A study of using a deep learning image reconstruction to improve the image quality of extremely low-dose contrast-enhanced abdominal CT for patients with hepatic lesions

被引:51
|
作者
Cao, Le [1 ]
Liu, Xiang [1 ]
Li, Jianying [2 ]
Qu, Tingting [1 ]
Chen, Lihong [1 ]
Cheng, Yannan [1 ]
Hu, Jieliang [1 ]
Sun, Jingtao [1 ]
Guo, Jianxin [1 ]
机构
[1] Xi An Jiao Tong Univ, Dept Radiol, Affiliated Hosp 1, Xian, Shaanxi, Peoples R China
[2] GE Healthcare, Computed Tomog Res Ctr, Beijing, Peoples R China
来源
BRITISH JOURNAL OF RADIOLOGY | 2021年 / 94卷 / 1118期
关键词
STATISTICAL ITERATIVE RECONSTRUCTION;
D O I
10.1259/bjr.20201086
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Objective: To investigate the feasibility of using deep learning image reconstruction (DLIR) to significantly reduce radiation dose and improve image quality in contrast-enhanced abdominal CT. Methods: This was a prospective study. 40 patients with hepatic lesions underwent abdominal CT using routine dose (120kV, noise index (NI) setting of 11 with automatic tube current modulation) in the arterial-phase (AP) and portal-phase (PP), and low dose (NI = 24) in the delayed-phase (DP). All images were reconstructed at 1.25 mm thickness using ASIR-V at 50% strength. In addition, images in DP were reconstructed using DLIR in high setting (DLIR-H). The CT value and standard deviation (SD) of hepatic parenchyma, spleen, paraspinal muscle and lesion were measured. The overall image quality includes subjective noise, sharpness, artifacts and diagnostic confidence were assessed by two radiologists blindly using a 5-point scale (1, unacceptable and 5, excellent). Dose between AP and DP was compared, and image quality among different reconstructions were compared using SPSS20.0. Results: Compared to AP, DP significantly reduced radiation dose by 76% (0.76 +/- 0.09 mSv vs 3.18 +/- 0.48 mSv), DLIR-H DP images had lower image noise (14.08 +/- 2.89 HU vs 16.67 +/- 3.74 HU, p < 0.001) but similar overall image quality score as the ASIR-V50% AP images (3.88 0.34 vs 4.05 +/- 0.44, p > 0.05). For the DP images, DLIR-H significantly reduced image noise in hepatic parenchyma, spleen, muscle and lesion to (14.77 +/- 2.61 HU, 14.26 +/- 2.67 HU, 14.08 +/- 2.89 HU and 16.25 +/- 4.42 HU) from (24.95 +/- 4.32 HU, 25.42 +/- 4.99 HU, 23.99 +/- 5.26 HU and 27.01 +/- 7.11) with ASIR-V50%, respectively (all p < 0.001) and improved image quality score (3.88 +/- 0.34 vs 2.87 +/- 0.53; p < 0.05). Conclusion: DLIR-H significantly reduces image noise and generates images with clinically acceptable quality and diagnostic confidence with 76% dose reduction. Advances In knowledge: (1) DLIR-H yielded a significantly lower image noise, higher CNR and higher overall image quality score and diagnostic confidence than the ASIR-V50% under low signal conditions. (2) Our study demonstrated that at 76% lower radiation dose, the DLIR-H DP images had similar overall image quality to the routine-dose ASIR-V50% AP images.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] Deep learning reconstruction allows low-dose imaging while maintaining image quality: comparison of deep learning reconstruction and hybrid iterative reconstruction in contrast-enhanced abdominal CT
    Tamura, Akio
    Mukaida, Eisuke
    Ota, Yoshitaka
    Nakamura, Iku
    Arakita, Kazumasa
    Yoshioka, Kunihiro
    [J]. QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2022, 12 (05) : 2977 - 2984
  • [2] Image Quality Improvement of Low-dose Abdominal CT using Deep Learning Image Reconstruction Compared with the Second Generation Iterative Reconstruction
    Kang, Hyo-Jin
    Lee, Jeong Min
    Park, Sae Jin
    Lee, Sang Min
    Joo, Ijin
    Yoon, Jeong Hee
    [J]. CURRENT MEDICAL IMAGING, 2024, 20
  • [3] Image Quality Improvement of Low-dose Abdominal CT Using Deep Learning Image Reconstruction Compared With the Second Generation Iterative Reconstruction
    Kang, Hyo-Jin
    Min Lee, Jeong
    Park, Sae Jin
    Lee, Sang Min
    Joo, Ijin
    Yoon, Jeong Hee
    [J]. Current Medical Imaging, 2024, 20
  • [4] A feasibility study of realizing low-dose abdominal CT using deep learning image reconstruction algorithm
    Li, Lu-Lu
    Wang, Huang
    Song, Jian
    Shang, Jin
    Zhao, Xiao-Ying
    Liu, Bin
    [J]. JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY, 2021, 29 (02) : 361 - 372
  • [5] Image quality improvement in low-dose chest CT with deep learning image reconstruction
    Tian, Qian
    Li, Xinyu
    Li, Jianying
    Cheng, Yannan
    Niu, Xinyi
    Zhu, Shumeng
    Xu, Wenting
    Guo, Jianxin
    [J]. JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS, 2022, 23 (12):
  • [6] Diagnostic performance and image quality of deep learning image reconstruction (DLIR) on unenhanced low-dose abdominal CT for urolithiasis
    Delabie, Aurelien
    Bouzerar, Roger
    Pichois, Raphael
    Desdoit, Xavier
    Vial, Jeremie
    Renard, Cedric
    [J]. ACTA RADIOLOGICA, 2022, 63 (09) : 1283 - 1292
  • [7] Low-Dose CT Image Reconstruction With a Deep Learning Prior
    Park, Hyoung Suk
    Kim, Kyungsang
    Jeon, Kiwan
    [J]. IEEE ACCESS, 2020, 8 : 158647 - 158655
  • [8] Deep-learning-based image reconstruction in dynamic contrast-enhanced abdominal CT: image quality and lesion detection among reconstruction strength levels
    Kaga, T.
    Noda, Y.
    Fujimoto, K.
    Suto, T.
    Kawai, N.
    Miyoshi, T.
    Hyodo, F.
    Matsuo, M.
    [J]. CLINICAL RADIOLOGY, 2021, 76 (09) : 710.e15 - 710.e24
  • [9] Deep learning image reconstruction for improving image quality of contrast-enhanced dual-energy CT in abdomen
    Sato, Mineka
    Ichikawa, Yasutaka
    Domae, Kensuke
    Yoshikawa, Kazuya
    Kanii, Yoshinori
    Yamazaki, Akio
    Nagasawa, Naoki
    Nagata, Motonori
    Ishida, Masaki
    Sakuma, Hajime
    [J]. EUROPEAN RADIOLOGY, 2022, 32 (08) : 5499 - 5507
  • [10] Deep learning image reconstruction for improving image quality of contrast-enhanced dual-energy CT in abdomen
    Mineka Sato
    Yasutaka Ichikawa
    Kensuke Domae
    Kazuya Yoshikawa
    Yoshinori Kanii
    Akio Yamazaki
    Naoki Nagasawa
    Motonori Nagata
    Masaki Ishida
    Hajime Sakuma
    [J]. European Radiology, 2022, 32 : 5499 - 5507