Automated coronary artery tree extraction in coronary CT angiography using a multiscale enhancement and dynamic balloon tracking (MSCAR-DBT) method

RATIONAL AND OBJECTIVES To evaluate our prototype method for segmentation and tracking of the coronary arterial tree, which is the foundation for a computer-aided detection (CADe) system to be developed to assist radiologists in detecting non-calcified plaques in coronary CT angiography (cCTA) scans. MATERIALS AND METHODS The heart region was first extracted by a morphological operation and an adaptive thresholding method based on expectation-maximization (EM) estimation. The vascular structures within the heart region were enhanced and segmented using a multiscale coronary response (MSCAR) method that combined 3D multiscale filtering, analysis of the eigenvalues of Hessian matrices and EM estimation segmentation. After the segmentation of vascular structures, the coronary arteries were tracked by a 3D dynamic balloon tracking (DBT) method. The DBT method started at two manually identified seed points located at the origins of the left and right coronary arteries (LCA and RCA) for extraction of the arterial trees. The coronary arterial trees of a data set containing 20 ECG-gated contrast-enhanced cCTA scans were extracted by our MSCAR-DBT method and a clinical GE Advantage workstation. Two experienced thoracic radiologists visually examined the coronary arteries on the original cCTA scans and the rendered volume of segmented vessels to count the untracked false-negative (FN) segments and false positives (FPs) for both methods. RESULTS For the visible coronary arterial segments in the 20 cases, the radiologists identified that 25 segments were missed by our MSCAR-DBT method, ranging from 0 to 5 FN segments in individual cases, and that 55 artery segments were missed by the GE software, ranging from 0 to 7 FN segments in individual cases. 19 and 15 FPs were identified in our and the GE coronary trees, ranging from 0 to 4 FPs for both methods in individual cases, respectively. CONCLUSION The preliminary study demonstrates the feasibility of our MSCAR-DBT method for segmentation and tracking coronary artery trees. The results indicated that both our method and GE software can extract coronary artery trees reasonably well and the performance of our method is superior to that of GE software in this small data set. Further studies are underway to develop methods for improvement of the segmentation and tracking accuracy.

[1]  Cristian Lorenz,et al.  A General Framework for Tree Segmentation and Reconstruction from Medical Volume Data , 2004, MICCAI.

[2]  Demetri Terzopoulos,et al.  T-snakes: Topology adaptive snakes , 2000, Medical Image Anal..

[3]  J. Alison Noble,et al.  Statistical 3D Vessel Segmentation Using a Rician Distribution , 1999, MICCAI.

[4]  Jonathan G Goldin,et al.  Assessment of Coronary Artery Disease by Cardiac Computed Tomography: A Scientific Statement From the American Heart Association Committee on Cardiovascular Imaging and Intervention, Council on Cardiovascular Radiology and Intervention, and Committee on Cardiac Imaging, Council on Clinical Cardiolog , 2006, Circulation.

[5]  D. Mozaffarian,et al.  Heart disease and stroke statistics--2009 update: a report from the American Heart Association Statistics Committee and Stroke Statistics Subcommittee. , 2009, Circulation.

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

[7]  Berkman Sahiner,et al.  Automated segmentation and tracking of coronary arteries in ECG-gated cardiac CT scans , 2008, SPIE Medical Imaging.

[8]  W.E. Higgins,et al.  System for analyzing high-resolution three-dimensional coronary angiograms , 1996, IEEE Trans. Medical Imaging.

[9]  Y. Kawata,et al.  Computer-aided diagnosis for pulmonary nodules based on helical CT images , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[10]  Jürgen Weese,et al.  A Multi-scale Line Filter with Automatic Scale Selection Based on the Hessian Matrix for Medical Image Segmentation , 1997, Scale-Space.

[11]  T van Walsum,et al.  Coronary centerline extraction from CT coronary angiography images using a minimum cost path approach. , 2009, Medical physics.

[12]  Qiang Li,et al.  Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans. , 2003, Medical physics.

[13]  Stephen R. Aylward,et al.  Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction , 2002, IEEE Transactions on Medical Imaging.

[14]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[15]  M. Budoff,et al.  Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Indi , 2008, Journal of the American College of Cardiology.

[16]  Y. Kawata,et al.  Computer-aided diagnosis for pulmonary nodules based on helical CT images , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[17]  Jonathan Lessick,et al.  Accuracy of 16-row multidetector computed tomography for the assessment of coronary artery stenosis. , 2006, JAMA.

[18]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[19]  H MacMahon,et al.  Automated Segmentation and Visualization of the Pulmonary Vascular Tree in Spiral CT Angiography: An Anatomy-Oriented Approach Based on Three-Dimensional Image Analysis , 2001, Journal of computer assisted tomography.

[20]  D S Paik,et al.  Measurement of the aorta and its branches with helical CT. , 1998, Radiology.

[21]  D. Mozaffarian,et al.  Heart disease and stroke statistics--2009 update: a report from the American Heart Association Statistics Committee and Stroke Statistics Subcommittee. , 2009, Circulation.

[22]  Guido Gerig,et al.  Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images , 1998, Medical Image Anal..

[23]  Olivier D. Faugeras,et al.  CURVES: Curve evolution for vessel segmentation , 2001, Medical Image Anal..

[24]  D. Berman,et al.  Prognostic value of multidetector coronary computed tomographic angiography for prediction of all-cause mortality. , 2007, Journal of the American College of Cardiology.

[25]  Milan Sonka,et al.  Automated segmentation of pulmonary vascular tree from 3D CT images , 2004, SPIE Medical Imaging.

[26]  Nicholas Ayache,et al.  Model-Based Detection of Tubular Structures in 3D Images , 2000, Comput. Vis. Image Underst..

[27]  R. Frye,et al.  A reporting system on patients evaluated for coronary artery disease. Report of the Ad Hoc Committee for Grading of Coronary Artery Disease, Council on Cardiovascular Surgery, American Heart Association. , 1975, Circulation.

[28]  Lubomir M. Hadjiiski,et al.  Automatic multiscale enhancement and segmentation of pulmonary vessels in CT pulmonary angiography images for CAD applications. , 2007, Medical physics.

[29]  Jeffrey J Fine,et al.  Comparison of accuracy of 64-slice cardiovascular computed tomography with coronary angiography in patients with suspected coronary artery disease. , 2006, The American journal of cardiology.

[30]  Sebastian Stier,et al.  Extraction of line properties based on direction fields , 1996, IEEE Trans. Medical Imaging.

[31]  R. Given-Wilson,et al.  Observer variability in cancer detection during routine repeat (incident) mammographic screening in a study of two versus one view mammography , 1999, Journal of medical screening.

[32]  Max A. Viergever,et al.  Proceedings of the First International Conference on Scale-Space Theory in Computer Vision , 1997 .