Numerous deep leaning methods for low-dose computed technology (CT) image denoising have been proposed, achieving impressive results. However, issues such as loss of structure and edge information and low denoising efficiency still exist.
Objective
To improve image denoising quality, an enhanced multi-dimensional hybrid attention LDCT image denoising network based on edge detection is proposed in this paper.
Methods
In our network, we employ a trainable Sobel convolution to design an edge enhancement module and fuse an enhanced triplet attention network (ETAN) after each convolutional layer to extract richer features more comprehensively and suppress useless information. During the training process, we adopt a strategy that combines total variation loss (TVLoss) with mean squared error (MSE) loss to reduce high-frequency artifacts in image reconstruction and balance image denoising and detail preservation.
Results
Compared with other advanced algorithms (CT-former, REDCNN and EDCNN), our proposed model achieves the best PSNR and SSIM values in CT image of the abdomen, which are 34.8211and 0.9131, respectively.
Conclusion
Through comparative experiments with other related algorithms, it can be seen that the algorithm proposed in this article has achieved significant improvements in both subjective vision and objective indicators.
KalraMKHomayouniehFArruC, et al.Chest CT practice and protocols for COVID-19 from radiation dose management perspective. Eur Radiol2020; 30: 6554–6560.
2.
LiBLiXWangY, et al.Diagnostic value and key features of computed tomography in Coronavirus Disease 2019. Emerg Microbes Infect2020; 9: 787–793.
3.
MaYWeiBFengP, et al.Low-dose CT image denoising using a generative adversarial network with a hybrid loss function for noise learning. IEEE Access2020; 8: 67519–67529.
4.
ImmonenEWongJNieminenM, et al.The use of deep learning towards dose optimization in low-dose computed tomography: a scoping review. Radiography2022; 28: 208–214.
5.
MäkinenYAzzariLFoiA. Collaborative filtering of correlated noise: exact transform-domain variance for improved shrinkage and patch matching. IEEE Trans Image Process2020; 29: 8339–8354.
6.
GreffierJFrandonJLarbiA, et al.CT Iterative reconstruction algorithms: a task-based image quality assessment. Eur Radiol2020; 30: 487–500.
7.
RongPJianchengHGuoquanH, et al.The application value of 256-slice spiral CT dynamic enhancement and multi-mode post-processing technology in preoperative diagnosis and staging of colorectal cancer. Anhui Med Pharm J2020; 24: 766–770.
8.
ZhangYZhangHLuH. Statistical sinogram smoothing for low-dose CT with segmentation-based adaptive filtering. IEEE Trans Nucl Sci2010; 57: 2587–2598.
9.
WangJLiTLuZ, et al.Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography. IEEE Trans Med Imag2006; 25: 1272–1283.
10.
ChenYMaJFengQ, et al.Nonlocal prior Bayesian tomographic reconstruction. Math Imag Vis2008; 30: 133–146.
11.
ChenYGaoCNieC, et al.Bayesian Statistical reconstruction for low-dose X-ray computed tomography using an adaptive nonlocal prior. Comput Med Imag Graph2009; 33: 495–500.
12.
ChenYYinXShiL, et al.Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing. Phys Med Biol2013; 58: 5803–5820.
13.
WangPFanEWangP. Comparative analysis of image classification algorithms based on traditional machine learning and deep learning. Pattern Recognit Lett2021; 141: 61–67.
14.
LiangTJinYLiY, et al.Edcnn: Edge enhancement-based densely connected network with compound loss for low-dose CT denoising. In: 2020 15th IEEE International conference on signal processing (ICSP), 2020, 1, pp. 193–198. IEEE.
15.
ZeilerMDTaylorGWFergusR. Adaptive deconvolutional networks for mid and high level feature learning. Proc IEEE Int Conf Comput Vis2011; 12: 2018–2025.
16.
HeKZhangXRenS,et al.Deep residual learning for image recognition. Proc IEEE Conf Comput Vis Pattern Recognit2016; 5: 770–778.
17.
ChenHZhangYKalraMK, et al.Low-Dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans Med Imag2017; 36: 2524–2535.
18.
YangQYanPZhangY, et al.Low-Dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss. IEEE Trans Med Imag2018; 37: 1348–1357.
19.
ChenXZhanSJiD, et al.Image denoising via deep network based on edge enhancement. Ambient Intell Humanized Comput2023; 14: 14795–14805.
20.
ZhangYHuDZhaoQ, et al.CLEAR: comprehensive learning enabled adversarial reconstruction for subtle structure enhanced low-dose CT imaging. IEEE Trans Med Imag2021; 40: 3089–3101.
21.
WangDFanFWuZ, et al.CTformer: convolution-free Token2Token dilated vision transformer for low-dose CT denoising. Phys Med Biol2023; 68: 065012.
22.
AnwarSBarnesN. Real image denoising with feature attention. In Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 3155–3164.
23.
LiMDuQDuanL, et al.Incorporation of residual attention modules into two neural networks for low-dose CT denoising. Med Phys2021; 48: 2973–2990.
24.
ZhaoHGalloOFrosioI, et al.Loss functions for image restoration with neural networks. IEEE Trans Computat Imag2017; 3: 47–57.
25.
JohnsonJAlahiAFei-FeiL. Perceptual losses for realtime style transfer and super-resolution. Cham: Springer, 2016, pp. 694–711.
26.
HangZOrazioG. Loss functions for image restoration with neural networks. IEEE Trans Computat Imag2017; 3: 47–57.
27.
TangYDuQWangJ, , et al.CCN-CL: a content-noise complementary network with constrastive learning for low-dose computed tomography denoising. Comput Biol Med2022; 147: 105759–105769.
28.
WuHQuYLinS, et al.Contrastive learning for compact single image dehazing. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 10551–10560.
29.
KhanMSMAhmedMRaselRZ, et al.Cataract detection using convolutional neural network with VGG-19 model. In: 2021 IEEE World AI IoT Congress (AIIoT), 2021, pp. 0209–0212. IEEE.
30.
ZulqarnainMGhazaliRAamirM, et al.An efficient two-state GRU based on feature attention mechanism for sentiment analysis. Multim Tools Appl2024; 83: 3085–3110.
31.
LiXLiMYanP, et al.Deep learning attention mechanism in medical image analysis: basics and beyonds. Int J Netw Dyn Intell2023; 14: 93–116.
32.
TangLYiJLiX. Improved multi-scale inverse bottleneck residual network based on triplet parallel attention for apple leaf disease identification. J Integr Agric2024; 23: 901–922.
33.
ScianoDRazaASalcedoR, et al.Evaluation of DC links on dense-load urban distribution networks. IEEE Trans Power Deliv2016; 31: 1317–1326.
34.
MaZXiaMLinH, et al.FENet: feature enhancement network for land cover classification. Int J Remote Sens2023; 44: 1702–1725.
35.
DongWZhaoJQuJ, et al.Abundance matrix correlation analysis network based on hierarchical multihead self-cross-hybrid attention for hyperspectral change detection. IEEE Trans Geosci Remote Sens2023; 61: 1–13.
36.
JinJZhouWYangR, et al.Edge detection guide network for semantic segmentation of remote-sensing images. IEEE Geosci Remote Sens Lett2023; 20: 1–5.
37.
IqbalSQureshiANLiJ, et al.On the analyses of medical images using traditional machine learning techniques and convolutional neural networks. Arch Computat Methods Eng2023; 30: 3173–3233.
38.
LuoPWangBWangH, et al.An ultrasmall bolt defect detection method for transmission line inspection. IEEE Trans Instrumentat Measure2023; 72: 1–12.
39.
YangRXuQLongH. Spatial distribution characteristics and optimized reconstruction analysis of China’s rural settlements during the process of rapid urbanization. J Rural Stud2016; 47: 413–424.
40.
ChangYYanLZhongS. Transformed low-rank model for line pattern noise removal. In: Proceedings of the IEEE international conference on computer vision, 2017, pp. 1726–1734.
