Linear vs. Quadratic Optimization Algorithms for Bias Correction of Left Ventricle Chamber Boundaries in Low Contrast Projection Ventriculograms Produced from Xray Cardiac Catheterization Procedure
Cardiac catheterization procedure produces ventriculograms which have very low contrast in the apical, anterior and inferior zones of the left ventricle (LV). Pixel-based classifiers operating on these images produce boundaries which have systematic positional and orientation bias and have a mean error of about 10.5 mm. Using the LV convex information, comprising of the apex and the aortic valve plane, this paper presents a comparison of the linear and quadratic optimization algorithms to remove these biases. These algorithms are named after the way the coefficients are computed: the identical coefficient and the independent coefficient. Using the polyline metric, we show that the quadratic optimization is better than the linear optimization. We also show that the independent coefficient method performs better than the identical coeffcient when the training data is large. The overall mean system error was 2.49 mm while the goal set by the cardiologist was 2.5 mm.
KeywordsLeft Ventricle Boundary Estimation Calibration Algorithm Cardiac Catheterization Procedure Left Ventricle Chamber
Unable to display preview. Download preview PDF.
- 1.Dumesnil et al.: LV Geometric Modeling and Quantification, Circulation (1979).Google Scholar
- 2.VanBree and Pope: Improving LV Border Recognition Using probability surfaces, IEEE Computers in Cardiology, pp. 121–124 (1989).Google Scholar
- 4.C. K. Lee: Ph.D Thesis, Department of Electrical Engineering, University of Washington, Seattle (1994).Google Scholar
- 5.Jasjit S. Suri, R. M. Haralick and F. H. Sheehan: Two Automatic Calibration Algorithms for Left Ventricle Boundary Estimation in X-ray Images, Proceedings of IEEE-Engineering in Medicine and Biology, Oct 31—Nov. 3 (1996).Google Scholar
- 6.Jasjit S. Suri, R. M. Haralick and F. H. Sheehan: Systematic Error Correction in automatically produced boundaries in Low Contrast Ventriculograms, International Conference in Pattern Recognition, Vienna, Austria, Vol. IV, Track D, pp. 361–365 (1996).Google Scholar
- 7.Jasjit S. Suri, R. M. Haralick and F. H. Sheehan: Accurate Left Ventricle Apex Position and Boundary Estimation From Noisy Ventriculograms, Proceedings of the IEEE Computers in Cardiology, Indianapolis, pp 257–260 (1996).Google Scholar
- 8.Jasjit S. Suri, R. M. Haralick and F. H. Sheehan: Left Ventricle Longitudinal Axis Fitting and LV Apex Estimation using a Robust Algorithm and its Performance: A Parametric Apex Model, International Conference in Image Processing, Santa Barbara, 1997, Volume III of III, IEEE ISBN Number 0-8186-8183-7, pp 118–121 (1997).Google Scholar
- 9.Jasjit S. Suri, R. M. Haralick and F. H. Sheehan: A General technique for automatic Left Ventricle Boundary Validation: Relation Between Cardioangiograms and Observed Boundary Errors, Journal of Digital Imaging, Vol. 10,No.2, Suppl 1, May, pp 1–7 (1997).Google Scholar
- 10.Jasjit S. Suri, R. M. Haralick and F. H. Sheehan: Effect of Edge Detection, Pixel Classification, Classification-Edge Fusion Over LV Calibration, A two Stage Automatic system, 10th Scandinavian Conference on Image Analysis (SCIA '97), June 9—11, Finland (1997).Google Scholar
- 11.Jasjit S. Suri, R. M. Haralick and F. H. Sheehan: Two Automatic Training-Based Forced Calibration Algorithms for Left Ventricle Boundary Estimation in Cardiac Images, Proceedings of IEEE-Engineering in Medicine and Biology, Chicago, Oct 31—Nov.2, ISBN 0-7803-4265-9(CD-ROM) SOE 9710002, pp. 528–532 (1997).Google Scholar
- 12.Jasjit S. Suri, R. M. Haralick and F. H. Sheehan: Automatic Quadratic Calibration for Correction of Pixel Classification Boundaries to an Accuracy of 2.5 Millimeters: An Application in Cardiac Imaging, Proceedings of Int. Conference in Pattern Recognition, Brisbane, Austrialia, pp. 30–33, Aug. (1998).Google Scholar