induced image shifts in single-shot diffusion-weighted echo-planar imaging (DW-EPI) for 7 tesla (T) MRI.This method integrates dummy diffusion gradients and optimized navigator echo placement to improve phase correction and artifact reduction, addressing the limitations of conventional phase correction methods.Materials and Methods: The proposed method was compared to the conventional approach, which uses Nav1 for phase correction without dummy diffusion gradients.The new approach incorporates Nav2 for phase correction and dummy diffusion gradients to mitigate eddy current effects.Phantom and in vivo experiments were conducted to evaluate the N/2 ghosting intensity, phase stability, and geometric accuracy.In vivo diffusion-weighted images were acquired at b = 1000 s/mm 2 and the effectiveness of the phase correction was qualitatively and quantitatively assessed.Results: Phase evolution analysis revealed that Nav2 more accurately captures diffusion gradient-induced phase perturbations compared to Nav1, leading to improved N/2 ghosting artifact correction.Phantom experiments demonstrated a 41% reduction in N/2 ghosting artifacts using Nav2 compared to Nav1, confirming its superior phase correction capabilities.The in vivo results showed that the proposed method reduced ghosting artifacts and image shifts, leading to an improved alignment of diffusion-weighted images with the reference b = 0 image.Furthermore, the inclusion of dummy diffusion gradients further reduced eddy current-induced artifacts, enhancing image stability and tissue contrast in high-field diffusion-weighted imaging. Conclusion:The proposed method of integrating Nav2 for phase correction and dummy diffusion gradients significantly reduced N/2 ghosting artifacts and geometric distortions in high-field diffusion MRI.These findings suggest that optimizing navigator positioning and incorporating dummy diffusion gradients can enhance the phase stability and improve the reliability of DW-EPI at 7 T.However, as this was a preliminary study with a limited in vivo dataset (n = 2), further validation with larger datasets, different MRI systems, and broader imaging conditions is necessary to fully assess its robustness and clinical applicability.

Abstract In magnetic resonance imaging (MRI), variations in scan parameters and scanner specifications can result in differences in image appearance. To minimize these differences, harmonization in MRI has been suggested as a crucial image processing technique. In this study, we developed an MR physics-based harmonization framework, Physics-Constrained Deep Neural Network for Multisite and multiscanner Harmonization (PhyCHarm). PhyCHarm includes two deep neural networks: (1) the Quantitative Maps Generator to generate T 1 - and M 0 -maps and (2) the Harmonization Network. We used an open dataset consisting of 3T MP2RAGE images from 50 healthy individuals for the Quantitative Maps Generator and a traveling dataset consisting of 3T T 1 w images from 9 healthy individuals for the Harmonization Network. PhyCHarm was evaluated using the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and normalized-root-mean square error (NRMSE) for the Quantitative Maps Generator, and using SSIM, PSNR, and volumetric analysis for the Harmonization network, respectively. PhyCHarm demonstrated increased SSIM and PSNR, the highest Dice score in the FSL FAST segmentation results for gray and white matter compared to U-Net, Pix2Pix, and CALAMITI. PhyCHarm showed a greater reduction in volume differences after harmonization for gray and white matter than U-Net, Pix2Pix, or CALAMITI. As an initial step toward developing advanced harmonization techniques, we investigated the applicability of physics-based constraints within a supervised training strategy. The proposed physics constraints could be integrated with unsupervised methods, paving the way for more sophisticated harmonization qualities.

Quantitative magnetization transfer (qMT) imaging is sensitive to myelin-related macromolecular content and brain microstructure but is limited by long scan times. We present a fast, SAR-efficient qMT technique using a segmented echo-planar imaging readout with variable power MT preparation (EP-vpMT). EP-vpMT was implemented at 3T (1.5×1.5×4.0 mm³ voxels; 9 µL) using a 3D segmented EPI readout with modulated MT RF pulses to reduce SAR while preserving contrast. Pseudo bound pool fraction (pseudo-BPF) maps were obtained from healthy participants. Consistency with pseudo-BPF derived from conventional GRE-MT and repeatability was subject to Bland-Altman analysis. Multiple sclerosis (MS) patients were examined at 3T and at 7T (2.0 mm isotropic voxels; 8 µL) to explore feasibility for assessing tissue integrity and for application at ultra-high field. EP-vpMT achieved whole-brain qMT in 6 min 25 sec, reducing scan time by 76% compared to GRE-based qMT (26 min 20 sec) while maintaining similar SAR levels. Strong agreement was observed between methods, and test-retest reliability showed minimal bias with 95% limits of agreement within a clinically negligible range. In MS patients, EP-vpMT delineated lesions at 3T and at 7T. EP-vpMT enables fast qMT imaging at 3T with strong agreement with conventional methods. Its ability to detect MS lesions and to translate to ultra-high field MRI supports future use for assessing myelin-related macromolecular content.

In MRI, researchers have long endeavored to effectively visualize myelin distribution in the brain, a pursuit with significant implications for both scientific research and clinical applications. Over time, various methods such as myelin water imaging, magnetization transfer imaging, and relaxometric imaging have been developed, each carrying distinct advantages and limitations. Recently, an innovative technique named as magnetic susceptibility source separation has emerged, introducing a novel surrogate biomarker for myelin in the form of a diamagnetic susceptibility map. This paper comprehensively reviews this cutting-edge method, providing the fundamental concepts of magnetic susceptibility, susceptibility imaging, and the validation of the diamagnetic susceptibility map as a myelin biomarker that indirectly measures myelin content. Additionally, the paper explores essential aspects of data acquisition and processing, offering practical insights for readers. A comparison with established myelin imaging methods is also presented, and both current and prospective clinical and scientific applications are discussed to provide a holistic understanding of the technique. This work aims to serve as a foundational resource for newcomers entering this dynamic and rapidly expanding field.

MRI is an imaging technology that non-invasively obtains high-quality medical images for diagnosis. However, MRI has the major disadvantage of long scan times which cause patient discomfort and image artifacts. As one of the methods for reducing the long scan time of MRI, the parallel MRI method for reconstructing a high-fidelity MR image from under-sampled multi-coil k-space data is widely used. In this study, we propose a method to reconstruct a high-fidelity MR image from under-sampled multi-coil k-space data using deep-learning. The proposed multi-domain Neumann network with sensitivity maps (MDNNSM) is based on the Neumann network and uses a forward model including coil sensitivity maps for parallel MRI reconstruction. The MDNNSM consists of three main structures: the CNN-based sensitivity reconstruction block estimates coil sensitivity maps from multi-coil under-sampled k-space data; the recursive MR image reconstruction block reconstructs the MR image; and the skip connection accumulates each output and produces the final result. Experiments using the fastMRI T1-weighted brain image dataset were conducted at acceleration factors of 2, 4, and 8. Qualitative and quantitative experimental results show that the proposed MDNNSM method reconstructs MR images more accurately than other methods, including the generalized autocalibrating partially parallel acquisitions (GRAPPA) method and the original Neumann network.