Automatic Coronary Calcium Scoring in Non-Contrast-Enhanced ECG-Triggered Cardiac CT With Ambiguity Detection

The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular events. We present a system that automatically quantifies total patient and per coronary artery CAC in non-contrast-enhanced, ECG-triggered cardiac CT. The system identifies candidate calcifications that cannot be automatically labeled with high certainty and optionally presents these to an expert for review. Candidates were extracted by intensity-based thresholding and described by location features derived from estimated coronary artery positions, as well as size, shape and intensity features. Next, a two-class classifier distinguished between coronary calcifications and negatives or a multiclass classifier labeled CAC per coronary artery. Candidates that could not be labeled with high certainty were identified by entropy-based ambiguity detection and presented to an expert for review and possible relabeling. The system was evaluated with 530 test images. Using the two-class classifier, the intra-class correlation coefficient (ICC) between reference and automatically determined total patient CAC volume was 0.95. Using the multiclass classifier, the ICC between reference and automatically determined per artery CAC volume was 0.98 (LAD), 0.69 (LCX), and 0.95 (RCA). In 49% of CTs, no ambiguous candidates were identified, while review of the remaining CTs increased the ICC for total patient CAC volume to 1.00, and per artery CAC volume to 1.00 (LAD), 0.95 (LCX), and 0.99 (RCA). In conclusion, CAC can be automatically identified in non-contrast-enhanced ECG-triggered cardiac CT. Ambiguity detection with expert review may enable the application of automatic CAC scoring in the clinic with a performance comparable to that of a human expert.

[1]  Frank Plastria,et al.  On the point for which the sum of the distances to n given points is minimum , 2009, Ann. Oper. Res..

[2]  Michael J Blaha,et al.  Polypill therapy, subclinical atherosclerosis, and cardiovascular events-implications for the use of preventive pharmacotherapy: MESA (Multi-Ethnic Study of Atherosclerosis). , 2014, Journal of the American College of Cardiology.

[3]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[4]  Tim Leiner,et al.  Coronary artery calcification scoring with state-of-the-art CT scanners from different vendors has substantial effect on risk classification. , 2014, Radiology.

[5]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[6]  Martin Styner,et al.  Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms , 2009, Medical Image Anal..

[7]  Philippe C. Cattin,et al.  Automatic Detection of Calcified Coronary Plaques in Computed Tomography Data Sets , 2008, MICCAI.

[8]  R. Detrano,et al.  Quantification of coronary artery calcium using ultrafast computed tomography. , 1990, Journal of the American College of Cardiology.

[9]  Alistair A. Young,et al.  Construction of a Coronary Artery Atlas from CT Angiography , 2014, MICCAI.

[10]  Max A. Viergever,et al.  An automatic machine learning system for coronary calcium scoring in clinical non-contrast enhanced, ECG-triggered cardiac CT , 2014, Medical Imaging.

[11]  Peter A. Flach,et al.  Improving Accuracy and Cost of Two-class and Multi-class Probabilistic Classifiers Using ROC Curves , 2003, ICML.

[12]  Bram van Ginneken,et al.  Detection of coronary calcifications from computed tomography scans for automated risk assessment of coronary artery disease. , 2007, Medical physics.

[13]  D. Rader,et al.  Electron beam computed tomographic coronary calcium scanning: a review and guidelines for use in asymptomatic persons. , 1999, Mayo Clinic proceedings.

[14]  Michael Fiechter,et al.  Inter-scan variability of coronary artery calcium scoring assessed on 64-multidetector computed tomography vs. dual-source computed tomography: a head-to-head comparison. , 2011, European heart journal.

[15]  Daniel S Berman,et al.  Progression of coronary artery calcium predicts all-cause mortality. , 2010, JACC. Cardiovascular imaging.

[16]  Anthony P. Reeves,et al.  Automated coronary artery calcification detection on low-dose chest CT images , 2014, Medical Imaging.

[17]  L. V. van Vliet,et al.  Vessel specific coronary artery calcium scoring: an automatic system. , 2013, Academic radiology.

[18]  Yen H. Le,et al.  A supervised classification-based method for coronary calcium detection in non-contrast CT , 2010, The International Journal of Cardiovascular Imaging.

[19]  Philip S. Yu,et al.  Effective estimation of posterior probabilities: explaining the accuracy of randomized decision tree approaches , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[20]  Max A. Viergever,et al.  Automatic Coronary Calcium Scoring in Low-Dose Chest Computed Tomography , 2012, IEEE Transactions on Medical Imaging.

[21]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[22]  Marleen de Bruijne,et al.  Toward a Theory of Statistical Tree-Shape Analysis , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  D. Goff,et al.  Comparison of novel risk markers for improvement in cardiovascular risk assessment in intermediate-risk individuals. , 2012, JAMA.

[24]  Moyses Szklo,et al.  Coronary calcium as a predictor of coronary events in four racial or ethnic groups. , 2008, The New England journal of medicine.

[25]  T. Callister,et al.  Coronary artery disease: improved reproducibility of calcium scoring with an electron-beam CT volumetric method. , 1998, Radiology.

[26]  I. Kakadiaris,et al.  Toward the automatic detection of coronary artery calcification in non-contrast computed tomography data , 2010, The International Journal of Cardiovascular Imaging.

[27]  Udo Hoffmann,et al.  Diagnostic and prognostic value of absence of coronary artery calcification. , 2009, JACC. Cardiovascular imaging.

[28]  Max A. Viergever,et al.  Label Fusion in Atlas-Based Segmentation Using a Selective and Iterative Method for Performance Level Estimation (SIMPLE) , 2010, IEEE Transactions on Medical Imaging.

[29]  Michael Pignone,et al.  Using the Coronary Artery Calcium Score to Guide Statin Therapy: A Cost-Effectiveness Analysis , 2014, Circulation. Cardiovascular quality and outcomes.