Keywords: Multidetector Computed Tomography Liver Deep-learning Image Reconstruction Radiation Exposure

被引：14

作者：

Nagayama, Yasunori ^{[1
]}

Goto, Makoto ^{[2
]}

Sakabe, Daisuke ^{[2
]}

Emoto, Takafumi ^{[2
]}

Shigematsu, Shinsuke ^{[2
]}

Taguchi, Narumi ^{[1
]}

Maruyama, Natsuki ^{[1
]}

Takada, Sentaro ^{[1
]}

Uchimura, Ryutaro ^{[1
]}

Hayashi, Hidetaka ^{[1
]}

Kidoh, Masafumi ^{[1
]}

Oda, Seitaro ^{[1
]}

Nakaura, Takeshi ^{[1
]}

Funama, Yoshinori ^{[3
]}

Hatemura, Masahiro ^{[2
]}

Hirai, Toshinori ^{[1
]}

机构：

[1] Kumamoto Univ, Grad Sch Med Sci, Dept Diagnost Radiol, Chuo Ku, 1-1-1 Honjo, Kumamoto 8608556, Japan

[2] Kumamoto Univ Hosp, Dept Cent Radiol, Chuo Ku, 1-1-1 Honjo, Kumamoto 8608556, Japan

[3] Kumamoto Univ, Fac Life Sci, Dept Med Radiat Sci, Chuo Ku, 4-24-1 Kuhonji, Kumamoto 8620976, Japan

来源：

EUROPEAN JOURNAL OF RADIOLOGY | 2022年 / 151卷

基金：

日本学术振兴会;

关键词：

Multidetector Computed Tomography; Liver; Deep-learning; Image Reconstruction; Radiation Exposure; ITERATIVE RECONSTRUCTION; LESION DETECTION; DOSE REDUCTION; MDCT; CT;

D O I：

10.1016/j.ejrad.2022.110280

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：

Purpose: This clinical and phantom study aimed to evaluate the impact of deep learning-based reconstruction (DLR) on image quality and its radiation dose optimization capability for multiphase hepatic CT relative to hybrid iterative reconstruction (HIR). Methods: Task-based image quality was assessed with a physical evaluation phantom; the high-and low-contrast detectability of HIR and DLR images were computed from the noise power spectrum and task-based transfer function at five different size-specific dose estimate (SSDE) values in the range 5.3 to 18.0-mGy. For the clinical study, images of 73 patients who had undergone multiphase hepatic CT under both standard-dose (STD) and lower-dose (LD) examination protocols within a time interval of about four-months on average, were retro-spectively examined. STD images were reconstructed with HIR, while LD with HIR (LD-HIR) and DLR (LD-DLR). SSDE, quantitative image noise, and contrast-to-noise ratio (CNR) were compared between protocols. The noise magnitude, noise texture, streak artifact, image sharpness, interface smoothness, and overall image quality were subjectively rated by two independent radiologists. Results: In phantom study, the high-and low-contrast detectability of DLR images obtained at 5.3-mGy and 7.3-mGy, respectively, were slightly higher than those obtained with HIR at the STD protocol dose (18.0-mGy). In clinical study, LD-DLR yielded lower image noise, higher CNR, and higher subjective scores for all evaluation criteria than STD (all, p <= 0.05), despite having 52.8% lower SSDE (8.0 +/- 2.5 vs. 16.8 +/- 3.4-mGy). Conclusions: DLR improved the subjective and objective image quality of multiphase hepatic CT compared with HIR techniques, even at approximately half the radiation dose.

引用

页数：8

共 26 条

[1] Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT [J].