Application of a Deep Learning-Based Contrast-Boosting Algorithm to Low-Dose Computed Tomography Pulmonary Angiography With Reduced Iodine Load

被引:0
作者
Park, Minsu [1 ,2 ]
Hwang, Minhee [3 ,4 ]
Lee, Ji Won [3 ,4 ]
Kim, Kun-Il [1 ,2 ]
Ahn, Chulkyun [5 ,6 ]
Suh, Young Ju [7 ]
Jeong, Yeon Joo [1 ,2 ]
机构
[1] Pusan Natl Univ, Sch Med, Dept Radiol, Yangsan Hosp, Yangsan, South Korea
[2] Pusan Natl Univ, Sch Med, Res Inst Convergence Biomed Sci & Technol, Yangsan Hosp, Yangsan, South Korea
[3] Pusan Natl Univ, Pusan Natl Univ Hosp, Dept Radiol, Sch Med, Busan, South Korea
[4] Biomed Res Inst, Busan, South Korea
[5] Seoul Natl Univ, Grad Sch Convergence Sci & Technol, Dept Transdisciplinary Studies, Program Biomed Radiat Sci, Seoul, South Korea
[6] ClariPi Res, Seoul, South Korea
[7] Inha Univ, Sch Med, Dept Biomed Sci, Incheon, South Korea
关键词
pulmonary embolism; CT angiography; deep learning; image enhancement; CT CORONARY-ANGIOGRAPHY; IMAGE QUALITY; ITERATIVE RECONSTRUCTION; 80; KVP; TUBE CURRENT; CHEST CT; REDUCTION; EMBOLISM; MODULATION; PROTOCOL;
D O I
10.1097/RCT.0000000000001665
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:The aim of this study was to assess the effectiveness of a deep learning-based image contrast-boosting algorithm by enhancing the image quality of low-dose computed tomography pulmonary angiography at reduced iodine load. Methods:This study included 179 patients who underwent low-dose computed tomography pulmonary angiography with a reduced iodine load using 64 mL of a 1:1 mixture of contrast medium from January 1 to June 30, 2023. For single-energy computed tomography, the noise index was set at 15.4 to maintain a CTDIvol of <2 mGy at 80 kVp, and for dual-energy computed tomography, fast kV-switching between 80 and 140 kVp was employed with a fixed tube current of 145 mA. Images were reconstructed by 50% adaptive statistical iterative reconstruction (AR50) and a commercially available deep learning image reconstruction (TrueFidelity) package at a high strength level (TFH). In addition, AR50 images were further processed using a deep learning-based contrast-boosting algorithm (AR50-CB). Quantitative and qualitative image qualities and numbers of involved vessels with thrombus at each pulmonary artery level were compared in the 3 image types using the Friedman test and Wilcoxon signed rank test. Results:Five hundred thirty-seven reconstructed image datasets of 179 patients were analyzed. Quantitative image analysis showed AR50-CB (30.8 +/- 10.0 and 28.1 +/- 9.6, respectively) had significantly higher signal-to-noise ratio and contrast-to-noise ratio values than AR50 (20.2 +/- 6.2 and 17.8 +/- 6.2, respectively) (P < 0.001) or TFH (28.3 +/- 8.3 and 24.9 +/- 8.1, respectively) (P < 0.001). Qualitative image analysis showed that contrast enhancement and noise scores of AR50-CB were significantly greater than those of AR50 (P < 0.001) and that AR50-CB enhancement scores were significantly higher than TFH enhancement scores (P < 0.001). The number of subsegmental pulmonary arteries affected by thrombus detected was significantly greater for AR50-CB (30 for AR50, 30 for TFH, and 55 for AR50-CB, P < 0.001). Conclusions:The use of a deep learning-based contrast-boosting algorithm improved image quality in terms of signal-to-noise ratio and contrast-to-noise ratio values and the detection of thrombi in subsegmental pulmonary arteries.
引用
收藏
页码:288 / 296
页数:9
相关论文
共 30 条
[1]   A Systematic Review of Double Low-dose CT Pulmonary Angiography in Pulmonary Embolism [J].
Aldosari, Sultan ;
Sun, Zhonghua .
CURRENT MEDICAL IMAGING, 2019, 15 (05) :453-460
[2]   Intravenous contrast material administration at helical 16-detector row CT coronary angiography: Effect of iodine concentration on vascular attenuation [J].
Cademartiri, F ;
Mollet, NR ;
van der Lugt, A ;
McFadden, EP ;
Stijnen, T ;
de Feyter, PJ ;
Krestin, GP .
RADIOLOGY, 2005, 236 (02) :661-665
[3]   Symptomatic subsegmental pulmonary embolism: to treat or not to treat? [J].
Carrier, Marc ;
Klok, Fredrikus A. .
HEMATOLOGY-AMERICAN SOCIETY OF HEMATOLOGY EDUCATION PROGRAM, 2017, :237-241
[4]   Spectral Optimization of Chest CT Angiography with Reduced Iodine Load: Experience in 80 Patients Evaluated with Dual-Source, Dual-Energy CT [J].
Delesalle, Marie-Aurelie ;
Pontana, Francois ;
Duhamel, Alain ;
Faivre, Jean-Baptiste ;
Flohr, Thomas ;
Tacelli, Nunzia ;
Remy, Jacques ;
Remy-Jardin, Martine .
RADIOLOGY, 2013, 267 (01) :256-266
[5]   EPIDEMIOLOGY [J].
GIUNTINI, C ;
DIRICCO, G ;
MARINI, C ;
MELILLO, E ;
PALLA, A .
CHEST, 1995, 107 (01) :S3-S9
[6]   Dose reduction in computed tomography by attenuation-based on-line modulation of tube current: evaluation of six anatomical regions [J].
Greess, H ;
Wolf, H ;
Baum, U ;
Lell, M ;
Pirkl, M ;
Kalender, W ;
Bautz, WA .
EUROPEAN RADIOLOGY, 2000, 10 (02) :391-394
[7]   Impact of Tube Current-Time and Tube Voltage Reduction in 64-Detector-row Computed Tomography Pulmonary Angiography for Pulmonary Embolism in a Porcine Model [J].
Henes, Frank Oliver Gerhard ;
Groth, Michael ;
Begemann, Philipp G. C. ;
Bley, Thorsten ;
Adam, Gerhard ;
Regier, Marc .
JOURNAL OF THORACIC IMAGING, 2012, 27 (02) :113-120
[8]   Chest CT performed with z-axis modulation: Scanning protocol and radiation dose [J].
Kalra, MK ;
Rizzo, S ;
Maher, MM ;
Halpern, EF ;
Toth, TL ;
Shepard, JAO ;
Aquino, SL .
RADIOLOGY, 2005, 237 (01) :303-308
[9]   Image quality and attenuation values of multidetector CT coronary angiography using high iodine-concentration contrast material: A comparison of the use of iopromide 370 and iomeprol 400 [J].
Kim, Eun Young ;
Yeh, Dae Wook ;
Choe, Yeon Hyeon ;
Lee, Won Jae ;
Lim, Hyo Keun .
ACTA RADIOLOGICA, 2010, 51 (09) :982-989
[10]  
Kim JH, 2021, KOREAN J RADIOL, V22, P131