Deep residual dense U-Net for resolution enhancement in accelerated MRI acquisition

Pak Lun Kevin Ding, Zhiqiang Li, Yuxiang Zhou, Baoxin Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Typical Magnetic Resonance Imaging (MRI) scan may take 20 to 60 minutes. Reducing MRI scan time is beneficial for both patient experience and cost considerations. Accelerated MRI scan may be achieved by acquiring less amount of k-space data (down-sampling in the k-space). However, this leads to lower resolution and aliasing artifacts for the reconstructed images. There are many existing approaches for attempting to reconstruct high-quality images from down-sampled k-space data, with varying complexity and performance. In recent years, deep-learning approaches have been proposed for this task, and promising results have been reported. Still, the problem remains challenging especially because of the high fidelity requirement in most medical applications employing reconstructed MRI images. In this work, we propose a deep-learning approach, aiming at reconstructing high-quality images from accelerated MRI acquisition. Specifically, we use Convolutional Neural Network (CNN) to learn the differences between the aliased images and the original images, employing a U-Net-like architecture. Further, a micro-architecture termed Residual Dense Block (RDB) is introduced for learning a better feature representation than the plain U-Net. Considering the peculiarity of the downsampled k-space data, we introduce a new term to the loss function in learning, which effectively employs the given k-space data during training to provide additional regularization on the update of the network weights. To evaluate the proposed approach, we compare it with other state-of-the-art methods. In both visual inspection and evaluation using standard metrics, the proposed approach is able to deliver improved performance, demonstrating its potential for providing an effective solution.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2019
Subtitle of host publicationImage Processing
EditorsBennett A. Landman, Elsa D. Angelini, Elsa D. Angelini, Elsa D. Angelini
PublisherSPIE
ISBN (Electronic)9781510625457
DOIs
StatePublished - Jan 1 2019
EventMedical Imaging 2019: Image Processing - San Diego, United States
Duration: Feb 19 2019Feb 21 2019

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10949
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2019: Image Processing
CountryUnited States
CitySan Diego
Period2/19/192/21/19

Fingerprint

magnetic resonance
acquisition
Magnetic Resonance Imaging
learning
augmentation
Learning
Image quality
Delayed Emergence from Anesthesia
Medical applications
Artifacts
plains
Inspection
artifacts
inspection
Sampling
Neural networks
education
Weights and Measures
Costs and Cost Analysis
sampling

Keywords

  • Accelerated MRI Acquisition
  • Deep Learning
  • U-Net

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Ding, P. L. K., Li, Z., Zhou, Y., & Li, B. (2019). Deep residual dense U-Net for resolution enhancement in accelerated MRI acquisition. In B. A. Landman, E. D. Angelini, E. D. Angelini, & E. D. Angelini (Eds.), Medical Imaging 2019: Image Processing [109490F] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10949). SPIE. https://doi.org/10.1117/12.2513158

Deep residual dense U-Net for resolution enhancement in accelerated MRI acquisition. / Ding, Pak Lun Kevin; Li, Zhiqiang; Zhou, Yuxiang; Li, Baoxin.

Medical Imaging 2019: Image Processing. ed. / Bennett A. Landman; Elsa D. Angelini; Elsa D. Angelini; Elsa D. Angelini. SPIE, 2019. 109490F (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10949).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ding, PLK, Li, Z, Zhou, Y & Li, B 2019, Deep residual dense U-Net for resolution enhancement in accelerated MRI acquisition. in BA Landman, ED Angelini, ED Angelini & ED Angelini (eds), Medical Imaging 2019: Image Processing., 109490F, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10949, SPIE, Medical Imaging 2019: Image Processing, San Diego, United States, 2/19/19. https://doi.org/10.1117/12.2513158
Ding PLK, Li Z, Zhou Y, Li B. Deep residual dense U-Net for resolution enhancement in accelerated MRI acquisition. In Landman BA, Angelini ED, Angelini ED, Angelini ED, editors, Medical Imaging 2019: Image Processing. SPIE. 2019. 109490F. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.2513158
Ding, Pak Lun Kevin ; Li, Zhiqiang ; Zhou, Yuxiang ; Li, Baoxin. / Deep residual dense U-Net for resolution enhancement in accelerated MRI acquisition. Medical Imaging 2019: Image Processing. editor / Bennett A. Landman ; Elsa D. Angelini ; Elsa D. Angelini ; Elsa D. Angelini. SPIE, 2019. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{0f3afe51ba494ab0b66a20cc5b029068,
title = "Deep residual dense U-Net for resolution enhancement in accelerated MRI acquisition",
abstract = "Typical Magnetic Resonance Imaging (MRI) scan may take 20 to 60 minutes. Reducing MRI scan time is beneficial for both patient experience and cost considerations. Accelerated MRI scan may be achieved by acquiring less amount of k-space data (down-sampling in the k-space). However, this leads to lower resolution and aliasing artifacts for the reconstructed images. There are many existing approaches for attempting to reconstruct high-quality images from down-sampled k-space data, with varying complexity and performance. In recent years, deep-learning approaches have been proposed for this task, and promising results have been reported. Still, the problem remains challenging especially because of the high fidelity requirement in most medical applications employing reconstructed MRI images. In this work, we propose a deep-learning approach, aiming at reconstructing high-quality images from accelerated MRI acquisition. Specifically, we use Convolutional Neural Network (CNN) to learn the differences between the aliased images and the original images, employing a U-Net-like architecture. Further, a micro-architecture termed Residual Dense Block (RDB) is introduced for learning a better feature representation than the plain U-Net. Considering the peculiarity of the downsampled k-space data, we introduce a new term to the loss function in learning, which effectively employs the given k-space data during training to provide additional regularization on the update of the network weights. To evaluate the proposed approach, we compare it with other state-of-the-art methods. In both visual inspection and evaluation using standard metrics, the proposed approach is able to deliver improved performance, demonstrating its potential for providing an effective solution.",
keywords = "Accelerated MRI Acquisition, Deep Learning, U-Net",
author = "Ding, {Pak Lun Kevin} and Zhiqiang Li and Yuxiang Zhou and Baoxin Li",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2513158",
language = "English (US)",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Landman, {Bennett A.} and Angelini, {Elsa D.} and Angelini, {Elsa D.} and Angelini, {Elsa D.}",
booktitle = "Medical Imaging 2019",

}

TY - GEN

T1 - Deep residual dense U-Net for resolution enhancement in accelerated MRI acquisition

AU - Ding, Pak Lun Kevin

AU - Li, Zhiqiang

AU - Zhou, Yuxiang

AU - Li, Baoxin

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Typical Magnetic Resonance Imaging (MRI) scan may take 20 to 60 minutes. Reducing MRI scan time is beneficial for both patient experience and cost considerations. Accelerated MRI scan may be achieved by acquiring less amount of k-space data (down-sampling in the k-space). However, this leads to lower resolution and aliasing artifacts for the reconstructed images. There are many existing approaches for attempting to reconstruct high-quality images from down-sampled k-space data, with varying complexity and performance. In recent years, deep-learning approaches have been proposed for this task, and promising results have been reported. Still, the problem remains challenging especially because of the high fidelity requirement in most medical applications employing reconstructed MRI images. In this work, we propose a deep-learning approach, aiming at reconstructing high-quality images from accelerated MRI acquisition. Specifically, we use Convolutional Neural Network (CNN) to learn the differences between the aliased images and the original images, employing a U-Net-like architecture. Further, a micro-architecture termed Residual Dense Block (RDB) is introduced for learning a better feature representation than the plain U-Net. Considering the peculiarity of the downsampled k-space data, we introduce a new term to the loss function in learning, which effectively employs the given k-space data during training to provide additional regularization on the update of the network weights. To evaluate the proposed approach, we compare it with other state-of-the-art methods. In both visual inspection and evaluation using standard metrics, the proposed approach is able to deliver improved performance, demonstrating its potential for providing an effective solution.

AB - Typical Magnetic Resonance Imaging (MRI) scan may take 20 to 60 minutes. Reducing MRI scan time is beneficial for both patient experience and cost considerations. Accelerated MRI scan may be achieved by acquiring less amount of k-space data (down-sampling in the k-space). However, this leads to lower resolution and aliasing artifacts for the reconstructed images. There are many existing approaches for attempting to reconstruct high-quality images from down-sampled k-space data, with varying complexity and performance. In recent years, deep-learning approaches have been proposed for this task, and promising results have been reported. Still, the problem remains challenging especially because of the high fidelity requirement in most medical applications employing reconstructed MRI images. In this work, we propose a deep-learning approach, aiming at reconstructing high-quality images from accelerated MRI acquisition. Specifically, we use Convolutional Neural Network (CNN) to learn the differences between the aliased images and the original images, employing a U-Net-like architecture. Further, a micro-architecture termed Residual Dense Block (RDB) is introduced for learning a better feature representation than the plain U-Net. Considering the peculiarity of the downsampled k-space data, we introduce a new term to the loss function in learning, which effectively employs the given k-space data during training to provide additional regularization on the update of the network weights. To evaluate the proposed approach, we compare it with other state-of-the-art methods. In both visual inspection and evaluation using standard metrics, the proposed approach is able to deliver improved performance, demonstrating its potential for providing an effective solution.

KW - Accelerated MRI Acquisition

KW - Deep Learning

KW - U-Net

UR - http://www.scopus.com/inward/record.url?scp=85068313704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068313704&partnerID=8YFLogxK

U2 - 10.1117/12.2513158

DO - 10.1117/12.2513158

M3 - Conference contribution

AN - SCOPUS:85068313704

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2019

A2 - Landman, Bennett A.

A2 - Angelini, Elsa D.

A2 - Angelini, Elsa D.

A2 - Angelini, Elsa D.

PB - SPIE

ER -