AM-FM Texture Image Analysis of the Intima and Media Layers of the Carotid Artery

  • Authors:
  • Christos P. Loizou;Victor Murray;Marios S. Pattichis;Christodoulos S. Christodoulou;Marios Pantziaris;Andrew Nicolaides;Constantinos S. Pattichis

  • Affiliations:
  • Department of Computer Science, School of Sciences, Intercollege, Limassol, Cyprus CY-3507;Department of Computer Science, School of Sciences, Intercollege, Limassol, Cyprus CY-3507;Department of Computer Science, School of Sciences, Intercollege, Limassol, Cyprus CY-3507;Department of Computer Science, School of Sciences, Intercollege, Limassol, Cyprus CY-3507;Department of Computer Science, School of Sciences, Intercollege, Limassol, Cyprus CY-3507;Department of Computer Science, School of Sciences, Intercollege, Limassol, Cyprus CY-3507;Department of Computer Science, School of Sciences, Intercollege, Limassol, Cyprus CY-3507

  • Venue:
  • ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

The purpose of this paper is to propose the use of amplitude modulation-frequency modulation (AM-FM) features for describing atherosclerotic plaque features that are associated with clinical factors such as intima media thickness and a patient's age. AM-FM analysis reveals the instantaneous amplitude (IA) of the media layer decreases with age. This decrease in IA maybe attributed to the reduction in calcified, stable plaque components and an increase in stroke risk with age. On the other hand, an increase in the median instantaneous frequency (IF) of the media layer suggests the fragmentation of solid, large plaque components, which also lead to an increase in the risk of stroke. The findings suggest that AM-FM features can be used to assess the risk of stroke over a wide range of patient populations. Future work will incorporate a new texture image retrieval system that uses AM-FM features to retrieve intima and intima media layer images that could be associated with the same level of the risk of stroke.