Abstract

The necessity for high-quality images obtained with limited radiation dose has led to the widespread use of super-resolution (SR) technology in medical imaging, particularly in conjunction with low-dose computed tomography (CT) and low-field MRI technology. Nevertheless, SR remains a formidable challenge due to its inherent complexity and the stringent requirements for image quality. In this study, the study suggests mixed residual attention super-resolution generative adversarial network (MRA-SRGAN), a GAN-based model for medical image super-resolution (MISR), designed to address the challenges of high-quality imaging with limited radiation in low-dose CT and low-field MRI. By integrating residual channel attention groups (RCAGs) and convolutional block attention modules (CBAMs) in the generator, and depthwise separable convolutions (DS-Convs) in the discriminator, our model enhances local detail recovery while reducing computational complexity. On the LUNA 16 and Covid19-CT-Scans datasets, MRA-SRGAN achieves peak signal-to-noise ratios (PSNRs) of 32.121 dB and 26.513 dB, and structural similarity indices (SSIMs) of 0.990 and 0.981, outperforming traditional methods. This approach effectively preserves high-frequency information, with future work aimed at further optimizing attention mechanisms and improving clinical applicability.

References

1.
Zhang
,
S.
, and
Metaxas
,
D.
,
2024
, “
On the Challenges and Perspectives of Foundation Models for Medical Image Analysis
,”
Med. Image Anal.
,
91
, p.
102996
.10.1016/j.media.2023.102996
2.
Amiri
,
Z.
,
Heidari
,
A.
,
Navimipour
,
N. J.
,
Esmaeilpour
,
M.
, and
Yazdani
,
Y.
,
2024
, “
The Deep Learning Applications in IoT-Based Bio- and Medical Informatics: A Systematic Literature Review
,”
Neural Comput. Appl.
,
36
(
11
), pp.
5757
5797
.10.1007/s00521-023-09366-3
3.
Zhang
,
Z.
,
Yu
,
C.
,
Wu
,
Y.
,
Wang
,
Z.
,
Xu
,
H.
,
Yan
,
Y.
,
Zhan
,
Z.
, and
Yin
,
S.
,
2024
, “
Semiconducting Polymer Dots for Multifunctional Integrated Nanomedicine Carriers
,”
Mater. Today Bio
,
26
, p.
101028
.10.1016/j.mtbio.2024.101028
4.
Ledig
,
C.
,
Theis
,
L.
, and
Huszár
,
F.
, Caballero, J., Cunningham, A., Acosta, A., Aitken, A., et al.,
2017
, “
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
,”
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
, Honolulu, HI, July 21--26, pp.
4681
4690
.10.1109/CVPR.2017.19
5.
Li
,
H.
,
Hossain
,
N. M. L.
,
Trocan
,
M.
,
Galayko
,
D.
, and
Sawan
,
M.
,
2024
, “
CMISR: Circular Medical Image Super-Resolution
,”
Eng. Appl. Artif. Intell.
,
133
, p.
108222
.10.1016/j.engappai.2024.108222
6.
Zhou
,
S. K.
,
Greenspan
,
H.
,
Davatzikos
,
C.
,
Duncan
,
J. S.
,
Van Ginneken
,
B.
,
Madabhushi
,
A.
,
Prince
,
J. L.
,
Rueckert
,
D.
, and
Summers
,
R. M.
,
2021
, “
A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future Promises
,”
Proc. IEEE
,
109
(
5
), pp.
820
838
.10.1109/JPROC.2021.3054390
7.
You
,
C.
,
Cong
,
W.
,
Vannier
,
M. W.
,
Saha
,
P. K.
,
Hoffman
,
E. A.
,
Wang
,
G.
, and
Li
,
G.
, et al.,
2020
, “
CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE)
,”
IEEE Trans. Med. Imaging
,
39
(
1
), pp.
188
203
.10.1109/TMI.2019.2922960
8.
Wang
,
X.
,
Yu
,
K.
,
Wu
,
S.
,
Gu
,
J.
,
Liu
,
Y.
,
Dong
,
C.
,
Loy
,
C. C.
,
Qiao
,
Y.
, and
Tang
,
X.
,
2018
, “
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
,” Proceedings of the European Conference on Computer Vision (
ECCV
) Workshops, Munich, Germany, Sept. 8--14.10.48550/arXiv.1809.00219
9.
Lyu
,
Y.
,
Jiang
,
X.
,
Xu
,
Y.
,
Hou
,
J.
,
Zhao
,
X.
, and
Zhu
,
X.
,
2023
, “
ARU-GAN: U-Shaped GAN Based on Attention and Residual Connection for Super-Resolution Reconstruction
,”
Comput. Biol. Med.
,
164
, p.
107316
.10.1016/j.compbiomed.2023.107316
10.
Patil
,
A.
,
2021
, “
DCGAN: Deep Convolutional GAN With Attention Module for Remote View Classification
,” 2021 International Conference on Forensics, Analytics, Big Data, Security (
FABS
), Vol.
1
, Bengaluru, India, Dec. 21–22, pp.
1
10
.10.1109/FABS52071.2021.9702655
11.
Odena
,
A.
,
2017
, “
Semi-Supervised Learning With Generative Adversarial Networks
,” Proceedings of the 31st International Conference on Neural Information Processing Systems (
NeurIPS
), Long Beach, CA, Dec. 4–9, pp. 2685–2694.10.48550/arXiv.1606.01583
12.
Kornack
,
D.
, and
Rakic
,
P.
,
2001
, “
Cell Proliferation Without Neurogenesis in Adult Primate Neocortex
,”
Science
,
294
(
5549
), pp.
2127
2130
.10.1126/science.1065467
13.
Goto
,
H.
,
Hasegawa
,
Y.
, and
Tanaka
,
M.
,
2007
, “
Efficient Scheduling Focusing on the Duality of MPL Representatives
,” Proceedings of the IEEE Symposium on Computational Intelligence in Scheduling (
SCIS 07
), Long Beach, CA, June 16--20, pp.
57
64
.10.1109/SCIS.2007.367670
14.
Karras
,
T.
,
Laine
,
S.
, and
Aila
,
T.
,
2019
, “
A Style-Based Generator Architecture for Generative Adversarial Networks
,” 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (
CVPR
), Long Beach, CA, June 16--20.10.1109/CVPR.2019.00453
15.
Gu
,
Y.
,
Zeng
,
Z.
,
Chen
,
H.
,
Wei
,
J.
,
Zhang
,
Y.
,
Chen
,
B.
, and
Li
,
Y.
, et al.,
2020
, “
MedSRGAN: Medical Images Super-Resolution Using Generative Adversarial Networks
,”
Multimedia Tools Appl.
,
79
(
29–30
), pp.
21815
21840
.10.1007/s11042-020-08980-w
16.
Du
,
W.
, and
Tian
,
S.
,
2024
, “
Transformer and GAN-Based Super-Resolution Reconstruction Network for Medical Images
,”
Tsinghua Sci. Technol.
,
29
(
1
), pp.
197
206
.10.26599/TST.2022.9010071
17.
Kingma
,
D. P.
, and Ba, J.,
2015
, “
Adam: A Method for Stochastic Optimization
,” Proceedings of the 3rd International Conference on Learning Representations (
ICLR
), San Diego, CA, May 7–9.10.48550/arXiv.1412.6980
You do not currently have access to this content.