ISSN 1004-4140
CN 11-3017/P
| Citation: |
LIU D D, LI W, ZHANG Y X, et al. Preliminary exploration of non-gated high-pitch chest CT combined with artificial intelligence in assessing coronary artery calcium score[J]. CT Theory and Applications, xxxx, x(x): 1-6. DOI: 10.15953/j.ctta.2024.085. (in Chinese).
|
Objective: To investigate the feasibility of using non-gated high-pitch chest computed tomography (CT) combined with artificial intelligence (AI) technology to measure the coronary artery calcium score. Methods: In this retrospective analysis, we reviewed the images of 24 patients who underwent both non-gated high-pitch chest CT and coronary artery calcium scoring CT. The scanning parameters were as follows: ① non-gated high-pitch chest CT scan: CarekV and CareDose 4D, ref.kV 110, ref.mAs 80, pitch 3, filter core BR40; ② ECG-gated coronary artery calcification score CT: CarekV, CareDose 4D, ref.kV 120, ref.mAs 50, pitch 0.15, acquisition R-R interval 35% and 75%, filter core QR36. The image window width/window level of the two groups was 345/50, and the slice thickness/interval was 3 mm/1.5 mm. The images of the two scan groups were divided into three subgroups according to the three measurement methods (Syngo.via workstation measurement, AI measurement, and AI + manual correction measurement). The image calcification score (Agatston Score, AS) was measured, risk classification was performed, and the time taken for the workstation measurement and the AI + manual correction measurement was recorded. The volume dose index (CTDIvol) and dose-length product (DLP) of the two examinations were recorded, and the effective dose (ED) was calculated. SPSS Statistics software (version 27.0) was used for the statistical analysis. Results: The tube voltages of the high-pitch chest CT were 100, 110, and 120 kV, and the coronary artery calcium score was 120 kV. EDs of high-pitch chest CT and coronary artery calcium score CT were 2.1±0.4 and 2.1±0.7 mSv, respectively. The three measurement methods used for high-pitch chest CT showed significant differences in AS (X2=27.163, P < 0.001), but the consistency of AS was high (ICC: 0.988). Regarding AS measurement, high-pitch chest CT combined with AI (X2 = 4.795, P = 0.091, ICC: 0.990), high-pitch chest CT using a workstation (Z = 0.912, P = 0.362, ICC: 0.988), and gated calcium scoring combined with AI (X2 = 10.900, P = 0.004, ICC: 0.980) showed no significant differences or high consistency compared to the workstation for coronary artery calcium scoring. The risk classification obtained by the AI was highly consistent, and the weighted kappa coefficients were between 0.818 and 1.000. The time taken for measurements using the workstation and AI + manual correction in both scanning groups showed significant differences (Z = 4.200, 4.049, P < 0.001). Conclusion: Non-gated high-pitch chest CT combined with AI can provide reliable results for artery calcium scores and risk classification with reduced time consumption, demonstrating substantial clinical utility.
| [1] |
周俊林, 萧毅, 张雪君, 等. 中国医学影像人工智能应用现状调研报告[J]. 中华放射学杂志, 2022, 56(11): 1248−1253. DOI: 10.3760/cma.j.cn112149-20220802-00650.
ZHOU J L, XIAO Y, ZHANG X J, et al. A survey report on the application status of artificial intelligence in medical imaging in China. Chinese Journal of Radiology, 2022, 56(11): 1248−1253. DOI: 10.3760/cma.j.cn112149-20220802-00650. (in Chinese).
|
| [2] |
YU J, QIAN L, SUN W, et al. Automated total and vessel-specific coronary artery calcium (CAC) quantification on chest CT: direct comparison with CAC scoring on non-contrast cardiac CT. BMC Med Imaging. 2022 Oct 14;22(1): 177. DOI: 10.1186/s12880-022-00907-1.
|
| [3] |
CHANG S, REN L, TANG S, et al. Technical note: Exploring the detectability of coronary calcification using ultra-high-resolution photon-counting-detector CT. Med Phys. 2023 Nov;50(11): 6836−6843. DOI: 10.1002/mp.16712.
|
| [4] |
LLEWELLYN O, WILLIAMS M C. What should we do about Coronary Calcification on Thoracic CT? Rofo. 2022 Aug;194(8): 833−840. English. DOI: 10.1055/a-1752-0577.
|
| [5] |
JACOBS P C, ISGUM I, GONDRIE M J, et al. Coronary artery calcification scoring in low-dose ungated CT screening for lung cancer: interscan agreement. AJR Am J Roentgenol. 2010 May;194(5): 1244−9. DOI: 10.2214/AJR.09.3047.
|
| [6] |
PARK S H, HAN K. Methodologic Guide for Evaluating Clinical Performance and Effect of Artificial Intelligence Technology for Medical Diagnosis and Prediction. Radiology. 2018 Mar;286(3): 800−809. DOI: 10.1148/radiol.2017171920.
|
| [7] |
The 2007 Recommendations of the International Commission on Radiological Protection. ICRP publication 103. Ann ICRP. 2007;37(2−4): 1−332. DOI: 10.1016/j.icrp.2007.10.003.
|
| [8] |
孙会利, 陈杰, 张焕, 等. 基于人工智能技术的非门控胸部CT平扫对冠状动脉钙化积分的准确性评价[J]. CT理论与应用研究, 2021, 30(1): 106−113. DOI: 10.15953/j.1004-4140.2021.30.01.11.
SUN H L, CHEN J, ZHANG H, et al. Accuracy evaluation of coronary artery calcification score by non gated chest CT scan based on artificial intelligence technology[J]. CT Theory and Applications, 2021, 30(1): 106−113. DOI: 10.15953/j.1004-4140.2021.30.01.11.
|
| [9] |
LESSMANN N, VAN GINNEKEN B, ZREIK M, et al. Automatic Calcium Scoring in Low-Dose Chest CT Using Deep Neural Networks With Dilated Convolutions. IEEE Trans Med Imaging. 2018 Feb;37(2): 615−625. DOI: 10.1109/TMI.2017.2769839.
|
| [10] |
LIU Y, CHEN X, LIU X, et al. Accuracy of non-gated low-dose non-contrast chest CT with tin filtration for coronary artery calcium scoring. Eur J Radiol Open. 2022 Jan 17;9: 100396. DOI: 10.1016/j.ejro.2022.100396.
|
| [11] |
BUDOFF M J, NASIR K, KINNEY G L, et al. Coronary artery and thoracic calcium on noncontrast thoracic CT scans: comparison of ungated and gated examinations in patients from the COPD Gene cohort. J Cardiovasc Comput Tomogr. 2011 Mar-Apr;5(2): 113−8. DOI: 10.1016/j.jcct.2010.11.002.
|
| [12] |
顾耕, 陶欣慰, 邓建宏. 无门控大螺距胸部CT扫描心脏冠状动脉钙化积分的可行性研究[J]. 实用放射学杂志, 2022, 38(6): 910−914, 918. DOI: 10.3969/j.issn.1002-1671.2022.06.010.
GU G, TAO X W, DENG J H. Coronary artery calcification score detection using thorax CT with TurboFlash mode: a feasibility study. Journal of Practical Radiology, 2022, 38(6): 910−914, 918. DOI: 10.3969/j.issn.1002-1671.2022.06.010. (in Chinese).
|
| [13] |
樊荣荣, 刘凯, 夏晨, 等. AI对非门控胸部LDCT平扫冠状动脉钙化积分危险分层的预测价值[J]. 国际医学放射学杂志, 2022, 45(1): 21−26. DOI: 10.19300/j.2022.L18690.
FAN R R, LIU K, XIA C, et al. Predictive value of AI in risk stratification of coronary artery calcification score using non-gated chest LDCT. International Journal of Medical Radiology, 2022, 45(1): 21−26. DOI: 10.19300/j.2022.L18690. (in Chinese).
|
| [14] |
闫玉辰, 胡磊, 王焰, 等. 基于深度学习技术的非门控胸部CT冠脉钙化积分系统的准确性评价[J]. 放射学实践, 2023, 38(3): 273−278. DOI: 10.13609/j.cnki.1000-0313.2023.03.006.
YAN Y C, HU L, WANG Y, et al. Accuracy evaluation of non-gated chest CT coronary calcification scoring system based on deep learning technology. Radiology Practice, 2023, 38(3): 273−278. DOI: 10.13609/j.cnki.1000-0313.2023.03.006. (in Chinese).
|
| [15] |
ANDRE F, SEITZ S, FORTNER P, et al. Simultaneous assessment of heart and lungs with gated high-pitch ultra-low dose chest CT using artificial intelligence-based calcium scoring. Eur J Radiol Open. 2023 Feb 15;10: 100481. DOI: 10.1016/j.ejro.2023.100481.
|
| [16] |
陈丽虹, 郭银霞, 李雅楠, 等. 人工智能冠状动脉钙化积分自动测量方法的临床有效性评估[J]. 实用放射学杂志, 2023, 39(1): 45−48, 69. DOI: 10.3969/j.issn.1002-1671.2023.01.012.
CHEN L H, GUO Y X, LI Y N, et al. Clinical effectiveness evaluation of artificial intelligence automatic measurement method for coronary artery calcium score. Journal of Practical Radiology, 2023, 39(1): 45−48, 69. DOI: 10.3969/j.issn.1002-1671.2023.01.012. (in Chinese).
|
| [17] |
COVAS P, DE GUZMAN E, BARROWS I, et al. Artificial Intelligence Advancements in the Cardiovascular Imaging of Coronary Atherosclerosis. Front Cardiovasc Med. 2022 Mar 21;9: 839400. DOI: 10.3389/fcvm.2022.839400.
|
Supported by: Beijing Renhe Information Technology Co. Ltd 
DownLoad: