The Feasibility of Using a Deep Learning-Based Model to Determine Cardiac Computed Tomographic Contrast Dose.
Journal
Journal of computer assisted tomography
ISSN: 1532-3145
Titre abrégé: J Comput Assist Tomogr
Pays: United States
ID NLM: 7703942
Informations de publication
Date de publication:
03 Aug 2023
03 Aug 2023
Historique:
medline:
2
8
2023
pubmed:
2
8
2023
entrez:
2
8
2023
Statut:
aheadofprint
Résumé
This study aimed to predict contrast effects in cardiac computed tomography (CT) from CT localizer radiographs using a deep learning (DL) model and to compare the prediction performance of the DL model with that of conventional models based on patients' physical size. This retrospective study included 473 (256 men and 217 women) cardiac CT scans between May 2014 and August 2017. We developed and evaluated DL models that predict milligrams of iodine per enhancement of the aorta from CT localizer radiographs. To assess the model performance, we calculated and compared Pearson correlation coefficient (r) between the actual iodine dose that was necessary to obtain a contrast effect of 1 HU (iodine dose per contrast effect [IDCE]) and IDCE predicted by DL, body weight, lean body weight, and body surface area of patients. The model was tested on 52 cases for the male group (mean [SD] age, 63.7 ± 11.4) and 44 cases for the female group (mean [SD] age, 69.8 ± 11.6). Correlation coefficients between the actual and predicted IDCE were 0.607 for the male group and 0.412 for the female group, which were higher than the correlation coefficients between the actual IDCE and body weight (0.539 for male, 0.290 for female), lean body weight (0.563 for male, 0.352 for female), and body surface area (0.587 for male, 0.349 for female). The performance for predicting contrast effects by analyzing CT localizer radiographs with the DL model was at least comparable with conventional methods using the patient's body size, notwithstanding that no additional measurements other than CT localizer radiographs were required.
Identifiants
pubmed: 37531644
doi: 10.1097/RCT.0000000000001532
pii: 00004728-990000000-00221
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.
Références
Cademartiri F, Maffei E, Palumbo AA, et al. Influence of intra-coronary enhancement on diagnostic accuracy with 64-slice CT coronary angiography. Eur Radiol. 2008;18:576–583.
Fei X, Du X, Yang Q, et al. 64-MDCT coronary angiography: phantom study of effects of vascular attenuation on detection of coronary stenosis. AJR Am J Roentgenol. 2008;191:43–49.
Awai K, Kanematsu M, Kim T, et al. The optimal body size index with which to determine iodine dose for hepatic dynamic CT: a prospective multicenter study. Radiology. 2016;278:773–781.
Bae KT, Heiken JP, Brink JA. Aortic and hepatic contrast medium enhancement at CT. Part II. Effect of reduced cardiac output in a porcine model. Radiology. 1998;207:657–662.
Masuda T, Nakaura T, Funama Y, et al. Aortic and hepatic contrast enhancement during hepatic-arterial and portal venous phase computed tomography scanning: multivariate linear regression analysis using age, sex, total body weight, height, and cardiac output. J Comput Assist Tomogr. 2017;41:309–314.
Matsumoto Y, Higaki T, Masuda T, et al. Minimizing individual variations in arterial enhancement on coronary CT angiographs using “contrast enhancement optimizer”: a prospective randomized single-center study. Eur Radiol. 2019;29:2998–3005.
Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60–88.
Ichikawa S, Hamada M, Sugimori H. A deep-learning method using computed tomography scout images for estimating patient body weight. Sci Rep. 2021;11:15627.
Kondo H, Kanematsu M, Goshima S, et al. Body size indexes for optimizing iodine dose for aortic and hepatic enhancement at multidetector CT: comparison of total body weight, lean body weight, and blood volume. Radiology. 2010;254:163–169.
Kondo H, Kanematsu M, Goshima S, et al. Body size indices to determine iodine mass with contrast-enhanced multi-detector computed tomography of the upper abdomen: does body surface area outperform total body weight or lean body weight? Eur Radiol. 2013;23:1855–1861.
Kidoh M, Nakaura T, Oda S, et al. Contrast enhancement during hepatic computed tomography: effect of total body weight, height, body mass index, blood volume, lean body weight, and body surface area. J Comput Assist Tomogr. 2013;37:159–164.
Kormano M, Partanen K, Soimakallio S, et al. Dynamic contrast enhancement of the upper abdomen: effect of contrast medium and body weight. Invest Radiol. 1983;18:364–367.
Heiken JP, Brink JA, McClennan BL, et al. Dynamic incremental CT: effect of volume and concentration of contrast material and patient weight on hepatic enhancement. Radiology. 1995;195:353–357.
Masuda T, Nakaura T, Higaki T, et al. Prediction of aortic contrast enhancement on dynamic hepatic computed tomography—performance comparison of machine learning methods and simulation software. J Comput Assist Tomogr. 2022;46:183–189.
Nakaura T, Awai K, Yauaga Y, et al. Contrast injection protocols for coronary computed tomography angiography using a 64-detector scanner: comparison between patient weight-adjusted- and fixed iodine-dose protocols. Invest Radiol. 2008;43:512–519.
Tan M, Le Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In: Proceedings of the 36th International Conference on Machine Learning. Long Beach, CA: PMLR; 6105–6114.
Du Bois D, Du Bois EF. Clinical calorimetry: tenth paper a formula to estimate the approximate surface area if height and weight be known. Arch Intern Med. 1916;17:863–871.
James WPT, Waterlow JC. Research on Obesity: A Report of the DHSS/MRC Group; Compiled by WPT James. London: HM Stationery Office; 1976.
Bae KT. Optimization of contrast enhancement in thoracic MDCT. Radiol Clin North Am. 2010;48:9–29.
Bae KT. Intravenous contrast medium administration and scan timing at CT: considerations and approaches. Radiology. 2010;256:32–61.
Foley WD, Hoffmann RG, Quiroz FA, et al. Hepatic helical CT: contrast material injection protocol. Radiology. 1994;192:367–371.
Heiken JP, Brink JA, McClennan BL, et al. Dynamic contrast-enhanced CT of the liver: comparison of contrast medium injection rates and uniphasic and biphasic injection protocols. Radiology. 1993;187:327–331.
Becker CR, Hong C, Knez A, et al. Optimal contrast application for cardiac 4-detector-row computed tomography. Invest Radiol. 2003;38:690–694.
Yamashita Y, Komohara Y, Takahashi M, et al. Abdominal helical CT: evaluation of optimal doses of intravenous contrast material—a prospective randomized study. Radiology. 2000;216:718–723.
Yanaga Y, Awai K, Nakaura T, et al. Effect of contrast injection protocols with dose adjusted to the estimated lean patient body weight on aortic enhancement at CT angiography. Am J Roentgenol. 2009;192:1071–1078.
Ho LM, Nelson RC, Delong DM. Determining contrast medium dose and rate on basis of lean body weight: does this strategy improve patient-to-patient uniformity of hepatic enhancement during multi-detector row CT? Radiology. 2007;243:431–437.
Nyman U. James lean body weight formula is not appropriate for determining CT contrast media dose in patients with high body mass index. Radiology. 2016;278:956–957. doi:10.1148/radiol.2016152031.
doi: 10.1148/radiol.2016152031
Caruso D, De Santis D, Rivosecchi F, et al. Lean body weight-tailored iodinated contrast injection in obese patient: Boer versus James formula. Biomed Res Int. 2018;2018:8521893.