Variant Wasserstein Generative Adversarial Network Applied on Low Dose CT Image Denoising
Source abstract
Abstract
Computed Tomography (CT) images have been extensively employed in disease diagnosis and treatment, causing a huge concern over the dose of radiation to which patients are exposed. Increasing the radiation dose to get a better image may lead to the development of genetic disorders and cancer in the patients; on the other hand, decreasing it by using a Low-Dose CT (LDCT) image may cause more noise and increased artifacts, which can compromise the diagnosis. So, image reconstruction from LDCT image data is necessary to improve radiologists’ judgment and confidence. This study proposed three novel models for denoising LDCT images based on Wasserstein Generative Adversarial Network (WGAN). They were incorporated with different loss functions, including Visual Geometry Group (VGG), Structural Similarity Loss (SSIM), and Structurally Sensitive Loss (SSL), to reduce noise and preserve important information on LDCT images and investigate the effect of different types of loss functions. Furthermore, experiments have been conducted on the Graphical Processing Unit (GPU) and Central Processing Unit (CPU) to compare the performance of the proposed models. The results demonstrated that images from the proposed WGAN-SSIM, WGAN-VGG-SSIM, and WGAN-VGG-SSL were denoised better than those from state-of-the-art models (WGAN, WGAN-VGG, and SMGAN) and converged to a stable equilibrium compared with WGAN and WGAN-VGG. The proposed models are effective in reducing noise, suppressing artifacts, and maintaining informative structure and texture details, especially WGAN-VGG-SSL which achieved a high peak-signal-to-noise ratio (PNSR) on both GPU (26.1336) and CPU (25.8270). The average accuracy of WGAN-VGG-SSL outperformed that of the state-of-the-art methods by 1 percent. Experiments prove that the WGAN-VGG-SSL is more stable than the other models on both GPU and CPU.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Image and Signal Denoising Methods · Generative Adversarial Networks and Image Synthesis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Analyzing trend and forecasting of rainfall changes in India using non-parametrical and machine learning approaches10.1038/s41598-020-67228-7 ↗
2. CDLSTM: A novel model for climate change forecasting10.32604/cmc.2022.023059 ↗
3. Planetscope nanosatellites image classification using machine learning10.32604/csse.2022.023221 ↗
4. DNNBoT: Deep neural network-based botnet detection and classification10.32604/cmc.2022.020938 ↗
5. A survey of deep learning and its applications: A new paradigm to machine learning10.1007/s11831-019-09344-w ↗
6. Generative adversarial networks10.1145/3422622 ↗
7. I. Goodfellow, “NIPS 2016 tutorial: Generative adversarial networks,” arXiv preprint arXiv:1701.00160, pp. 1–57, 2016. [Online]. Available: https://arxiv.org/abs/1701.00160
8. In-domain GAN inversion for real image editing
9. Image-to-image translation with conditional adversarial networks
10. Photo-realistic single image super-resolution using a generative adversarial network
11. SSGAN: Secure steganography based on generative adversarial networks
12. A. Radford, L. Metz and S. Chintala, “Unsupervised representation learning with deep convolutional generative adversarial networks,” arXivpreprintarXiv:1511.06434, pp. 1–16, 2015. [Online]. Available: https://arxiv.org/abs/1511.06434
13. A. Brock, J. Donahue and K. Simonyan, “Large scale GAN training for high fidelity natural image synthesis,” arXiv Preprint arXiv, 1809.11096, pp. 1–35, 2018. [Online]. Available: https://arxiv.org/abs/1809.11096
14. Low-dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss
15. Medical image reconstruction with image-adaptive priors learned by use of generative adversarial networks
16. Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
17. SegAN: Adversarial network with multi-scale L1 loss for medical image segmentation
18. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery
19. F-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks
20. Deep learning in medical imaging: General overview
21. Synthetic data augmentation using GAN for improved liver lesion classification
22. Deep learning in medical ultrasound analysis: A review10.1016/j.eng.2018.11.020 ↗
23. Low-dose CT with a residual encoder-decoder convolutional neural network
24. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, pp. 1–14, 2014. [Online]. Available: https://arxiv.org/abs/1409.1556
25. Structurally-sensitive multi-scale deep neural network for low-dose CT denoising
26. Low-dose CT denoising using a progressive wasserstein generative adversarial network
27. Loss functions for image restoration with neural networks10.1109/TCI.2016.2644865 ↗
28. M. Arjovsky and L. Bottou, “Towards principled methods for training generative adversarial networks,” arXiv preprint arXiv:1701.04862, pp. 1–17, 2017. [Online]. Available: https://arxiv.org/abs/1701.04862
29. Improved techniques for training GANs
30. Improved training of wasserstein GANs
31. Projection space denoising with bilateral filtering and CT noise modeling for dose reduction in CT
32. Iterative reconstruction technique for reducing body radiation dose at CT: Feasibility study
33. Low-dose computed tomography image restoration using previous normal-dose scan
34. Generative adversarial networks for noise reduction in low-dose CT
35. Low-dose CT via convolutional neural network
36. A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction
37. SCRDN: Residual dense network with self-calibrated convolutions for low dose CT image denoising10.1016/j.nima.2022.167625 ↗
38. Sharpness-aware low-dose CT denoising using conditional generative adversarial network
39. Low-dose CT image denoising using a generative adversarial network with a hybrid loss function for noise learning10.1109/ACCESS.2020.2986388 ↗
40. MM-Net: Multi-frame and multi-mask-based unsupervised deep denoising for low-dose computed tomography
41. Unpaired low-dose CT denoising via an improved cycle-consistent adversarial network with attention ensemble
42. Q. Yang, P. Yan, M. K. Kalra and G. Wang, “CT image denoising with perceptive deep neural networks,” arXiv preprint arXiv:1702.07019, pp. 1–8, 2017. [Online]. Available: https://arxiv.org/abs/1702.07019
43. Rectified linear units improve restricted boltzmann machines
44. AAPM, “Low dose CT grand challenge,” 2017. [Online]. Available: http://www.aapm.org/GrandChallenge/LowDoseCT/#
45. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, pp. 1–15, 2014. [Online]. Available: https://arxiv.org/abs/1412.6980