Motion-corrected coronary calcium scores by a convolutional neural network: a robotic simulating study
- 109 Downloads
To classify motion-induced blurred images of calcified coronary plaques so as to correct coronary calcium scores on nontriggered chest CT, using a deep convolutional neural network (CNN) trained by images of motion artifacts.
Three artificial coronary arteries containing nine calcified plaques of different densities (high, medium, and low) and sizes (large, medium, and small) were attached to a moving robotic arm. The artificial arteries moving at 0–90 mm/s were scanned to generate nine categories (each from one calcified plaque) of images with motion artifacts. An inception v3 CNN was fine-tuned and validated. Agatston scores of the predicted classification by CNN were considered as corrected scores. Variation of Agatston scores on moving plaque and by CNN correction was calculated using the scores at rest as reference.
The overall accuracy of CNN classification was 79.2 ± 6.1% for nine categories. The accuracy was 88.3 ± 4.9%, 75.9 ± 6.4%, and 73.5 ± 5.0% for the high-, medium-, and low-density plaques, respectively. Compared with the Agatston score at rest, the overall median score variation was 37.8% (1st and 3rd quartile, 10.5% and 68.8%) in moving plaques. CNN correction largely decreased the variation to 3.7% (1.9%, 9.1%) (p < 0.001, Mann–Whitney U test) and improved the sensitivity (percentage of non-zero scores among all the scores) from 65 to 85% for detection of coronary calcifications.
In this experimental study, CNN showed the ability to classify motion-induced blurred images and correct calcium scores derived from nontriggered chest CT. CNN correction largely reduces the overall Agatston score variation and increases the sensitivity to detect calcifications.
• A deep CNN architecture trained by CT images of motion artifacts showed the ability to correct coronary calcium scores from blurred images.
• A correction algorithm based on deep CNN can be used for a tenfold reduction in Agatston score variations from 38 to 3.7% of moving coronary calcified plaques and to improve the sensitivity from 65 to 85% for the detection of calcifications.
• This experimental study provides a method to improve its accuracy for coronary calcium scores that is a fundamental step towards a real clinical scenario.
KeywordsTomography, X-ray computed Phantoms, imaging Artifacts Artificial intelligence
Convolutional neural network
Joint Photographic Experts Group
Left anterior descending artery
Left circumflex artery
The Dutch-Belgian randomized lung cancer screening trial
Right coronary artery
This study was sponsored by the National Natural Science Foundation of China (project no. 81471662), Ministry of Science and Technology of China (2016YFE0103000), Science and Technology Commission of Shanghai Municipality (16411968500 and 16410722300), Shanghai Municipal Education Commission – Gaofeng Clinical Medicine Grant Support (20181814), Shanghai Jiao Tong University (ZH2018ZDB10), and Clinical Research Innovation Plan of Shanghai General Hospital (CTCCR-2018B04). The funders played no role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Compliance with ethical standards
The scientific guarantor of this publication is Xueqian Xie, MD PhD, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
Xueqian Xie, MD PhD, performed deep learning.
Written informed consent was not required for this study because this is not a research on human subjects.
Institutional Review Board approval was not required because this is not a research on human subjects.
• Performed at one institution
- 15.He Y, Guo J, Ding X et al (2019) Convolutional neural network to predict the local recurrence of giant cell tumor of bone after curettage based on pre-surgery magnetic resonance images. Eur Radiol. https://doi.org/10.1007/s00330-019-06082-2
- 18.Sprem J, de Vos BD, Lessmann N, de Jong PA, Viergever MA, Isgum I (2018) Impact of automatically detected motion artifacts on coronary calcium scoring in chest computed tomography. J Med Imaging (Bellingham) 5:044007Google Scholar
- 23.de Vos BD, Wolterink JM, Leiner T, de Jong PA, Lessmann N, Isgum I (2019) Direct automatic coronary calcium scoring in cardiac and chest CT. IEEE Trans Med Imaging. https://doi.org/10.1109/TMI.2019.2899534
- 24.Xie Y, Liu S, Miller A et al (2017) Coronary artery calcification identification and labeling in low-dose chest CT images. Proc SPIE 10134, Medical Imaging: Computer-Aided Diagnosis, 101340LGoogle Scholar
- 29.Elss T, Nickisch H, Wissel T, Bippus R, Morlock MM, Grass M (2018) Motion estimation in coronary CT angiography images using convolutional neural networks. 1st Conference on Medical Imaging with Deep Learning (MIDL 2018). Available via https://openreview.net/pdf?id=HkBtaBjoz. Accessed on 4 June 2019
- 30.Greuter MJ, Groen JM, Nicolai LJ, Dijkstra H, Oudkerk M (2009) A model for quantitative correction of coronary calcium scores on multidetector, dual source, and electron beam computed tomography for influences of linear motion, calcification density, and temporal resolution: a cardiac phantom study. Med Phys 36:5079–5088CrossRefGoogle Scholar