qMTNet+ , an Improved qMTNet with Residual Connection for Accelerated Quantitative Magnetization Transfer Imaging

Purpose@#To develop qMTNet+ , an improved version of a recently proposed neural network called qMTNet, to accelerate quantitative magnetization transfer (qMT) imaging acquisition and processing. @*Materials and Methods@#Conventional and inter-slice qMT data were acquired with two flip angles at six offset frequencies from seven subjects for developing networks and from four young and four older subjects for testing its generalizability.qMTNet+ was designed to incorporate residual and multi-task learning to improve its performance. qMTNet+ is composed of multiple fully-connected layers. It can simultaneously generate missing MT-weighted images and qMT parameters from undersampled MT images. The network was trained and validated with 7-fold cross-validation. Additional testing with unseen data was performed to assess the generalizability of the network. Performance of qMTNet+ was compared with that of qMTNet-1 and qMTNet-acq for fitting and MT images generation, respectively. @*Results@#qMTNet+ achieved quantitative results that were better than qMTNet across all metrics (peak signal-to-noise ratio, structural similarity index, normalized mean squared error) for both conventional and inter-slice MT data. Produced offset images were better quantitatively than those produced by qMTNet-acq. @*Conclusion@#qMTNet+ improves qMTNet, generating qMT parameters from undersampled MT data with higher agreement with ground truth values. Additionally, qMTNet+ can produce both qMT parameters and unsampled MT images with a single network in an end-to-end manner, obviating the need for separate networks required for qMTNet. qMTNet+ has the potential to accelerate qMT imaging for diagnostic and research purposes.

qMTNet+ , an Improved qMTNet with Residual Connection for Accelerated Quantitative Magnetization Transfer Imaging

Purpose@#To develop qMTNet+ , an improved version of a recently proposed neural network called qMTNet, to accelerate quantitative magnetization transfer (qMT) imaging acquisition and processing. @*Materials and Methods@#Conventional and inter-slice qMT data were acquired with two flip angles at six offset frequencies from seven subjects for developing networks and from four young and four older subjects for testing its generalizability.qMTNet+ was designed to incorporate residual and multi-task learning to improve its performance. qMTNet+ is composed of multiple fully-connected layers. It can simultaneously generate missing MT-weighted images and qMT parameters from undersampled MT images. The network was trained and validated with 7-fold cross-validation. Additional testing with unseen data was performed to assess the generalizability of the network. Performance of qMTNet+ was compared with that of qMTNet-1 and qMTNet-acq for fitting and MT images generation, respectively. @*Results@#qMTNet+ achieved quantitative results that were better than qMTNet across all metrics (peak signal-to-noise ratio, structural similarity index, normalized mean squared error) for both conventional and inter-slice MT data. Produced offset images were better quantitatively than those produced by qMTNet-acq. @*Conclusion@#qMTNet+ improves qMTNet, generating qMT parameters from undersampled MT data with higher agreement with ground truth values. Additionally, qMTNet+ can produce both qMT parameters and unsampled MT images with a single network in an end-to-end manner, obviating the need for separate networks required for qMTNet. qMTNet+ has the potential to accelerate qMT imaging for diagnostic and research purposes.

Evaluation of Tumor Blood Flow Using Alternate Ascending/Descending Directional Navigation in Primary Brain Tumors: A Comparison Study with Dynamic Susceptibility Contrast Magnetic Resonance Imaging

OBJECTIVE: Alternate ascending/descending directional navigation (ALADDIN) is a novel arterial spin labeling technique that does not require a separate spin preparation pulse. We sought to compare the normalized cerebral blood flow (nCBF) values obtained by ALADDIN and dynamic susceptibility contrast (DSC) perfusion magnetic resonance imaging (MRI) in patients with primary brain tumors. MATERIALS AND METHODS: Sixteen patients with primary brain tumors underwent MRI scans including contrast-enhanced T1-weighted imaging, DSC perfusion MRI, and ALADDIN. The nCBF values of normal gray matter (GM) and tumor areas were measured by both DSC perfusion MRI and ALADDIN, which were compared by the Wilcoxon signed rank test. Subgroup analyses according to pathology were performed with the Wilcoxon signed rank test. RESULTS: Higher mean nCBF values of GM regions in the bilateral frontal lobe, temporal lobe, and caudate were detected by ALADDIN than by DSC perfusion MRI (p <0.05). In terms of the mean or median nCBF values and the mean of the top 10% nCBF values from tumors, DSC perfusion MRI and ALADDIN did not statistically significantly differ either overall or in each tumor group. CONCLUSION: ALADDIN tended to detect higher nCBF values in normal GM, as well as higher perfusion portions of primary brain tumors, than did DSC perfusion MRI. We believe that the high perfusion signal on ALADDIN can be beneficial in lesion detection and characterization.

Physiological and Functional Magnetic Resonance Imaging Using Balanced Steady-state Free Precession

Balanced steady-state free precession (bSSFP) is a highly efficient pulse sequence that is known to provide the highest signal-to-noise ratio per unit time. Recently, bSSFP is getting increasingly popular in both the research and clinical communities. This review will be focusing on the application of the bSSFP technique in the context of probing the physiological and functional information. In the first part of this review, the basic principles of bSSFP are briefly covered. Afterwards, recent developments related to the application of bSSFP, in terms of physiological and functional imaging, are introduced and reviewed. Despite its long development history, bSSFP is still a promising technique that has many potential benefits for obtaining high-resolution physiological and functional images.