Effect of correction methods on image resolution of myocardial perfusion imaging using single photon emission computed tomography combined with computed tomography hybrid systems

Tantawy, Hazem M.; Abdelhafez, Yasser; Helal, Nadia; Kany, A.M.I.; Saad, Ibrahim E.

doi:10.1088/2399-6528/ab661b

Cited by 1 publication

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to traditional mathematical methods, neural networks possess superior non-linear matching capabilities. SR methods based on deep learning include different usage scenarios, such as those based on classic blind image SR [3], non-blind image SR [19], real image SR [20], text-focused scene image SR [21], lightweight image SR [22], hyperspectral image SR [23], video SR [24], attenuation correction SR [25,26], etc. Dong et al first introduced SRCNN [3], which contains three convolutional layers, to address superresolution issues.…”

Section: Image Super-resolution Based On Deep Learningmentioning

confidence: 99%

Frequency-Separated Attention Network for Image Super-Resolution

Qu,

Li,

Yao

2024

Applied Sciences

View full text Add to dashboard Cite

The use of deep convolutional neural networks has significantly improved the performance of super-resolution. Employing deeper networks to enhance the non-linear mapping capability from low-resolution (LR) to high-resolution (HR) images has inadvertently weakened the information flow and disrupted long-term memory. Moreover, overly deep networks are challenging to train, thus failing to exhibit the expressive capability commensurate with their depth. High-frequency and low-frequency features in images play different roles in image super-resolution. Networks based on CNNs, which should focus more on high-frequency features, treat these two types of features equally. This results in redundant computations when processing low-frequency features and causes complex and detailed parts of the reconstructed images to appear as smooth as the background. To maintain long-term memory and focus more on the restoration of image details in networks with strong representational capabilities, we propose the Frequency-Separated Attention Network (FSANet), where dense connections ensure the full utilization of multi-level features. In the Feature Extraction Module (FEM), the use of the Res ASPP Module expands the network’s receptive field without increasing its depth. To differentiate between high-frequency and low-frequency features within the network, we introduce the Feature-Separated Attention Block (FSAB). Furthermore, to enhance the quality of the restored images using heuristic features, we incorporate attention mechanisms into the Low-Frequency Attention Block (LFAB) and the High-Frequency Attention Block (HFAB) for processing low-frequency and high-frequency features, respectively. The proposed network outperforms the current state-of-the-art methods in tests on benchmark datasets.

show abstract