Aims and objectives
Non-invasive coronary CT angiography (CCTA) is preferentially used for the detection and diagnosis of coronary artery disease [1].
But,
high quality CT imaging of the coronary arteries is a challenging task as hardware constraints restrict the temporal resolution of reconstructed CT image volumes.
Coronary motion artifacts may interfere reliable evaluation and potentially cause misinterpretations [2].
We introduce a deep-learning-based method for the recognition and quantification of coronary motion artifacts,
in order to assess the image quality and reliability of CCTA images [3].
Furthermore,
steering and...
Methods and materials
Two convolutional neural networks are trained to recognize typical coronary motion artifact pattern like arc-shaped blurring and intensity undershoots in coronary cross-sectional image patches.
The data required for the supervised learning is generated by introducing simulated cardiac motion to 17 prospectively ECG-triggered CT cases with excellent image quality.
The data sets are acquired with a 256-slice CT scanner and verified as artifact-free by visual inspection.
Data generation: A Coronary Motion Forward Artifact model for CT data (CoMoFACT) is developed for retrospective simulation of cardiac motion...
Results
Evaluation on synthetic motion artifacts: During classification,
a threshold of 0.5 is selected for the separation of motion-free and motion-perturbed coronary cross-sections.
The achieved mean classification accuracy of 93.26 % +- 1.82 is split into the ratio 46.90 % : 46.36 % : 3.64 % : 3.10 % for the rates TN : TP : FN : FP,
where positive refers to the class artifact.
The regression networks reach a mean absolute error of 0.112 +- 0.007; the corresponding confusion matrix exhibits a clear diagonal...
Conclusion
CNNs are suitable for absolute artifact measurement,
i.e.
for consistent artifact recognition and quantification across vessel segments and patients.
The proposed deep-learning-based motion artifact measures allow one to decide whether and where diagnosis of coronary artery disease may be compromised by motion artifacts and motion correction algorithms should be applied to prevent misinterpretations.
Personal information
PD Dr.
habil.
Michael Graß
Principal Scientist
Philips Research
Philips GmbH Innovative Technologies
Research Laboratories Hamburg
Röntgenstrasse 24-26
22335 Hamburg / Germany
References
[1] Foy,
A.
J.,
Dhruva,
S.
S.,
Peterson,
B.,
Mandrola,
J.
M.,
Morgan,
D.
J.,
& Redberg,
R.
F.
(2017).
Coronary computed tomography angiography vs functional stress testing for patients with suspected coronary artery disease: a systematic review and meta-analysis.
JAMA internal medicine,
177(11),
1623-1631.
[2] Ghekiere,
O.,
Salgado,
R.,
Buls,
N.,
Leiner,
T.,
Mancini,
I.,
Vanhoenacker,
P.,
Dendale,
P.,
& Nchimi,
A.
(2017).
Image quality in coronary CT angiography: challenges and technical solutions.
The British journal of radiology,
90(1072),
20160567.
[3] Lossau,
T.,
Nickisch,...