Premium
Resolution and SNR effects on carotid plaque classification
Author(s) -
Ronen Raphael R.,
Clarke Sharon E.,
Hammond Robert R.,
Rutt Brian K.
Publication year - 2006
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.20956
Subject(s) - weighting , pattern recognition (psychology) , artificial intelligence , robustness (evolution) , segmentation , carotid endarterectomy , image resolution , resolution (logic) , computer science , mathematics , nuclear medicine , carotid arteries , medicine , radiology , chemistry , biochemistry , gene
Multicontrast‐weighted MRI, which is increasingly being used in combination with automatic classification algorithms, has the potential to become a powerful tool for assessing plaque composition. The current literature, however, does not address the relationship between imaging conditions and segmentation viability well. In this study 13 carotid endarterectomy samples were imaged with a 156‐μm in‐plane resolution and high signal‐to‐noise ratio (SNR) using proton density (PD), T 1 , T 2 , and diffusion weightings. The maximum likelihood (ML) algorithm was used to classify plaque components, with sets of three contrast weighting intensities used as features. The resolution and SNR of the images were then degraded. Classification accuracy was found to be independent of in‐plane resolution between 156 μm and 1250 μm, but dependent on SNR. Accuracy decreased less than 10% for degradation in SNR down to 25% of original values, and decreased sharply thereafter. The robustness of automatic classifiers makes them applicable to a wide range of imaging conditions, including standard in vivo carotid imaging scenarios. Magn Reson Med, 2006. © 2006 Wiley‐Liss, Inc.