Retrospective correction of motion‐affected MR images using deep learning frameworks

Küstner, Thomas; Armanious, Karim; Yang, Jiahuan; Yang, Bin; Schick, Fritz; Gatidis, Sergios

doi:10.1002/mrm.27783

Cited by 105 publications

(98 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further reductions in scan time may be achievable by removing the need for respiratory navigation, however this would result in blurring and loss of resolution in the acquired images due to breathing motion. Machine learning algorithms have recently shown the potential to recover high resolution images from this motion corrupted data [ 25 – 27 ].…”

Section: Discussionmentioning

confidence: 99%

Rapid whole-heart CMR with single volume super-resolution

Steeden

Quail

Gotschy

et al. 2020

Journal of Cardiovascular Magnetic Resonance

View full text Add to dashboard Cite

Background: Three-dimensional, whole heart, balanced steady state free precession (WH-bSSFP) sequences provide delineation of intra-cardiac and vascular anatomy. However, they have long acquisition times. Here, we propose significant speed-ups using a deep-learning single volume super-resolution reconstruction, to recover highresolution features from rapidly acquired low-resolution WH-bSSFP images. Methods: A 3D residual U-Net was trained using synthetic data, created from a library of 500 high-resolution WH-bSSFP images by simulating 50% slice resolution and 50% phase resolution. The trained network was validated with 25 synthetic test data sets. Additionally, prospective low-resolution data and high-resolution data were acquired in 40 patients. In the prospective data, vessel diameters, quantitative and qualitative image quality, and diagnostic scoring was compared between the low-resolution, super-resolution and reference high-resolution WH-bSSFP data. Results: The synthetic test data showed a significant increase in image quality of the low-resolution images after super-resolution reconstruction. Prospectively acquired low-resolution data was acquired~× 3 faster than the prospective high-resolution data (173 s vs 488 s). Super-resolution reconstruction of the low-resolution data took < 1 s per volume. Qualitative image scores showed super-resolved images had better edge sharpness, fewer residual artefacts and less image distortion than low-resolution images, with similar scores to high-resolution data. Quantitative image scores showed super-resolved images had significantly better edge sharpness than lowresolution or high-resolution images, with significantly better signal-to-noise ratio than high-resolution data. Vessel diameters measurements showed over-estimation in the low-resolution measurements, compared to the highresolution data. No significant differences and no bias was found in the super-resolution measurements in any of the great vessels. However, a small but significant for the underestimation was found in the proximal left coronary artery diameter measurement from super-resolution data. Diagnostic scoring showed that although super-resolution did not improve accuracy of diagnosis, it did improve diagnostic confidence compared to low-resolution imaging. Conclusion: This paper demonstrates the potential of using a residual U-Net for super-resolution reconstruction of rapidly acquired low-resolution whole heart bSSFP data within a clinical setting. We were able to train the network using synthetic training data from retrospective high-resolution whole heart data. The resulting network can be applied very quickly, making these techniques particularly appealing within busy clinical workflow. Thus, we believe that this technique may help speed up whole heart CMR in clinical practice.

show abstract

Section: Discussionmentioning

confidence: 99%

Rapid whole-heart CMR with single volume super-resolution

Steeden

Quail

Gotschy

et al. 2020

Journal of Cardiovascular Magnetic Resonance

View full text Add to dashboard Cite

show abstract

“…Consequently, methods that better correlate with human ratings are preferred. Considering typical usage of NR methods, limited to 2D images, NORMIQA can be applied to select best performing denoising techniques, approaches for correcting artifacts, or image reconstruction solutions . Also, the method can be used to support subjective tests with human observers since such an assessment is often unrepeatable.…”

Section: Discussionmentioning

confidence: 99%

No‐reference image quality assessment of magnetic resonance images with high‐boost filtering and local features

Oszust

Piórkowski

Obuchowicz

2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose: Subjective quality assessment of displayed magnetic resonance (MR) images plays a key role in diagnosis and the resultant treatment. Therefore, this study aims to introduce a new no-reference (NR) image quality assessment (IQA) method for the objective, automatic evaluation of MR images and compare its judgments with those of similar techniques. Methods: A novel NR-IQA method was developed. The method uses a sequence of scaled images filtered to enhance high-frequency components and preserve lowfrequency parts. Since the human visual system (HVS) is sensitive to local image variations and local features often mimic the attraction of the HVS to high-frequency image regions, they were detected in the filtered images and described. Then, the statistics of obtained descriptors were used to build a quality model via the Support Vector Regression method. Results: The method was compared with 21 state-of-the-art techniques for NR-IQA on a new dataset of 70 distorted MR images assessed by 31 experienced radiologists, using typical evaluation criteria for the comparison of NR measures. The introduced method significantly outperforms the compared approaches, in terms of the correlation with human judgments. Conclusions: It is demonstrated that the presented NR-IQA method for the assessment of MR images is superior to the state-of-the-art NR techniques. The method would be beneficial for a wide range of image processing applications, assessing their outputs and affecting the directions of their development. K E Y W O R D Shigh-boost filtering, image quality assessment, local features, magnetic resonance images, no-reference, subjective tests

show abstract

“…In this work, we sought to investigate the use of deep neural networks (DNNs) for respiratory motion compensation in MRI to alleviate some of the aforementioned problems. DNNs, particularly convolutional DNNs, have presented new possibilities for tackling a wide range of inverse problems including image in-painting, super resolution, [20][21][22][23] denoising and deblurring [24][25][26][27][28][29][30] in an efficient manner. The main advantage of a DNN over classical data-processing approaches is that it learns the effective features and priors in a data-driven fashion.…”

Section: Introductionmentioning

confidence: 99%

“…To date, few studies have implemented DNNs for motion compensation. [30][31][32][33][34] Recent studies have shown that DNN can correct rigid-motion artifacts in brain imaging. 31,32,35 They mainly trained convolutional neural networks (CNNs) with pixel-wise objective functions in a supervised manner.…”

Section: Introductionmentioning

confidence: 99%

“…Küstner et al reported a feasibility study to correct rigid and nonrigid motion artifacts by implementing a conditional generative adversarial network (GAN) (MedGAN), in which the generative network consists of eight cascaded U-nets. 30 The network was trained using a combination of adversarial, style transferring and perceptual loss functions. 36 Among the loss functions used by Küstner et al, 30 the perceptual loss function requires paired data, which are challenging to obtain, especially for nonrigid motion-correction tasks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Retrospective respiratory motion correction in cardiac cine MRI reconstruction using adversarial autoencoder and unsupervised learning

et al. 2020

View full text Add to dashboard Cite

The aim of this study was to develop a deep neural network for respiratory motion compensation in free‐breathing cine MRI and evaluate its performance. An adversarial autoencoder network was trained using unpaired training data from healthy volunteers and patients who underwent clinically indicated cardiac MRI examinations. A U‐net structure was used for the encoder and decoder parts of the network and the code space was regularized by an adversarial objective. The autoencoder learns the identity map for the free‐breathing motion‐corrupted images and preserves the structural content of the images, while the discriminator, which interacts with the output of the encoder, forces the encoder to remove motion artifacts. The network was first evaluated based on data that were artificially corrupted with simulated rigid motion with regard to motion‐correction accuracy and the presence of any artificially created structures. Subsequently, to demonstrate the feasibility of the proposed approach in vivo, our network was trained on respiratory motion‐corrupted images in an unpaired manner and was tested on volunteer and patient data. In the simulation study, mean structural similarity index scores for the synthesized motion‐corrupted images and motion‐corrected images were 0.76 and 0.93 (out of 1), respectively. The proposed method increased the Tenengrad focus measure of the motion‐corrupted images by 12% in the simulation study and by 7% in the in vivo study. The average overall subjective image quality scores for the motion‐corrupted images, motion‐corrected images and breath‐held images were 2.5, 3.5 and 4.1 (out of 5.0), respectively. Nonparametric‐paired comparisons showed that there was significant difference between the image quality scores of the motion‐corrupted and breath‐held images (P < .05); however, after correction there was no significant difference between the image quality scores of the motion‐corrected and breath‐held images. This feasibility study demonstrates the potential of an adversarial autoencoder network for correcting respiratory motion‐related image artifacts without requiring paired data.

show abstract

Retrospective correction of motion‐affected MR images using deep learning frameworks

Cited by 105 publications

References 31 publications

Rapid whole-heart CMR with single volume super-resolution

Rapid whole-heart CMR with single volume super-resolution

No‐reference image quality assessment of magnetic resonance images with high‐boost filtering and local features

Retrospective respiratory motion correction in cardiac cine MRI reconstruction using adversarial autoencoder and unsupervised learning

Contact Info

Product

Resources

About