A fully automated shape analysis algorithm based on the Point Distribution Model is proposed (APoD). The algorithm identifies automatically the edges of noisy shapes, determining for each shape a fixed number of contour points and the underlying true shape. The proposed algorithm has been tested using a database of simulated images with different noise levels. The performance of the model was investigated using 50000 simulated images which differ from a gold standard for approximately 20% of pixels.With this method a Dice index D=0.968±0.004 is obtained. © 2012 Taylor & Francis Group.
Automated Shape Analysis landmarks detection for medical image processing
Amoroso N.;Bellotti R.;Logroscino G.;Tangaro S.;
2012-01-01
Abstract
A fully automated shape analysis algorithm based on the Point Distribution Model is proposed (APoD). The algorithm identifies automatically the edges of noisy shapes, determining for each shape a fixed number of contour points and the underlying true shape. The proposed algorithm has been tested using a database of simulated images with different noise levels. The performance of the model was investigated using 50000 simulated images which differ from a gold standard for approximately 20% of pixels.With this method a Dice index D=0.968±0.004 is obtained. © 2012 Taylor & Francis Group.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
