Curvelet-Based Texture Classification of Tissues in Computed Tomography

The research presented in this article is aimed at the development of an automated imaging system for classification of tissues in medical images obtained from Computed Tomography (CT) scans. The article focuses on using curvelet-based multi-resolution texture analysis. The approach consists of two steps: automatic extraction of the most discriminative texture features of regions of interest and creation of a classifier that automatically identifies the various tissues. The discriminating power of several curvelet-based texture descriptors are investigated. Tests indicate that Energy, Entropy, Mean and Standard Deviation signatures are the most effective descriptors for curvelets, yielding accuracy rates in the 97 - 98% range. A comparison with a similar algorithm based on wavelet and ridgelet texture descriptors clearly shows that using curvelet-based texture features significantly improves the classification of normal tissues in CT scans.

• Type: Conference
• Year: 2006
• Where: ICIP
• Authors: Lindsay Semler, Lucia Dettori
• Keywords: Curvelet-based Texture Descriptors, Curvelet-based Texture Features, Discriminative Texture Features, ICIP 2006, Image Processing, Multi-resolution Texture Analysis, Ridgelet Texture Descriptors