Coronary artery disease (CAD) remains the first cause of morbidity and mortality in the Western world and it is expected that this trend will continue in the coming years. In clinical routine, patients with CAD are increasingly identified using non-invasive coronary CT angiography (CCTA), a non-invasive imaging tool for detection and exclusion of the obstructive coronary artery stenosis. Despite its high sensitivity, CCTA is currently not capable of determining the functional significance of the detected stenosis. Therefore, after undergoing CCTA, many patients undergo invasive coronary angiography (ICA).
In this project, we design a quantitative method to determine which coronary artery stenoses as seen on CCTA images are functionally significant, and thereby to identify patients who need to undergo invasive coronary catheterization and spare those who do not.
The video below describes our method for coronary calcium scoring in contrast-enhanced cardiac CT, which was presented at MICCAI 2015.
A slice from contrast enhanced cardiac CT scan (left) and corresponding slice from cardiac CT scan without contrast enhancement. Areas indicated in blue show calcified plaque in the left coronary artery.
Papers in international journals
|1.||Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis. Medical Image Analysis, 2018, vol. 44, pp. 72-85.|
|2.||Generative adversarial networks for noise reduction in low-dose CT. IEEE Transactions on Medical Imaging, in press, 2017.|
|3.||Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks. Medical Image Analysis, 2016, vol. 34, pp. 123-136.|
Papers in conference proceedings
|1.||Automatic segmentation and disease classification using cardiac cine MR images. In: Statistical Atlases and Computational Modeling of the Heart Workshop, in press, 2017.|
|2.||Dilated convolutional neural networks for cardiovascular MR segmentation in congenital heart disease. In: HVSMR 2016: MICCAI Workshop on Whole-Heart and Great Vessel Segmentation from 3D Cardiovascular MRI in Congenital Heart Disease, 2017, vol. 10129, pp. 95-102.|
|3.||Deep learning for multi-task medical image segmentation in multiple modalities. In: Medical Image Computing and Computer-Assisted Intervention, 2016, vol. 9901, pp. 478-486.|
|4.||Automatic segmentation of the left ventricle in cardiac CT angiography using convolutional neural networks. In: IEEE International Symposium on Biomedical Imaging, 2016, pp. pp. 40-43.|
|5.||Automatic coronary calcium scoring in cardiac CT angiography using convolutional neural networks. In: Medical Image Computing and Computer-Assisted Intervention, 2015, vol. 9349, pp. 589-596.|
|1.||Improving Specificity of Coronary CT Angiography for the Detection of Functionally Significant Coronary Artery Disease: A Deep Learning Approach. Radiological Society of North America, 103rd Annual Meeting , 2017.|
|2.||Deep learning analysis of the left ventricular myocardium in cardiac CT images enables detection of functionally significant coronary artery stenosis regardless of coronary anatomy. Radiological Society of North America, 103rd Annual Meeting , 2017.|
|3.||An adversarial deep learning approach to coronary CT radiation reduction. Society of Cardiovascular Computed Tomography, 12th Annual Scientific Meeting, 2017.|
|4.||Towards understanding the role of the hematological system in the pathophysiology of coronary calcifications: A cohort study. Society of Cardiovascular Computed Tomography, 12th Annual Scientific Meeting, 2017.|