Automated segmentation and quantification of aortic calcification at abdominal CT: application of a deep learning-based algorithm to a longitudinal screening cohort
To investigate an automated aortic calcium segmentation and scoring tool at abdominal CT in an adult screening cohort.
Using instance segmentation with convolutional neural networks (Mask R-CNN), a fully automated vascular calcification algorithm was applied to a data set of 9914 non-contrast CT scans from 9032 consecutive asymptomatic adults (mean age, 57.5 ± 7.8 years; 4467 M/5447F) undergoing colonography screening. Follow-up scans were performed in a subset of 866 individuals (mean interval, 5.4 years). Automated abdominal aortic calcium volume, mass, and Agatston score were assessed. In addition, comparison was made with a separate validated semi-automated approach in a subset of 812 cases.
Mean values were significantly higher in males for Agatston score (924.2 ± 2066.2 vs. 564.2 ± 1484.2, p < 0.001), aortic calcium mass (222.2 ± 526.0 mg vs. 144.5 ± 405.4 mg, p < 0.001) and volume (699.4 ± 1552.4 ml vs. 426.9 ± 1115.5 HU, p < 0.001). Overall age-specific Agatston scores increased an average of 10%/year for the entire cohort; males had a larger Agatston score increase between the ages of 40 to 60 than females (91.2% vs. 75.1%, p < 0.001) and had significantly higher mean Agatston scores between ages 50 and 80 (p < 0.001). For the 812-scan subset with both automated and semi-automated methods, median difference in Agatston score was 66.4 with an r2 agreement value of 0.84. Among the 866-patient cohort with longitudinal follow-up, the average Agatston score change was 524.1 ± 1317.5 (median 130.9), reflecting a mean increase of 25.5% (median 73.6%).
This robust, fully automated abdominal aortic calcification scoring tool allows for both individualized and population-based assessment. Such data could be automatically derived at non-contrast abdominal CT, regardless of the study indication, allowing for opportunistic assessment of cardiovascular risk.
KeywordsAortic calcium Deep learning Fully automated Artificial intelligence Cardiovascular disease
Convolutional neural networks
Region of interest
This research was supported in part by the Intramural Research Program of the National Institutes of Health Clinical Center and made use of the high performance computing capabilities of the NIH Biowulf system.
Compliance with ethical standards
Conflict of interest
The authors have no direct conflict of interest, but Dr. Pickhardt serves as an advisor to Bracco and is a shareholder in SHINE, Elucent, and Cellectar and Dr. Summers receives royalties from iCAD, PingAn, Philips and ScanMed and research support from PingAn and NVIDIA.
This study was approved by our institutional IRB.
- 4.Executive Summary of The Third Report of The National Cholesterol Education Program (NCEP) Expert Panel on Detection, Evaluation, And Treatment of High Blood Cholesterol In Adults (Adult Treatment Panel III). Jama, 2001. 285(19): p. 2486-97.Google Scholar
- 8.DeLoach, S.S., et al., Aortic calcification predicts cardiovascular events and all-cause mortality in renal transplantation. Nephrology, dialysis, transplantation: official publication of the European Dialysis and Transplant Association - European Renal Association, 2009. 24(4): p. 1314-1319.CrossRefGoogle Scholar
- 9.O’Leary, D.H., et al., Carotid-artery intima and media thickness as a risk factor for myocardial infarction and stroke in older adults. Cardiovascular Health Study Collaborative Research Group. N Engl J Med, 1999. 340(1): p. 14-22.Google Scholar
- 13.Isgum, I., B. van Ginneken, and M. Olree, Automatic detection of calcifications in the aorta from CT scans of the abdomen. 3D computer-aided diagnosis. Acad Radiol, 2004. 11(3): p. 247-57.Google Scholar
- 19.Chellamuthu, K., et al., Atherosclerotic Vascular Calcification Detection and Segmentation on Low Dose Computed Tomography Scans Using Convolutional Neural Networks, in IEEE ISBI. 2017: Melbourne, Australia. p. 388-391.Google Scholar
- 20.Liu, J., et al., Pelvic artery calcification detection on CT scans using convolutional neural networks, in SPIE Medical Imaging, S.G. Armato and N.A. Petrick, Editors. 2017. p. 101341A.Google Scholar
- 21.Liu, J., et al., A Semi-Supervised CNN Learning Method with Pseudo-class Labels for Atherosclerotic Vascular Calcification Detection, in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy, April 8-11, 2019. pp. 780-783.Google Scholar
- 22.Yao, J., O’Connor, S.D. and Summers, R.M. Automated spinal column extraction and partitioning. in 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006. 2006.Google Scholar
- 41.Pickhardt, P.J., et al., Population-based opportunistic osteoporosis screening: Validation of a fully automated CT tool for assessing longitudinal BMD changes. British Journal of Radiology, 2019. 92(1094).Google Scholar