Retrospective Motion Correction in Multishot MRI using Generative Adversarial Network

Abstract

Multishot Magnetic Resonance Imaging (MRI) is a promising data acquisition technique that can produce a high-resolution image with relatively less data acquisition time than the standard spin echo. The downside of multishot MRI is that it is very sensitive to subject motion and even small levels of motion during the scan can produce artifacts in the final magnetic resonance (MR) image, which may result in a misdiagnosis. Numerous efforts have focused on addressing this issue; however, all of these proposals are limited in terms of how much motion they can correct and require excessive computational time. In this paper, we propose a novel generative adversarial network (GAN)-based conjugate gradient SENSE (CG-SENSE) reconstruction framework for motion correction in multishot MRI. First CG-SENSE reconstruction is employed to reconstruct an image from the motion-corrupted kspace data and then the GAN-based proposed framework is applied to correct the motion artifacts. The proposed method has been rigorously evaluated on synthetically corrupted data on varying degrees of motion, numbers of shots, and encoding trajectories. Our analyses (both quantitative as well as qualitative/visual analysis) establish that the proposed method is robust and reduces several-fold the computational time reported by the current state-of-the-art technique.Magnetic resonance imaging (MRI) is a safe, non-ionizing, and non-invasive imaging modality that provides high resolution and excellent contrast of soft tissues. It has emerged as a powerful and effective technique for early diagnosis of many common but potentially treatable diseases including stroke, cancer, and ischemic heart disease. Despite these advantages, the prolonged data acquisition time of MRI causes many difficulties in its clinical applications, and various research efforts have been proposed in response to expedite the data acquisition process including the use of parallel imaging (PI) 1 , compressed sensing (CS) 2 , and echo-planar imaging (EPI) 3 .In single-shot echo-planar imaging (EPI), all the k-space data necessary to reconstruct the final magnetic resonance (MR) image is acquired in a single excitation pulse. It significantly accelerates the data acquisition time and minimizes the possibility of motion artifacts in MR images 4,5 . However, MR images reconstructed using single-shot EPI suffers from low resolution and susceptibility artifacts. To overcome these limitations, segmented EPI or multishot MRI is used 6 , which is a compromise between echo-planar and standard spin-echo imaging. It significantly reduces the demands on gradient performance and allows the in-plane spatial resolution to be improved to a level comparable to that of standard spin echo pulse sequences 7 . In multi-shot MRI, the k-space data is acquired in using a large number of shots at different time instances to obtain the high-resolution volumetric image. As a result, the image may be severely degraded due to subject motion between consecutive shots. This makes the multishot sequences very sen...

Image-based Motion Artifact Reduction on Liver Dynamic Contrast Enhanced MRI

“…Future work includes increasing the size of training dataset with more comprehensive motion artifact simulations. Finally, other advanced networks such as generative adversarial network (GAN) (41) with its unique generator and discriminator can be exploited to generate super-resolution image to reduce image blurriness (42) and correct motion artifacts in MRI (43).…”

Volumetric lung nodule segmentation using adaptive ROI with multi-view residual learning

“…Despite extensive research, classical image processing techniques were unable to provide sufficiently robust and accurate volumetric nodule segmentation. On the other hand, recent advancements in deep learning (DL) have revolutionized image enhancement 20 and segmentation-related applications 21 22 , including lung nodule segmentation tasks 23 . Especially the introduction of the U-Net architecture 24 , for segmentation in medical images, has remarkably enhanced the performance for these tasks.…”

Leveraging Data Science To Combat COVID-19: A Comprehensive Review

“…Despite these advantages, to the best of our knowledge, no study has yet explored the potential of automatically detecting COVID-19 infections via ultrasound scans. Similarly, magnetic resonance imaging (MRI) is considered the safest imaging modality as it is a non-invasive and non-ionising technique, which provides a high resolution image and excellent soft tissue contrast [110]. Some studies like [233] have described the significance of MRI in fighting against COVID-19 infections.…”