MR‐PET head motion correction based on co‐registration of multicontrast MR images

Chen, Zhaolin; Sforazzini, Francesco; Baran, Jakub; Close, Thomas G.; Shah, N. Jon; Egan, Gary F.

doi:10.1002/hbm.24497

Cited by 22 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Motion simulation was performed with randomly generated 3D rigid body motion between ±5 mm of translation and ±5 0 of rotation on all three axes. The simulated motion range was consistent with a previous in-vivo cohort study (47). The MPRAGE images of size 256×256×256 were used for simulation purposes and the motion was simulated along the phase encode direction (anterior-posterior).…”

Section: Motion Simulationmentioning

confidence: 73%

See 1 more Smart Citation

Suppressing motion artefacts in MRI using an Inception‐ResNet network with motion simulation augmentation

et al. 2019

Self Cite

View full text Add to dashboard Cite

The suppression of motion artefacts from MR images is a challenging task. The purpose of this paper was to develop a standalone novel technique to suppress motion artefacts in MR images using a data-driven deep learning approach. A simulation framework was developed to generate motion-corrupted images from motion-free images using randomly generated motion profiles. An Inception-ResNet deep learning network architecture was used as the encoder and was augmented with a stack of convolution and upsampling layers to form an encoder-decoder network. The network was trained on simulated motion-corrupted images to identify and suppress those artefacts attributable to motion. The network was validated on unseen simulated datasets and real-world experimental motion-corrupted in vivo brain datasets. The trained network was able to suppress the motion artefacts in the reconstructed images, and the mean SSIM increased from 0.9058 to 0.9338. The network was able to suppress the motion artefacts from the real-world experimental dataset and the mean SSIM increased from 0.8671 to 0.9145. The motion correction of the experimental datasets demonstrated the effectiveness of the motion simulation generation process. The proposed method successfully removed motion artefacts and outperformed an iterative entropy minimization method in terms of the SSIM index and normalised root mean squared error, which were 5-10% better for the proposed method. A novel, data-driven motion correction technique has been developed that can suppress motion artefacts from motion-corrupted MR images. The proposed technique is a standalone, post-processing method that does not interfere with data acquisition or reconstruction parameters, thus making it suitable for routine clinical practice.

show abstract

Section: Motion Simulationmentioning

confidence: 73%

“…The simulated motion range was consistent with a previous in vivo cohort study. 47 The MPRAGE images of size 256 × 256 × 256 were used for simulation purposes and the motion was simulated along the phase encode direction (anterior-posterior). Any motion within a single phase encode was neglected in the simulations.…”

Section: Motion Simulationmentioning

confidence: 99%

Suppressing motion artefacts in MRI using an Inception‐ResNet network with motion simulation augmentation

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…acquired at the beginning of the scan) to estimate the motion fields. BrainCOMPASS is applied when imaging the head, while an extension of this technique named BodyCOMPASS can be applied to other regions, such as the thorax [ 52 , 95 ].…”

Section: Software and Test Datasetsmentioning

confidence: 99%

Synergistic motion compensation strategies for positron emission tomography when acquired simultaneously with magnetic resonance imaging

Polycarpou

Soultanidis

Tsoumpas

2021

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Subject motion in positron emission tomography (PET) is a key factor that degrades image resolution and quality, limiting its potential capabilities. Correcting for it is complicated due to the lack of sufficient measured PET data from each position. This poses a significant barrier in calculating the amount of motion occurring during a scan. Motion correction can be implemented at different stages of data processing either during or after image reconstruction, and once applied accurately can substantially improve image quality and information accuracy. With the development of integrated PET-MRI (magnetic resonance imaging) scanners, internal organ motion can be measured concurrently with both PET and MRI. In this review paper, we explore the synergistic use of PET and MRI data to correct for any motion that affects the PET images. Different types of motion that can occur during PET-MRI acquisitions are presented and the associated motion detection, estimation and correction methods are reviewed. Finally, some highlights from recent literature in selected human and animal imaging applications are presented and the importance of motion correction for accurate kinetic modelling in dynamic PET-MRI is emphasized. This article is part of the theme issue ‘Synergistic tomographic image reconstruction: part 2’.

show abstract

“…Fig 3. Motion degraded (left-hand column) and motion-corrected (right-hand column) images highlighting the image quality improvement for a case with a brain tumor.…”

mentioning

confidence: 99%

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

et al. 2022

Self Cite

View full text Add to dashboard Cite

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.

show abstract

MR‐PET head motion correction based on co‐registration of multicontrast MR images

Abstract: This is the author manuscript accepted for publication and has undergone full peer review but has not been through the copyediting, typesetting, pagination and proofreading process, which may lead to differences between this version and the Version of Record. Please cite this article as

Cited by 22 publications

References 31 publications

Suppressing motion artefacts in MRI using an Inception‐ResNet network with motion simulation augmentation

Suppressing motion artefacts in MRI using an Inception‐ResNet network with motion simulation augmentation

Synergistic motion compensation strategies for positron emission tomography when acquired simultaneously with magnetic resonance imaging

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

Contact Info

Product

Resources

About