TY  - CONF
AU  - Aura Hernandez-Sabate
AU  - Debora Gil
AU  - Petia Radeva
PY  - 2005//
TI  - On the usefulness of supervised learning for vessel border detection in IntraVascular Imaging
BT  - Proceeding of the 2005 conference on Artificial Intelligence Research and Development
SP  - 67
EP  - 74
PB  - IOS Press
CY  - Amsterdam, The Netherlands
KW  - classification
KW  - vessel border modelling
KW  - IVUS
N2  - IntraVascular UltraSound (IVUS) imaging is a useful tool in diagnosis of cardiac diseases since sequences completely show the morphology of coronary vessels. Vessel borders detection, especially the external adventitia layer, plays a central role in morphological measures and, thus, their segmentation feeds development of medical imaging techniques. Deterministic approaches fail to yield optimal results due to the large amount of IVUS artifacts and vessel borders descriptors. We propose using classification techniques to learn the set of descriptors and parameters that best detect vessel borders. Statistical hypothesis test on the error between automated detections and manually traced borders by 4 experts show that our detections keep within inter-observer variability.
L1  - http://refbase.cvc.uab.es/files/HGR2005c.pdf
N1  - IAM;MILAB
ID  - Aura Hernandez-Sabate2005
ER  -