Application of sigmoidal optimization to reconstruct nuclear medicine image: Comparison with filtered back projection and iterative reconstruction method

Shin, Han-Back; Kim, Moo-Sub; Law, Martin; Djeng, Shih-Kien; Choi, Min-Geon; Choi, Byung Wook; Kang, Sungmin; Kim, Dong-Wook; Suh, Tae Suk; Yoon, Do-Kun

doi:10.1016/j.net.2020.06.029

Cited by 4 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Yu et al [5][6][7][8][9] proposed several nonlinear noise filters with easy algorithms, nonlinear distribution and large parameter space. Wang et al [10][11][12][13][14][15][16] proposed iterative denoising algorithms based on statistics, which are suitable for sampling data in different ways, and can reconstruct images for incomplete data, but the amount of calculation is large and the reconstruction speed is slow. Elbakri et al [17] believed that the number of photons detected by the detector approximately obeyed the Poisson distribution where the background noise is Gaussian noise, and proposed a penalty maximum likelihood estimation algorithm for denoising.…”

Section: Introductionmentioning

confidence: 99%

Low-dose CT I mage D enoising M ethod B ased on Generative Adversarial Network

Jiao

Yang

Shi

et al. 2022

Preprint

View full text Add to dashboard Cite

In order to solve the problems of artifacts and noise in low-dose computed tomography ( CT ) images in clinical medical diagnosis, an improved image denoising algorithm under the architecture of generative adversarial network ( GAN ) is proposed. First, a noise model based on Style GAN2 is constructed to estimate the real noise distribution, and the noise information similar to the real noise distribution is generated by as the experimental noise data set. Then, a network model with encoder-decoder architecture as the core based on GAN idea is constructed, and the network model is trained with the generated noise data set until it reaches the optimal value. Finally, the noise and artifacts in low-dose CT images can be removed by inputting low-dose CT images into the denoising network. The experimental results show that the constructed network model based on GAN architecture can improve the utilization rate of noise feature information and the stability of network training, remove image noise and artifacts, and the reconstructed image has rich texture and realistic visual effect.

show abstract