Related Experiment Video
Updated: Oct 1, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Dual U-Net residual networks for cardiac magnetic resonance images super-resolution
Defu Qiu1, Yuhu Cheng1, Xuesong Wang1
1Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou 221116, China; School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China.
Insights
This study introduces a Dual U-Net Residual Network (DURN) to enhance cardiac magnetic resonance (CMR) imaging resolution. The DURN method significantly improves image quality, offering clearer details for better heart disease diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Biomedical Engineering
Background:
- Heart disease is a leading cause of mortality, with increasing incidence.
- Cardiac magnetic resonance (CMR) imaging is crucial for diagnosing and treating heart disease.
- Improving CMR image resolution is vital for accurate medical assessment.
Purpose of the Study:
- To address limitations in current single-image super-resolution (SISR) methods for CMR images.
- To enhance the resolution of CMR images for improved diagnostic capabilities.
Main Methods:
- Proposed a novel Dual U-Net Residual Network (DURN) for CMR image super-resolution.
- The DURN model utilizes dual U-Net structures with residual connections to extract and upscale deep features.
- Employs residual blocks, up-blocks, and down-blocks for comprehensive feature extraction.
Main Results:
- DURN achieved peak signal to noise ratio (PSNR) values of 37.86 dB, 33.96 dB, and 31.65 dB at scale factors 2, 3, and 4, respectively.
- Demonstrated significant improvements over Bicubic and competitive performance against LapSRN algorithms.
- Results on benchmark datasets confirmed DURN's effectiveness in enhancing image quality.
Conclusions:
- The proposed DURN method outperforms existing state-of-the-art SR algorithms in PSNR and SSIM.
- DURN reconstructs super-resolution CMR images with superior clarity, richer details, and sharper edges.
- This advancement holds significant medical value for the diagnosis and assessment of heart disease.
Background And Objective:
Heart disease is a vital disease that has threatened human health, and is the number one killer of human life. Moreover, with the added influence of recent health factors, its incidence rate keeps showing an upward trend. Today, cardiac magnetic resonance (CMR) imaging can provide a full range of structural and functional information for the heart, and has become an important tool for the diagnosis and treatment of heart disease. Therefore, improving the image resolution of CMR has an important medical value for the diagnosis and condition assessment of heart disease. At present, most single-image super-resolution (SISR) reconstruction methods have some serious problems, such as insufficient feature information mining, difficulty to determine the dependence of each channel of feature map, and reconstruction error when reconstructing high-resolution image.
Methods:
To solve these problems, we have proposed and implemented a dual U-Net residual network (DURN) for super-resolution of CMR images. Specifically, we first propose a U-Net residual network (URN) model, which is divided into the up-branch and the down-branch. The up-branch is composed of residual blocks and up-blocks to extract and upsample deep features; the down-branch is composed of residual blocks and down-blocks to extract and downsample deep features. Based on the URN model, we employ this a dual U-Net residual network (DURN) model, which combines the extracted deep features of the same position between the first URN and the second URN through residual connection. It can make full use of the features extracted by the first URN to extract deeper features of low-resolution images.
Results:
When the scale factors are 2, 3, and 4, our DURN can obtain 37.86 dB, 33.96 dB, and 31.65 dB on the Set5 dataset, which shows (i) a maximum improvement of 4.17 dB, 3.55 dB, and 3.22dB over the Bicubic algorithm, and (ii) a minimum improvement of 0.34 dB, 0.14 dB, and 0.11 dB over the LapSRN algorithm.
Conclusion:
Comprehensive experimental study results on benchmark datasets demonstrate that our proposed DURN can not only achieve better performance for peak signal to noise ratio (PSNR) and structural similarity index (SSIM) values than other state-of-the-art SR image algorithms, but also reconstruct clearer super-resolution CMR images which have richer details, edges, and texture.
