[Noise Reduction Effect of Deep-learning-based Image Reconstruction Algorithms in Thin-section Chest CT]

Sichuan Da Xue Xue Bao Yi Xue Ban. 2021 Mar;52(2):286-292. doi: 10.12182/20210360506.
[Article in Chinese]

Abstract
in English, Chinese

Objective: To evaluate the noise reduction effect of deep learning-based reconstruction algorithms in thin-section chest CT images by analyzing images reconstructed with filtered back projection (FBP), adaptive statistical iterative reconstruction (ASIR), and deep learning image reconstruction (DLIR) algorithms.

Methods: The chest CT scan raw data of 47 patients were included in this study. Images of 0.625 mm were reconstructed using six reconstruction methods, including FBP, ASIR hybrid reconstruction (ASIR50%, ASIR70%), and deep learning low, medium and high modes (DL-L, DL-M, and DL-H). After the regions of interest were outlined in the aorta, skeletal muscle and lung tissue of each group of images, the CT values, SD values and signal-to-noise ratio (SNR) of the regions of interest were measured, and two radiologists evaluated the image quality.

Results: CT values, SD values and SNR of the images obtained by the six reconstruction methods showed statistically significant difference ( P<0.001). There were statistically significant differences in the image quality scores of the six reconstruction methods ( P<0.001). Images reconstruced with DL-H have the lowest noise and the highest overall quality score.

Conclusion: The model based on deep learning can effectively reduce the noise of thin-section chest CT images and improve the image quality. Among the three deep-learning models, DL-H showed the best noise reduction effect.

目的: 为了评估基于深度学习的重建算法在胸部薄层计算机断层扫描（computed tomography，CT）图像中的降噪效果，对滤波反投影重建（filtered back projection，FBP）、自适应统计迭代重建（adaptive statistical iterative reconstruction，ASIR）与深度学习图像重建（deep learning image reconstruction，DLIR）图像进行分析。

方法: 回顾性纳入47例患者胸部CT平扫原始数据，利用FBP，ASIR混合重建（ASIR50%、ASIR70%），深度学习低、中、高3种模式（DL-L、DL-M、DL-H）共6种，重建出0.625 mm的图像。在每组图像的主动脉内、骨骼肌以及肺组织内分别勾画感兴趣区，测量感兴趣区内的CT值、SD值和信噪比（signal-to-noise ratio，SNR）进行客观评价，并对图像进行主观评价。

结果: 6种重建图像CT、SD和SNR值的差异有统计学意义（P<0.001）。6种重建图像主观评分差异有统计学意义（P<0.001）。DLIR在主动脉和骨骼肌处的图像噪声明显低于传统的FBP和ASIR，图像质量能够满足临床需求。而且呈现出DL-H降噪效果最佳、噪声最低，ASIR70%、DL-M、ASIR50%、DL-L、FBP 图像噪声依次增加。通过主观评分的比较发现，DL-H的图像整体质量有明显的提升，但不能使肺纹理重建更清晰。

结论: 基于深度学习的模型能够有效减少胸部薄层CT图像的噪声，提高图像的质量。而在3种深度学习模型中，DL-H的降噪效能最佳。

Keywords: Computed tomography; Deep learning; The noise reduction algorithm.

MeSH terms

  • Algorithms
  • Deep Learning*
  • Humans
  • Image Processing, Computer-Assisted
  • Radiation Dosage
  • Radiographic Image Interpretation, Computer-Assisted
  • Tomography, X-Ray Computed