Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Feb 25;41(2):230-237.
doi: 10.12122/j.issn.1673-4254.2021.02.10.

[CT image quality assessment based on prior information of pre-restored images]

[Article in Chinese]
Q Gao  1 , M Zhu  1 , D Li  1 , Z Bian  1 , J Ma  1
Affiliations

[CT image quality assessment based on prior information of pre-restored images]

[Article in Chinese]
Q Gao et al. Nan Fang Yi Ke Da Xue Xue Bao. .

Abstract
in English, Chinese

Objective: We propose a CT IQA strategy based on the prior information of pre-restored images (PR-IQA) to improve the performance of IQA models.

Objective: We propose a CNN-based no-reference CT IQA strategy using the prior information of image quality features in the image restoration algorithm, which is combined with the original distorted image information into the two CNNs through the pre-restored image and the residual image. Multi-information fusion was used to improve the feature extraction ability and prediction performance of CNN. We built a CT IQA dataset based on spiral CT data published by Mayo Clinic. The performance of PR- IQA was evaluated by calculating the quantitative metrics and statistical tests. The influence of different hyperparameter settings for PR-IQA was analyzed. We then compared PR-IQA with the BASELINE model based on the single CNN to evaluate the original distorted image without reference image and other eight IQA algorithms.

Objective: The comparative experiment results showed that the PR-IQA model based on the prior information of 3 different image restoration algorithms (BF, NLM and BM3D) was better than all the tested IQA algorithms. Compared with the BASELINE method, the proposed method showed significantly improved performance, and the mean PLCC was increased by 12.56% and SROCC by 19.95%, and RMSE was decreased by 22.77%.

Objective: The proposed PR-IQA method can make full use of the prior information of the image restoration algorithm to effectively predict the quality of CT images.

目的: 为有效提取更多无参考CT图像质量特征，本文提出一种基于预恢复图像先验信息的医用CT图像质量评估策略（PR-IQA），利用多信息融合输入提高IQA模型性能。

方法: 基于卷积神经网络（CNN）的无参考医用CT图像质量评估策略。该方法利用图像恢复算法中的图像质量特征先验信息，将其以预恢复图像和恢复前后残差图像的形式，与原始失真图像信息融合输入到两个CNN中，通过多信息融合以提升CNN的特征提取能力和预测性能。实验使用基于Mayo诊所公开螺旋CT数据所建立的医用CT图像质量评估数据集。通过计算定量指标以及统计学检验对PR-IQA性能进行评估，分析了不同超参数设置对PR-IQA性能的影响。并将PR-IQA与基于单个CNN模型直接对原始失真图像进行NR-IQA的方法（BASELINE）以及8种经典的IQA算法进行对比实验。

结果: 对比实验结果表明，基于3种不同图像恢复算法先验信息（双边滤波、非局部均值滤波、三维块匹配协同滤波）的PR-IQA模型性能优于所有对比IQA算法。并且相比BASELINE方法性能均有提升，其中PLCC平均提升12.56%，SROCC平均提升19.95%，RMSE平均降低22.77%。

结论: 本文提出的PR-IQA方法能够充分利用图像恢复算法的先验信息，有效地预测医用CT图像质量。

Keywords: convolutional neural network; image restoration algorithm; no-reference CT image quality assessment.

PubMed Disclaimer

Figures

1
1
PR-IQA方法框架 PR-IQAmethod framework.
2
2
分数融合概念示意图，坐标轴上方为原始失真图像和预恢复图像示例图 Schematic diagram of the score fusion concept. Above the coordinate axis are examples of original distorted image and pre-restored image.
3
3
不同剂量和部位的示例CT图像 Examples of CT images with different parts and dose levels.
4
4
超参数对PR-IQA方法性能的影响 Influence of hyperparameters on performance of PR-IQA method. A: Influence of patch size. B: Influence of conv layer number. C: Influence of kernel size. D: Influence of kernel number.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Cai J, Chen X, Huang W, et al. Image quality assessment on CT reconstruction images: Task-specific vs general quality assessment. Fully3D. 2017 [Cai J, Chen X, Huang W, et al. Image quality assessment on CT reconstruction images: Task-specific vs general quality assessment [J]. Fully3D, 2017.]
    1. Zarb F, Rainford L, McEntee MF. Image quality assessment tools for optimization of CT images. Radiography. 2010;16(2):147–53. doi: 10.1016/j.radi.2009.10.002. [Zarb F, Rainford L, McEntee MF. Image quality assessment tools for optimization of CT images[J]. Radiography, 2010, 16(2): 147-53.] - DOI
    1. Chow LS, Paramesran R. Review of medical image quality assessment. Biomed Signal Process Control. 2016;27(1):145–54. [Chow LS, Paramesran R. Review of medical image quality assessment[J]. Biomed Signal Process Control, 2016, 27(1): 145-54.]

    1. Gao Q, Li S, Zhu MM, et al. Combined global and local information for blind CT image quality assessment via deep learning[C]//SPIE Medical Imaging. Proc SPIE 11316, Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment, Houston, Texas, USA, 2020, 1131: 1131615.

    1. Kang L, Ye P, Li Y, et al. Convolutional neural networks for noreference image quality assessment[C]. IEEE Conf Comput Vis Pattern Recognit, 2014: 1733-40.