TY - GEN
T1 - Covariance shrinking in active shape models with application to gyral labeling of the cerebral cortex
AU - Yang, Zhen
AU - Carass, Aaron
AU - Prince, Jerry L.
PY - 2013
Y1 - 2013
N2 - Active shape models (ASMs) have been widely used in segmentation tasks in medical image analysis. Complex structures and a limited number of training samples can, however, result in the failure to capture the complete range of shape variations. Various modifications to the point distribution model (PDM) have been proposed to increase the flexibility of the model. Still model parameters are often determined empirically without respect to the underlying data structure. We explore shrinkage covariance estimation in building a PDM by combining the sample covariance matrix with a target covariance matrix estimated from a low-dimensional constrained model. Instead of using a global shrinkage intensity, we apply a spatially varying shrinkage intensity field to better adapt to the spatially varying characteristic of a complex shape. The parameters of the constrained model and the amount of shrinkage are determined in a data-driven fashion, so that the resulting distribution is optimized in representing the underlying data. The PDM, which we call SC-PDM, shows an increased flexibility in fitting new shapes and at the same time, is robust to noise. We demonstrate the effectiveness of using SC-PDM to label gyral regions on the human cerebral cortex.
AB - Active shape models (ASMs) have been widely used in segmentation tasks in medical image analysis. Complex structures and a limited number of training samples can, however, result in the failure to capture the complete range of shape variations. Various modifications to the point distribution model (PDM) have been proposed to increase the flexibility of the model. Still model parameters are often determined empirically without respect to the underlying data structure. We explore shrinkage covariance estimation in building a PDM by combining the sample covariance matrix with a target covariance matrix estimated from a low-dimensional constrained model. Instead of using a global shrinkage intensity, we apply a spatially varying shrinkage intensity field to better adapt to the spatially varying characteristic of a complex shape. The parameters of the constrained model and the amount of shrinkage are determined in a data-driven fashion, so that the resulting distribution is optimized in representing the underlying data. The PDM, which we call SC-PDM, shows an increased flexibility in fitting new shapes and at the same time, is robust to noise. We demonstrate the effectiveness of using SC-PDM to label gyral regions on the human cerebral cortex.
KW - Active shape model
KW - cerebral cortex
KW - covariance shrinking
KW - gyral labeling
KW - point distribution model
UR - http://www.scopus.com/inward/record.url?scp=84881645485&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84881645485&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2013.6556650
DO - 10.1109/ISBI.2013.6556650
M3 - Conference contribution
AN - SCOPUS:84881645485
SN - 9781467364546
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 1018
EP - 1021
BT - ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging
T2 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013
Y2 - 7 April 2013 through 11 April 2013
ER -