Advertisement

Automated segmentation and quantification of aortic calcification at abdominal CT: application of a deep learning-based algorithm to a longitudinal screening cohort

  • Peter M. Graffy
  • Jiamin Liu
  • Stacy O’Connor
  • Ronald M. Summers
  • Perry J. PickhardtEmail author
Technical

Abstract

Objective

To investigate an automated aortic calcium segmentation and scoring tool at abdominal CT in an adult screening cohort.

Methods

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.

Results

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%).

Conclusion

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.

Keywords

Aortic calcium Deep learning Fully automated Artificial intelligence Cardiovascular disease 

Abbreviations

R-CNN

Convolutional neural networks

CVD

Cardiovascular disease

CT

Computed tomography

ROI

Region of interest

HU

Hounsfield unit

Notes

Acknowledgement

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.

Ethical approval

This study was approved by our institutional IRB.

References

  1. 1.
    Benjamin, E.J., et al., Heart Disease and Stroke Statistics-2017 Update: A Report From the American Heart Association. Circulation, 2017. 135(10): p. e146-e603.CrossRefGoogle Scholar
  2. 2.
    Sidney, S., et al., Recent Trends in Cardiovascular Mortality in the United States and Public Health Goals. JAMA Cardiol, 2016. 1(5): p. 594-9CrossRefGoogle Scholar
  3. 3.
    Hajar, R., Framingham Contribution to Cardiovascular Disease. Heart views: the official journal of the Gulf Heart Association, 2016. 17(2): p. 78-81.CrossRefGoogle Scholar
  4. 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
  5. 5.
    James, P.A., et al., 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). Jama, 2014. 311(5): p. 507-20.CrossRefGoogle Scholar
  6. 6.
    Alqahtani, A.M., et al., Quantifying Aortic Valve Calcification using Coronary Computed Tomography Angiography. J Cardiovasc Comput Tomogr, 2017. 11(2): p. 99-104.CrossRefGoogle Scholar
  7. 7.
    Budoff, M.J., et al., Thoracic aortic calcification and coronary heart disease events: the multi-ethnic study of atherosclerosis (MESA). Atherosclerosis, 2011. 215(1): p. 196-202.CrossRefGoogle Scholar
  8. 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. 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
  10. 10.
    Pletcher, M.J., et al., Using the coronary artery calcium score to predict coronary heart disease events: a systematic review and meta-analysis. Arch Intern Med, 2004. 164(12): p. 1285-92.CrossRefGoogle Scholar
  11. 11.
    Eberhard, M., et al., Quantification of aortic valve calcification on contrast-enhanced CT of patients prior to transcatheter aortic valve implantation. EuroIntervention, 2017. 13(8): p. 921-927.CrossRefGoogle Scholar
  12. 12.
    Gernaat, S.A.M., et al., Automatic quantification of calcifications in the coronary arteries and thoracic aorta on radiotherapy planning CT scans of Western and Asian breast cancer patients. Radiother Oncol, 2018. 127(3): p. 487-492.CrossRefGoogle Scholar
  13. 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
  14. 14.
    Zoghbi, W.A., Cardiovascular imaging: a glimpse into the future. Methodist DeBakey cardiovascular journal, 2014. 10(3): p. 139-145.CrossRefGoogle Scholar
  15. 15.
    Elmasri, K., et al., Automatic Detection and Quantification of Abdominal Aortic Calcification in Dual Energy X-ray Absorptiometry. Procedia Computer Science, 2016. 96: p. 1011-1021.CrossRefGoogle Scholar
  16. 16.
    Kurugol, S., et al., Automated quantitative 3D analysis of aorta size, morphology, and mural calcification distributions. Medical physics, 2015. 42(9): p. 5467-5478.CrossRefGoogle Scholar
  17. 17.
    O’Connor, S.D., et al., Does Nonenhanced CT-based Quantification of Abdominal Aortic Calcification Outperform the Framingham Risk Score in Predicting Cardiovascular Events in Asymptomatic Adults? Radiology, 2019. 290(1): p. 108-115.CrossRefGoogle Scholar
  18. 18.
    Pickhardt, P.J., Imaging and Screening for Colorectal Cancer with CT Colonography. Radiol Clin North Am, 2017. 55(6): p. 1183-1196.CrossRefGoogle Scholar
  19. 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. 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. 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. 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
  23. 23.
    He, K.M., et al., Mask R-CNN. 2017 Ieee International Conference on Computer Vision (Iccv), 2017: p. 2980-2988.CrossRefGoogle Scholar
  24. 24.
    Rumberger, J.A. and L. Kaufman, A Rosetta Stone for Coronary Calcium Risk Stratification: Agatston, Volume, and Mass Scores in 11,490 Individuals. American Journal of Roentgenology, 2003. 181(3): p. 743-748.CrossRefGoogle Scholar
  25. 25.
    Dudina, A., et al., Relationships between body mass index, cardiovascular mortality, and risk factors: a report from the SCORE investigators. Eur J Cardiovasc Prev Rehabil, 2011. 18(5): p. 731-42.CrossRefGoogle Scholar
  26. 26.
    Khan, S.S., et al., Association of Body Mass Index With Lifetime Risk of Cardiovascular Disease and Compression of Morbidity. JAMA Cardiol, 2018. 3(4): p. 280-287.CrossRefGoogle Scholar
  27. 27.
    Mancio, J., et al., Association of body mass index and visceral fat with aortic valve calcification and mortality after transcatheter aortic valve replacement: the obesity paradox in severe aortic stenosis. Diabetol Metab Syndr, 2017. 9: p. 86.CrossRefGoogle Scholar
  28. 28.
    Glodny, B., et al., A method for calcium quantification by means of CT coronary angiography using 64-multidetector CT: very high correlation with Agatston and volume scores. Eur Radiol, 2009. 19(7): p. 1661-8.CrossRefGoogle Scholar
  29. 29.
    Laudon, D.A., et al., Computed tomographic coronary artery calcium assessment for evaluating chest pain in the emergency department: long-term outcome of a prospective blind study. Mayo Clinic proceedings, 2010. 85(4): p. 314-322.CrossRefGoogle Scholar
  30. 30.
    Li, Q., et al., Coronary artery calcium quantification using contrast-enhanced dual-energy computed tomography scans in comparison with unenhanced single-energy scans. Phys Med Biol, 2018. 63(17): p. 175006.CrossRefGoogle Scholar
  31. 31.
    Moreno, C.C., et al., Changing Abdominal Imaging Utilization Patterns: Perspectives From Medicare Beneficiaries Over Two Decades. Journal of the American College of Radiology, 2016. 13(8): p. 894-903.CrossRefGoogle Scholar
  32. 32.
    Lee, S.J. and P.J. Pickhardt, Opportunistic Screening for Osteoporosis Using Body CT Scans Obtained for Other Indications: the UW Experience. Clinical Reviews in Bone and Mineral Metabolism, 2017. 15(3): p. 128-137.CrossRefGoogle Scholar
  33. 33.
    Pickhardt, P.J., et al., Opportunistic Screening for Osteoporosis Using Abdominal Computed Tomography Scans Obtained for Other Indications. Annals of Internal Medicine, 2013. 158(8): p. 588-595.CrossRefGoogle Scholar
  34. 34.
    Boyce, C.J., et al., Hepatic Steatosis (Fatty Liver Disease) in Asymptomatic Adults Identified by Unenhanced Low-Dose CT. American Journal of Roentgenology, 2010. 194(3): p. 623-628.CrossRefGoogle Scholar
  35. 35.
    Pickhardt, P.J., et al., Natural History of Hepatic Steatosis: Observed Outcomes for Subsequent Liver and Cardiovascular Complications. American Journal of Roentgenology, 2014. 202(4): p. 752-758.CrossRefGoogle Scholar
  36. 36.
    Pickhardt, P.J., et al., Visceral Adiposity and Hepatic Steatosis at Abdominal CT: Association With the Metabolic Syndrome. American Journal of Roentgenology, 2012. 198(5): p. 1100-1107.CrossRefGoogle Scholar
  37. 37.
    Pickhardt, P.J., et al., CT colonography to screen for colorectal cancer and aortic aneurysm in the Medicare population: cost-effectiveness analysis. AJR Am J Roentgenol, 2009. 192(5): p. 1332-40.CrossRefGoogle Scholar
  38. 38.
    Lee, S.J., et al., Fully automated segmentation and quantification of visceral and subcutaneous fat at abdominal CT: application to a longitudinal adult screening cohort. Br J Radiol, 2018. 91(1089): p. 20170968.CrossRefGoogle Scholar
  39. 39.
    Lee, S.J., P.A. Anderson, and P.J. Pickhardt, Predicting Future Hip Fractures on Routine Abdominal CT Using Opportunistic Osteoporosis Screening Measures: A Matched Case-Control Study. AJR Am J Roentgenol, 2017. 209(2): p. 395-402.CrossRefGoogle Scholar
  40. 40.
    Lee, S.J., et al., Future Osteoporotic Fracture Risk Related to Lumbar Vertebral Trabecular Attenuation Measured at Routine Body CT. J Bone Miner Res, 2018. 33(5): p. 860-867.CrossRefGoogle Scholar
  41. 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

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Peter M. Graffy
    • 1
  • Jiamin Liu
    • 2
  • Stacy O’Connor
    • 3
  • Ronald M. Summers
    • 2
  • Perry J. Pickhardt
    • 1
    Email author
  1. 1.E3/311 Clinical Science CenterUniversity of Wisconsin School of Medicine and Public HealthMadisonUSA
  2. 2.Radiology & Imaging SciencesNational Institutes of Health Clinical CenterBethesdaUSA
  3. 3.Department of RadiologyMedical College of WisconsinMilwaukeeUSA

Personalised recommendations