Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec 22;10(1):22.
doi: 10.3390/bioengineering10010022.

De-Aliasing and Accelerated Sparse Magnetic Resonance Image Reconstruction Using Fully Dense CNN with Attention Gates

Md Biddut Hossain  1 , Ki-Chul Kwon  1 , Shariar Md Imtiaz  1 , Oh-Seung Nam  1 , Seok-Hee Jeon  2 , Nam Kim  1
Affiliations

De-Aliasing and Accelerated Sparse Magnetic Resonance Image Reconstruction Using Fully Dense CNN with Attention Gates

Md Biddut Hossain et al. Bioengineering (Basel). .

Abstract

When sparsely sampled data are used to accelerate magnetic resonance imaging (MRI), conventional reconstruction approaches produce significant artifacts that obscure the content of the image. To remove aliasing artifacts, we propose an advanced convolutional neural network (CNN) called fully dense attention CNN (FDA-CNN). We updated the Unet model with the fully dense connectivity and attention mechanism for MRI reconstruction. The main benefit of FDA-CNN is that an attention gate in each decoder layer increases the learning process by focusing on the relevant image features and provides a better generalization of the network by reducing irrelevant activations. Moreover, densely interconnected convolutional layers reuse the feature maps and prevent the vanishing gradient problem. Additionally, we also implement a new, proficient under-sampling pattern in the phase direction that takes low and high frequencies from the k-space both randomly and non-randomly. The performance of FDA-CNN was evaluated quantitatively and qualitatively with three different sub-sampling masks and datasets. Compared with five current deep learning-based and two compressed sensing MRI reconstruction techniques, the proposed method performed better as it reconstructed smoother and brighter images. Furthermore, FDA-CNN improved the mean PSNR by 2 dB, SSIM by 0.35, and VIFP by 0.37 compared with Unet for the acceleration factor of 5.

Keywords: MRI reconstruction; aliasing artifacts; attention gate; deep learning; fully dense network.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Reconstructed artifact image from sparsely sampled k-space.
Figure 2
Figure 2
Flowchart of the proposed de-aliasing technique.
Figure 3
Figure 3
Proposed FDA-CNN architecture.
Figure 4
Figure 4
Last dense block with four layers of encoding part, where k5 = 128 and f5 = 512.
Figure 5
Figure 5
Schematic diagram of an attention gate.
Figure 6
Figure 6
Several sampling patterns: (a) fully sampled; (b) 2D Gaussian pattern; (c) 1D Gaussian pattern; (d) mixed center and periphery under-sampling pattern.
Figure 7
Figure 7
Training and validation losses of proposed FDA-CNN.
Figure 8
Figure 8
Reconstructed MRI images from the BraTs testing dataset (slice No. 140) using zero filling, Unet, and FDA-CNN: (a) 2D Gaussian distribution; (b) 1D Gaussian distribution; (c) mixed center and peripheral mask; (d) fully sampled ground truth image.
Figure 9
Figure 9
Comparison of three sampling patterns using FDA-CNN.
Figure 10
Figure 10
Reconstructed MRI images from the fastMRI dataset (slice No. 01) using zero filling, Unet, and FDA-CNN: (a) 2D Gaussian distribution; (b) 1D Gaussian distribution; (c) mixed center and peripheral mask; (d) fully sampled ground truth image.
Figure 11
Figure 11
Comparison of three sampling patterns on fastMRI dataset using FDA-CNN.
Figure 12
Figure 12
Reconstructed MRI images from IXI dataset (slice No. 75) using zero filling, Unet, and FDA-CNN at a sampling rate of 20%: (a) 2D Gaussian distribution; (b) 1D Gaussian distribution; (c) mixed center and peripheral under-sampling; (d) fully sampled ground truth image.
Figure 13
Figure 13
Comparison of three sampling patterns on IXI dataset using FDA-CNN.
Figure 14
Figure 14
Average NRMSE variation across the slices. Edge slices have larger errors.
See this image and copyright information in PMC

References

    1. Brown R.W., Cheng Y.-C.N., Haacke E.M., Thompson M.R., Venkatesan R. Magnetic Resonance Imaging: Physical Principles and Sequence Design. 2nd ed. John Wiley & Sons Ltd; Hoboken, NJ, USA: 2014.
    1. Cercignani M., Dowell N.G., Paul S. Tofts Quantitative MRI of the Brain: Principles of Physical Measurement. Volume 15. CRC Press; Boca Raton, FL, USA: 2018.
    1. Muckley M.J., Riemenschneider B., Radmanesh A., Kim S., Jeong G., Ko J., Jun Y., Shin H., Hwang D., Mostapha M., et al. Results of the 2020 fastMRI challenge for machine learning MR image reconstruction. IEEE Trans. Med. Imaging. 2021;40:2306–2317. doi: 10.1109/TMI.2021.3075856. - DOI - PMC - PubMed
    1. Por E., van Kooten M., Sarkovic V. Nyquist–Shannon Sampling Theorem. Leiden University; Leiden, The Netherlands: 2019.
    1. Schoenberg S.O., Dietrich O., Reiser M.F. Parallel Imaging in Clinical MR Applications. Springer; Berlin/Heidelberg, Germany: 2007. (Medical Radiology).

LinkOut - more resources