Investigating the Feasibility of Using DenseNet to Improve Coronary Calcification Detection in CT

Published:November 15, 2022DOI:


      Interscan reproducibility of coronary artery calcium (CAC) scoring can be improved by using a smaller slice thickness but at the cost of higher image noise. This study aimed to investigate the feasibility of using densely connected convolutional network (DenseNet) to reduce the image noise in CAC scans reconstructed with slice thickness < 3 mm for improving coronary calcification detection in CT.


      Phantom data acquired with QRM and CIRS phantoms were used for model training and testing, where the DenseNet model adopted in this work was a convolutional neural network (CNN) designed for super resolution recovery. After phantom study, the proposed method was evaluated in terms of its ability to improve calcification detection using patient data. The CNN input images ( IM G input ) were CAC scans reconstructed with 0.5-, 1.0- and 1.5-mm slice thickness, while CNN label images were CAC scans reconstructed with 3-mm slice thickness ( IM G 3 mm ). Region of interest (ROI) analysis was carried out on IM G 3 mm , IM G input and CNN output images ( IM G output ). Two-sample t test was used to compare the difference in Hounsfield Unit (HU) values within ROI between IM G 3 mm and IM G output .


      For the calcifications in QRM phantoms, no statistically significant difference was found when comparing the HU values of 400- and 800-HA calcifications identified on IM G 3 mm to those on IM G output with slice thickness of 0.5, 1.0 or 1.5 mm. On the other hand, statistically significant difference was found when comparing the HU values of 200-HA calcifications identified on IM G 3 mm to those on IM G output with a slice thickness of 0.5 and 1.0 mm. Meanwhile, no statistically significant difference was found when comparing the HU values of 200-HA calcifications identified on IM G 3 mm to those on IM G output with a slice thickness of 1.5 mm. As for the rod inserts in CIRS phantoms simulating 9 different tissue types in human body, there was no statistically significant difference between IM G 3 mm and IM G output with slice thickness of 1.5 mm, and all the p values were larger than 0.10. With regards to patient study, more calcification pixels were detected on IM G output with a slice thickness of 1.5 mm than on IM G 3 mm , so calcifications were more clear on the denoised images.


      According to our results, the CNN-based denoising method could reduce statistical noise in IM G input with a slice thickness of 1.5 mm without causing significant texture change or variation in HU values. The proposed method could improve cardiovascular risk prediction by detecting small and soft calcifications that are barely identified on 3-mm slice images used in conventional CAC scans.

      Key words

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Academic Radiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Budoff MJ
        • Achenbach S
        • Blumenthal RS
        • et al.
        Assessment of coronary artery disease by cardiac computed tomography: a scientific statement from the American Heart Association Committee on Cardiovascular Imaging and Intervention, Council on Cardiovascular Radiology and Intervention, and Committee on Cardiac Imaging, Council on Clinical Cardiology.
        Circulation. 2006; 114: 1761-1791
        • Greenland P
        • Blaha MJ
        • Budoff MJ
        • et al.
        Coronary calcium score and cardiovascular risk.
        J Am Coll Cardiol. 2018; 72: 434-447
        • Blaha MJ
        • Mortensen MB
        • Kianoush S
        • et al.
        Coronary artery calcium scoring: is it time for a change in methodology?.
        JACC Cardiovasc Imaging. 2017; 10: 923-937
        • Malguria N
        • Zimmerman S
        • Fishman EK.
        Coronary artery calcium scoring: current status and review of literature.
        J Comput Assist Tomogr. 2018; 42: 887-897
        • Lehker A
        • Mukherjee D.
        Coronary calcium risk score and cardiovascular risk.
        Current Vasc Pharmacol. 2021; 19: 280-284
        • Jacobs PC
        • Isgum I
        • Gondrie MJ
        • et al.
        Coronary artery calcification scoring in low-dose ungated CT screening for lung cancer: interscan agreement.
        AJR Am J Roentgenol. 2010; 194: 1244-1249
        • Van Hoe LR
        • De Meerleer KG
        • Leyman PP
        • et al.
        Coronary artery calcium scoring using ECG-gated multidetector CT: effect of individually optimized image-reconstruction windows on image quality and measurement reproducibility.
        AJR Am J Roentgenol. 2003; 181: 1093-1100
        • Šprem J
        • de Vos BD
        • Lessmann N
        • et al.
        Coronary calcium scoring with partial volume correction in anthropomorphic thorax phantom and screening chest CT images.
        PloS one. 2018; 13e0209318
        • Fukumoto W
        • Nagaoka M
        • Higaki T
        • et al.
        Measurement of coronary artery calcium volume using ultra-high-resolution computed tomography: a preliminary phantom and cadaver study.
        Eur J Radiol Open. 2020; 7100253
        • Aslam A
        • Khokhar US
        • Chaudhry A
        • et al.
        Assessment of isotropic calcium using 0.5-mm reconstructions from 320-row CT data sets identifies more patients with non-zero Agatston score and more subclinical atherosclerosis than standard 3.0-mm coronary artery calcium scan and CT angiography.
        J Cardiovasc Comput Tomogr. 2014; 8: 58-66
        • Urabe Y
        • Yamamoto H
        • Kitagawa T
        • et al.
        Identifying small coronary calcification in non-contrast 0.5-mm slice reconstruction to diagnose coronary artery disease in patients with a conventional zero coronary artery calcium score.
        J Atheroscler Thromb. 2016; 23: 1324-1333
        • Luhur R
        • Schuijf JD
        • Mews J
        • et al.
        Accuracy of coronary artery calcium scoring with tube current reduction by 75%, using an adaptive iterative reconstruction algorithm.
        Br J Radiol. 2018; 9120170678
        • Lee CH
        • Goo JM
        • Ye HJ
        • et al.
        Radiation dose modulation techniques in the multidetector CT era: from basics to practice.
        Radiographics. 28. 2008: 1451-1459
        • Imai K
        • Ikeda M
        • Enchi Y
        • et al.
        Quantitative assessment of image noise and streak artifact on CT image: comparison of z-axis automatic tube current modulation technique with fixed tube current technique.
        Comput Med Imaging Graph. 2009; 33: 353-358
        • Silva AC
        • Lawder HJ
        • Hara A
        • et al.
        Innovations in CT dose reduction strategy: application of the adaptive statistical iterative reconstruction algorithm.
        AJR Am J Roentgenol. 2010; 194: 191-199
        • den Harder AM
        • Willemink MJ
        • de Ruiter QM
        • et al.
        Achievable dose reduction using iterative reconstruction for chest computed tomography: a systematic review.
        Eur J Radiol. 2015; 84: 2307-2313
        • Immonen E
        • Wong J
        • Nieminen M
        • et al.
        The use of deep learning towards dose optimization in low-dose computed tomography: a scoping review.
        Radiography. 2022; 28: 208-214
        • Lee JE
        • Choi S-Y
        • Hwang JA
        • et al.
        The potential for reduced radiation dose from deep learning-based CT image reconstruction: A comparison with filtered back projection and hybrid iterative reconstruction using a phantom.
        Medicine. 2021; 100: 1-9
        • Kulathilake K
        • Abdullah NA
        • Sabri AQM
        • et al.
        A review on deep learning approaches for low-dose computed tomography restoration.
        Complex Intell Systems. 2021; : 1-33
        • Shrestha A
        • Mahmood A.
        Review of deep learning algorithms and architectures.
        IEEE Access. 2019; 7: 53040-53065
        • Huang L
        • Jiang H
        • Li S
        • et al.
        Two stage residual CNN for texture denoising and structure enhancement on low dose CT image.
        Comput Methods Programs Biomed. 2020; 184105115
        • Jiang X
        • Jin Y
        • Yao Y.
        Low-dose CT lung images denoising based on multiscale parallel convolution neural network.
        Visual Computer. 2021; 37: 1-13
        • Shiri I
        • Akhavanallaf A
        • Sanaat A
        • et al.
        Ultra-low-dose chest CT imaging of COVID-19 patients using a deep residual neural network.
        Eur Radiol. 2021; 31: 1420-1431
        • Tong T
        • Li G
        • Liu X
        • et al.
        Image super-resolution using dense skip connections.
        in: Paper presented at: Venice, Italy: 2017 IEEE International Conference on Computer Vision (ICCV); 22-29 Oct. 2017. 2017
        • He K
        • Zhang X
        • Ren S
        • et al.
        Delving deep into rectifiers: surpassing human-level performance on Imagenet classification.
        in: Santiago, Chile: IEEE International Conference on Computer Vision (ICCV 2015). 2015: 1502
        • Kingma D
        • Adam Ba J.
        A method for stochastic optimization.
        in: Banff, Canada: International Conference on Learning Representations. 2014
        • Jia Y
        • Shelhamer E
        • Donahue J
        • et al.
        Caffe: convolutional architecture for fast feature embedding.
        in: Orlando, USA: MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia. 2014