An artificial intelligence‐accelerated 2‐minute multi‐shot echo planar imaging protocol for comprehensive high‐quality clinical brain imaging

Abstract

We introduce and validate an artificial intelligence (AI)-accelerated multi-shot echo-planar imaging (msEPI)-based method that provides T1w, T2w, T * 2 , T2-FLAIR, and DWI images with high SNR, high tissue contrast, low specific absorption rates (SAR), and minimal distortion in 2 minutes. Methods:The rapid imaging technique combines a novel machine learning (ML) scheme to limit g-factor noise amplification and improve SNR, a magnetization transfer preparation module to provide clinically desirable contrast, and high per-shot EPI undersampling factors to reduce distortion. The ML training and image reconstruction incorporates a tunable parameter for controlling the level of denoising/smoothness. The performance of the reconstruction method is evaluated across various acceleration factors, contrasts, and SNR conditions. The 2-minute protocol is directly compared to a 10-minute clinical reference protocol through deployment in a clinical setting, where five representative cases with pathology are examined. Results: Optimization of custom msEPI sequences and protocols was performed to balance acquisition efficiency and image quality compared to the five-fold longer clinical reference. Training data from 16 healthy subjects across multiple contrasts and orientations were used to produce ML networks at various

Clinical Evaluation of Scout Accelerated Motion Estimation and Reduction Technique for 3D MR Imaging in the Inpatient and Emergency Department Settings

“…Very rapid brain MR imaging protocols have been developed with 1-2 minutes of the total scan time. 4,23 The highly accelerated MR imaging techniques rely on high-end multichannel receiver arrays that may not always be clinically available or feasible to implement, eg, in large patients. Accelerated imaging techniques and SAMER motion correction are not mutually exclusive, and a combination of these methods may provide additional benefits.…”

“…While these techniques are valuable, there are often compromises and trade-offs in terms of image quality and contrast compared with standard brain sequences. 4,5 Moreover, fast imaging techniques still do not fully solve the motion problem because patient motion can occur on a time scale on the order of seconds. 6,7 Navigator-free retrospective motion-correction approaches estimate patient motion in a purely data-driven manner using only the raw k-space data from the standard data acquisition.…”

Ultrafast Brain MRI at 3 T for MS: Evaluation of a 51-Second Deep-Learning-Enhanced T2-EPI-FLAIR Sequence

“…In order to alleviate the deterioration in image quality caused by the above-mentioned acceleration techniques, the FLAIRUF sequence has several novel features. One of them is a DLenhanced processing technique that employs a machine-learning-based reconstruction to decrease image noise and residual aliasing [43][44][45]59]. It was trained on data acquired with a 20-channel head matrix coil at 3 T [43,44].…”

“…The acceleration provided by these techniques has redoubled interest in further investigations. Particularly, the integration of several of these methods with EPI-based imaging has led to the development of ultrafast multi-contrast protocols, providing all contrasts required in an emergency setting (T1, T2, T2*, T2-FLAIR, DWI) [39][40][41][42][43][44][45][46]. There is also an approach to incorporate various contrasts in one sequence [47][48][49][50][51][52].…”

Diagnostic evaluation of deep learning accelerated lumbar spine MRI

“…[5][6][7] Recent advances in medical imaging technology have enabled the development of fast MRI techniques that can reduce acquisition times while still providing high-quality diagnostic images. [8][9][10][11][12][13][14][15][16][17] These fast-imaging techniques can mitigate the impact of artifacts from patient motion, improve patient comfort, reduce anxiety, and optimize workflow thereby allowing for quicker access to imaging results. 18 Accelerated MRI techniques such as parallel imaging and compressed sensing have been developed and applied in recent years, leading to a marked reduction in acquisition times.…”