Impact of deep learning-based image reconstruction on image quality and lesion visibility in renal computed tomography at different doses

被引:4
|
作者
Bie, Yifan [1 ]
Yang, Shuo [1 ]
Li, Xingchao [1 ]
Zhao, Kun [1 ]
Zhang, Changlei [1 ]
Zhong, Hai [1 ,2 ]
机构
[1] Shandong Univ, Hosp 2, Dept Radiol, Jinan, Peoples R China
[2] Shandong Univ, Hosp 2, Dept Radiol, 247 Beiyuan Rd, Jinan 250033, Peoples R China
关键词
Deep learning image reconstruction; adaptive statistical iterative reconstruction-Veo (ASiR-V); image quality; tomography; kidney; ITERATIVE RECONSTRUCTION; ABDOMINAL CT; VERSION;
D O I
10.21037/qims-22-852
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
Background: Numerous computed tomography (CT) image reconstruction algorithms have been developed to improve image quality, and high-quality renal CT images are crucial to clinical diagnosis. This study evaluated the image quality and lesion visibility of deep learning-based image reconstruction (DLIR) compared with adaptive statistical iterative reconstruction-Veo (ASiR-V) in contrast-enhanced renal CT at different reconstruction strengths and doses. Methods: From January 2020 to May 2021, we prospectively included 101 patients who underwent renal contrast-enhanced CT scanning (69 at 120 kV; 32 at 80 kV). All image data were reconstructed with ASiR-V (30% and 70%) and DLIR at low, medium, and high reconstruction strengths (DLIR-L, DLIR-M, and DLIR-H, respectively). The CT number, noise, noise reduction rate (NRR), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), overall image quality, and the proportion of acceptable images were compared. Lesions of DLIR groups were evaluated, and the conspicuity-to-noise ratio (C/N) was calculated.Results: Quantitative values (noise, SNR, CNR, and NRR) significantly differed between all reconstructions at 120 and 80 kV (P<0.00 1) and between each reconstruction, except ASiR-V 70% vs. DLIR-M. At 120 kV, the overall image quality and the proportion of acceptable images significantly differed between all reconstructions (P<0.001) and between each reconstruction, except ASiR-V 30% vs. DLIR-L and ASiR-V 70% vs. DLIR-M. At 80 kV, the overall image quality significantly differed between all reconstructions (P<0.001) and between each reconstruction, except between ASiR-V 30%, ASiR-V 70%, and DLIR-L. Quantitative and qualitative values were highest in DLIR-H, while the values were close in DLIR-H (80 kV) vs. ASiR-V 70% (120 kV) and DLIR-M (80 kV) vs. ASiR-V 30% (120 kV). The lesion conspicuity and noise significantly differed in DLIR at 120 kV and 80 kV (P<0.001). C/N significantly differed in DLIR at 120 kV (P<0.001) but not at 80 kV. DLIR-L and DLIR-M exhibited much-improved lesion display (C/N >1), and DLIR-H exhibited much-improved noise (C/N <1) at 120 kV. Conclusions: DLIR significantly improved the image quality and lesion visibility of renal CT compared with ASiR-V, even at a low dose.
引用
收藏
页码:2197 / 2207
页数:11
相关论文
共 50 条
  • [31] Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    Chung, Yeon Woong
    Kang, Dong Gyun
    Lee, Yong Oh
    Cho, Won-Kyung
    JOVE-JOURNAL OF VISUALIZED EXPERIMENTS, 2022, (189):
  • [32] A deep learning-based automatic image quality assessment method for respiratory phase on computed tomography chest images
    Su, Jialin
    Li, Meifang
    Lin, Yongping
    Xiong, Liu
    Yuan, Caixing
    Zhou, Zhimin
    Yan, Kunlong
    QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2024, 14 (03) : 2240 - 2254
  • [33] Deep learning-based image quality improvement for low-dose computed tomography simulation in radiation therapy
    Wang, Tonghe
    Lei, Yang
    Tian, Zhen
    Dong, Xue
    Liu, Yingzi
    Jiang, Xiaojun
    Curran, Walter J.
    Liu, Tian
    Shu, Hui-Kuo
    Yang, Xiaofeng
    JOURNAL OF MEDICAL IMAGING, 2019, 6 (04)
  • [34] Deep Learning-Based Dictionary Learning and Tomographic Image Reconstruction
    Rudzusika, Jevgenija
    Koehler, Thomas
    Oktem, Ozan
    SIAM JOURNAL ON IMAGING SCIENCES, 2022, 15 (04): : 1729 - 1764
  • [35] Deep learning image reconstruction for quality assessment of iodine concentration in computed tomography: A phantom study
    Jeon, Pil-Hyun
    Lee, Chang-Lae
    JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY, 2023, 31 (02) : 409 - 422
  • [36] Super-resolution deep learning image reconstruction: image quality and myocardial homogeneity in coronary computed tomography angiography
    Chuluunbaatar Otgonbaatar
    Hyunjung Kim
    Pil-Hyun Jeon
    Sang-Hyun Jeon
    Sung-Jin Cha
    Jae-Kyun Ryu
    Won Beom Jung
    Hackjoon Shim
    Sung Min Ko
    Journal of Cardiovascular Imaging, 32 (1)
  • [37] A Physics-Constrained Deep Learning-Based Image Reconstruction for Electrical Capacitance Tomography
    Jin, Yiqi
    Li, Yi
    Zhang, Maomao
    Peng, Lihui
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73 : 1 - 12
  • [38] Advanced deep learning-based image reconstruction in lumbar spine MRI at 0.55 T - Effects on image quality and acquisition time in comparison to conventional deep learning-based reconstruction
    Schlicht, Felix
    Vosshenrich, Jan
    Donners, Ricardo
    Seifert, Alina Carolin
    Fenchel, Matthias
    Nickel, Dominik
    Obmann, Markus
    Harder, Dorothee
    Breit, Hanns-Christian
    EUROPEAN JOURNAL OF RADIOLOGY OPEN, 2024, 12
  • [39] Deep learning-based reconstruction enhanced image quality and lesion detection of white matter hyperintensity through in FLAIR MRI
    Sun, Jie ping
    Bu, Chun xiao
    Dang, Jing han
    Lv, Qing qing
    Tao, Qiu ying
    Kang, Yi meng
    Niu, Xiao yu
    Wen, Bao hong
    Wang, Wei jian
    Wang, Kai yu
    Cheng, Jing liang
    Zhang, Yong
    ASIAN JOURNAL OF SURGERY, 2025, 48 (01) : 342 - 349
  • [40] Dual-dictionary learning-based iterative image reconstruction for spectral computed tomography application
    Zhao, Bo
    Ding, Huanjun
    Lu, Yang
    Wang, Ge
    Zhao, Jun
    Molloi, Sabee
    PHYSICS IN MEDICINE AND BIOLOGY, 2012, 57 (24): : 8217 - 8229