Comparison of image quality and lesion diagnosis in abdominopelvic unenhanced CT between reduced-dose CT using deep learning post-processing and standard-dose CT using iterative reconstruction: A prospective study. Issue 139 (June 2021)

• Record Type: Journal Article
• Authors: Wang, Xiao; Zheng, Fuling; Xiao, Ran; Liu, Zhuoheng; Li, Yutong; Li, Juan; Zhang, Xi; Hao, Xuemin; Zhang, Xinhu; Guo, Jiawu; Zhang, Yan; Xue, Huadan; Jin, Zhengyu
• Is Part Of: European journal of radiology. Issue 139(2021)
• Publication Date: 2021-06
• Subjects: SNR signal-to-noise ratio -- CNR contrast-to-noise ratio -- kV voltage current -- mAs tube current -- IR iterative reconstruction -- FBP filtered back projection -- DL deep learning -- CNN convolutional neural network -- CTDIvol computer tomography dose index -- SD standard deviation -- Hu Hounsfield units -- DLP dose length product -- ED effective dose -- ROI region of interest -- CT computed tomography; Deep learning -- X-ray computed tomography -- Abdominal radiography -- Radiation dosage; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2021.109735
• Languages: English
• ISSNs: 0720-048X

Abstract

Highlights: Deep learning algorithm reduced the noise of low-dose CT images. Deep learning algorithm maintained the diagnostic confidence and sensitivity of lesion diagnosis in low-dose CT images. Deep learning algorithm ensured the image quality of low-dose CT images. Abstract: Purpose: To compare image quality and lesion diagnosis between reduced-dose abdominopelvic unenhanced computed tomography (CT) using deep learning (DL) post-processing and standard-dose CT using iterative reconstruction (IR). Method: Totally 251 patients underwent two consecutive abdominopelvic unenhanced CT scans of the same range, including standard and reduced doses, respectively. In group A, standard-dose data were reconstructed by (blend 30 %) IR. In group B, reduced-dose data were reconstructed by filtered back projection reconstruction to obtain group B1 images, and post-processed using the DL algorithm (NeuAI denosing, Neusoft medical, Shenyang, China) with 50 % and 100 % weights to obtain group B2 and B3 images, respectively. Then, CT values of the liver, the second lumbar vertebral centrum, the erector spinae and abdominal subcutaneous fat were measured. CT values, noise levels, signal-to-noise ratios (SNRs), contrast-to-noise ratios (CNRs), radiation doses and subjective scores of image quality were compared. Subjective evaluations of low-density liver lesions were compared by diagnostic results from enhanced CT or Magnetic Resonance Imaging. Results: Groups B3 and B1 showed the lowest and highest noise levels, respectively (P < 0.001). The SNR and CNR in group B3 were highest (P < 0.001). The radiation dose in group B was reduced by 71.5 % on average compared to group A. Subjective scores in groups A and B2 were highest (P < 0.001). Diagnostic sensitivity and confidence for liver metastases in groups A and B2 were highest (P < 0.001). Conclusions: Reduced-dose abdominopelvic unenhanced CT combined with DL post-processing could ensure image quality and satisfy diagnostic needs.