Incorporation of residual attention modules into two neural networks for low-dose CT denoising
- PMID: 33890681
- DOI: 10.1002/mp.14856
Incorporation of residual attention modules into two neural networks for low-dose CT denoising
Abstract
Purpose: The low-dose computed tomography (CT) imaging can reduce the damage caused by x-ray radiation to the human body. However, low-dose CT images have a different degree of artifacts than conventional CT images, and their resolution is lower than that of conventional CT images, which can affect disease diagnosis by clinicians. Therefore, methods for noise-level reduction and resolution improvement in low-dose CT images have inevitably become a research hotspot in the field of low-dose CT imaging.
Methods: In this paper, residual attention modules (RAMs) are incorporated into the residual encoder-decoder convolutional neural network (RED-CNN) and generative adversarial network with Wasserstein distance (WGAN) to learn features that are beneficial to improving the performances of denoising networks, and developed models are denoted as RED-CNN-RAM and WGAN-RAM, respectively. In detail, RAM is composed of a multi-scale convolution module and an attention module built on the residual network architecture, where the attention module consists of a channel attention module and a spatial attention module. The residual network architecture solves the problem of network degradation with increased network depth. The function of the attention module is to learn which features are beneficial to reduce the noise level of low-dose CT images to reduce the loss of detail in the final denoising images, which is also the key point of the proposed algorithms.
Results: To develop a robust network for low-dose CT image denoising, multidose-level torso phantom images provided by a cooperating equipment vendor are used to train the network, which can improve the network's adaptability to clinical application. In addition, a clinical dataset is used to test the network's migration capabilities and clinical applicability. The experimental results demonstrate that these proposed networks can effectively remove noise and artifacts from multidose CT scans. Subjective and objective analyses of multiple groups of comparison experiments show that the proposed networks achieve good noise suppression performance while preserving the image texture details.
Conclusion: In this study, two deep learning network models are developed using multidose-level CT images acquired from a commercial spiral CT scanner. The two network models can reduce and even remove streaking artifacts, and noise from low-dose CT images confirms the effectiveness of the proposed algorithms.
Keywords: RED-CNN; WGAN; image denoising; low-dose CT; residual attention module.
© 2021 American Association of Physicists in Medicine.
Similar articles
-
STEDNet: Swin transformer-based encoder-decoder network for noise reduction in low-dose CT.Med Phys. 2023 Jul;50(7):4443-4458. doi: 10.1002/mp.16249. Epub 2023 Feb 9. Med Phys. 2023. PMID: 36708286
-
A performance comparison of convolutional neural network-based image denoising methods: The effect of loss functions on low-dose CT images.Med Phys. 2019 Sep;46(9):3906-3923. doi: 10.1002/mp.13713. Epub 2019 Aug 6. Med Phys. 2019. PMID: 31306488 Free PMC article.
-
Artifact correction in low-dose dental CT imaging using Wasserstein generative adversarial networks.Med Phys. 2019 Apr;46(4):1686-1696. doi: 10.1002/mp.13415. Epub 2019 Feb 14. Med Phys. 2019. PMID: 30697765
-
HCformer: Hybrid CNN-Transformer for LDCT Image Denoising.J Digit Imaging. 2023 Oct;36(5):2290-2305. doi: 10.1007/s10278-023-00842-9. Epub 2023 Jun 29. J Digit Imaging. 2023. PMID: 37386333 Free PMC article. Review.
-
A Review of deep learning methods for denoising of medical low-dose CT images.Comput Biol Med. 2024 Mar;171:108112. doi: 10.1016/j.compbiomed.2024.108112. Epub 2024 Feb 15. Comput Biol Med. 2024. PMID: 38387380 Review.
Cited by
-
Reducing image artifacts in sparse projection CT using conditional generative adversarial networks.Sci Rep. 2024 Feb 16;14(1):3917. doi: 10.1038/s41598-024-54649-x. Sci Rep. 2024. PMID: 38365934 Free PMC article.
-
CT image denoising methods for image quality improvement and radiation dose reduction.J Appl Clin Med Phys. 2024 Feb;25(2):e14270. doi: 10.1002/acm2.14270. Epub 2024 Jan 19. J Appl Clin Med Phys. 2024. PMID: 38240466 Free PMC article. Review.
-
Parallel processing model for low-dose computed tomography image denoising.Vis Comput Ind Biomed Art. 2024 Jun 12;7(1):14. doi: 10.1186/s42492-024-00165-8. Vis Comput Ind Biomed Art. 2024. PMID: 38865022 Free PMC article.
-
Evaluation of motion artefact reduction depending on the artefacts' directions in head MRI using conditional generative adversarial networks.Sci Rep. 2023 May 26;13(1):8526. doi: 10.1038/s41598-023-35794-1. Sci Rep. 2023. PMID: 37237139 Free PMC article.
-
Understanding the harm of low-dose computed tomography radiation to the body (Review).Exp Ther Med. 2022 Jun 23;24(2):534. doi: 10.3892/etm.2022.11461. eCollection 2022 Aug. Exp Ther Med. 2022. PMID: 35911849 Free PMC article. Review.
References
REFERENCES
-
- Brenner DJ, Ph D, Sc D, Hall EJ, Phil D, Sc D. Computed tomography - an increasing source of radiation exposure. N Engl J Med. 2007;357:2277-2284.
-
- Jiang H. Adaptive streak artifact reduction in computed tomography resulting from excessive x-ray photon noise. Med Phys. 1998;25:2139-2147.
-
- Kachelrieß M, Watzke O, Kalender WA. Generalized multi-dimensional adaptive filtering for conventional and spiral single-slice, multi-slice, and cone-beam CT. Med Phys. 2001;28:475-490.
-
- Kwan ALC, Boone JM, Shah N. Evaluation of x-ray scatter properties in a dedicated cone-beam breast CT scanner. Med Phys. 2005;32:2967-2975.
-
- Wang J, Li T, Hongbing LU, Liang Z. Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography. IEEE Trans Med Imaging. 2006;25:1272-1283.
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources