Active shape models—their training and application
Computer Vision and Image Understanding
ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 3 - Volume 3
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume IV-Volume 7472 - Volume 7472
Hi-index | 0.03 |
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 coeffcients are computed: the identical coeffcient and the independent coeffcient. Using the polyline metric, we show that the quadratic optimization is better than the linear optimization. We also show that the independent coeffcient 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.