Deep neural networks-based denoising models for CT imaging and their efficacy

被引:9
|
作者
Kc, Prabhat [1 ]
Zeng, Rongping [1 ]
Farhangi, M. Mehdi [1 ]
Myers, Kyle J. [1 ]
机构
[1] US FDA, Silver Spring, MD 20993 USA
来源
MEDICAL IMAGING 2021: PHYSICS OF MEDICAL IMAGING | 2021年 / 11595卷
关键词
CT image denoising; deep learning; neural networks; loss functions; image quality; LOW-DOSE CT; NUMBERS;
D O I
10.1117/12.2581418
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Most of the Deep Neural Networks (DNNs) based CT image denoising literature shows that DNNs outperform traditional iterative methods in terms of metrics such as the RMSE, the PSNR and the SSIM. In many instances, using the same metrics, the DNN results from low-dose inputs are also shown to be comparable to their high-dose counterparts. However, these metrics do not reveal if the DNN results preserve the visibility of subtle lesions or if they alter the CT image properties such as the noise texture. Accordingly, in this work, we seek to examine the image quality of the DNN results from a holistic viewpoint for low-dose CT image denoising. First, we build a library of advanced DNN denoising architectures. This library is comprised of denoising architectures such as the DnCNN, U-Net, Red-Net, GAN, etc. Next, each network is modeled, as well as trained, such that it yields its best performance in terms of the PSNR and SSIM. As such, data inputs (e.g. training patch-size, reconstruction kernel) and numeric-optimizer inputs (e.g. minibatch size, learning rate, loss function) are accordingly tuned. Finally, outputs from thus trained networks are further subjected to a series of CT bench testing metrics such as the contrast-dependent MTF, the NPS and the HU accuracy. These metrics are employed to perform a more nuanced study of the resolution of the DNN outputs' low-contrast features, their noise textures, and their CT number accuracy to better understand the impact each DNN algorithm has on these underlying attributes of image quality.
引用
收藏
页数:13
相关论文
共 50 条
  • [31] A joint deep neural networks-based method for single nighttime rainy image enhancement
    Zhenghao Shi
    Yaning Feng
    Minghua Zhao
    Lifeng He
    Neural Computing and Applications, 2020, 32 : 1913 - 1926
  • [32] Neural networks-based variationally enhanced sampling
    Bonati, Luigi
    Zhang, Yue-Yu
    Parrinello, Michele
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2019, 116 (36) : 17641 - 17647
  • [33] Neural networks-based approximation of fuzzy systems
    Gao, XZ
    Ovaska, SJ
    INTEGRATED COMPUTER-AIDED ENGINEERING, 2003, 10 (04) : 319 - 331
  • [34] A joint deep neural networks-based method for single nighttime rainy image enhancement
    Shi, Zhenghao
    Feng, Yaning
    Zhao, Minghua
    He, Lifeng
    NEURAL COMPUTING & APPLICATIONS, 2020, 32 (07): : 1913 - 1926
  • [35] Blast furnace hot metal temperature prediction through neural networks-based models
    Jiménez, J
    Mochón, J
    de Ayala, JS
    Obeso, F
    ISIJ INTERNATIONAL, 2004, 44 (03) : 573 - 580
  • [36] Multivariate Statistical Analysis for Training Process Optimization in Neural Networks-Based Forecasting Models
    Jimenez, Jamer
    Navarro, Loraine
    Quintero M, Christian G.
    Pardo, Mauricio
    APPLIED SCIENCES-BASEL, 2021, 11 (08):
  • [37] SENTIMENT ANALYSIS AND ARTIFICIAL NEURAL NETWORKS-BASED ECONOMETRIC MODELS FOR TOURISM DEMAND FORECASTING
    Folgieri, Raffaella
    Baldigara, Tea
    Mamula, Maja
    TOURISM & HOSPITALITY INDUSTRY 2018: TRENDS AND CHALLENGES, 2018, : 88 - 97
  • [38] Modeling of the pyruvate production with Escherichia coli: comparison of mechanistic and neural networks-based models
    B. Zelić
    N. Bolf
    Đ. Vasić-Rački
    Bioprocess and Biosystems Engineering, 2006, 29 : 39 - 47
  • [39] Claim Severity Prediction of Workers' Compensation Using Tree and Neural Networks-Based Models
    Tjahjono, Samuel
    Murfi, Hendri
    Devila, Sindy
    2024 11TH IEEE SWISS CONFERENCE ON DATA SCIENCE, SDS 2024, 2024, : 225 - 228
  • [40] Modeling of the pyruvate production with Escherichia coli:: comparison of mechanistic and neural networks-based models
    Zelic, B.
    Bolf, N.
    Vasic-Racki, D.
    BIOPROCESS AND BIOSYSTEMS ENGINEERING, 2006, 29 (01) : 39 - 47