TY - JOUR

T1 - Automatic shape model building based on principal geodesic analysis bootstrapping

AU - Dam, Erik B

AU - Fletcher, P Thomas

AU - Pizer, Stephen M

PY - 2008/4

Y1 - 2008/4

N2 - We present a novel method for automatic shape model building from a collection of training shapes. The result is a shape model consisting of the mean model and the major modes of variation with a dense correspondence map between individual shapes. The framework consists of iterations where a medial shape representation is deformed into the training shapes followed by computation of the shape mean and modes of shape variation. In the first iteration, a generic shape model is used as starting point - in the following iterations in the bootstrap method, the resulting mean and modes from the previous iteration are used. Thereby, we gradually capture the shape variation in the training collection better and better. Convergence of the method is explicitly enforced. The method is evaluated on collections of artificial training shapes where the expected shape mean and modes of variation are known by design. Furthermore, collections of real prostates and cartilage sheets are used in the evaluation. The evaluation shows that the method is able to capture the training shapes close to the attainable accuracy already in the first iteration. Furthermore, the correspondence properties measured by generality, specificity, and compactness are improved during the shape model building iterations.

AB - We present a novel method for automatic shape model building from a collection of training shapes. The result is a shape model consisting of the mean model and the major modes of variation with a dense correspondence map between individual shapes. The framework consists of iterations where a medial shape representation is deformed into the training shapes followed by computation of the shape mean and modes of shape variation. In the first iteration, a generic shape model is used as starting point - in the following iterations in the bootstrap method, the resulting mean and modes from the previous iteration are used. Thereby, we gradually capture the shape variation in the training collection better and better. Convergence of the method is explicitly enforced. The method is evaluated on collections of artificial training shapes where the expected shape mean and modes of variation are known by design. Furthermore, collections of real prostates and cartilage sheets are used in the evaluation. The evaluation shows that the method is able to capture the training shapes close to the attainable accuracy already in the first iteration. Furthermore, the correspondence properties measured by generality, specificity, and compactness are improved during the shape model building iterations.

KW - Algorithms

KW - Artificial Intelligence

KW - Computer Simulation

KW - Humans

KW - Image Enhancement

KW - Image Interpretation, Computer-Assisted

KW - Imaging, Three-Dimensional

KW - Models, Biological

KW - Pattern Recognition, Automated

KW - Reproducibility of Results

KW - Sensitivity and Specificity

KW - Evaluation Studies

KW - Journal Article

U2 - 10.1016/j.media.2007.08.004

DO - 10.1016/j.media.2007.08.004

M3 - Journal article

C2 - 18178124

VL - 12

SP - 136

EP - 151

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 2

ER -