Abstract—The objective of this paper is to design and implement classifier framework to assist the surgeon for preoperative assessment of bone quality from Dental Computed Tomography images. This article focuses on comparing the discriminating power of several multiresolution texture analysis methods to evaluate the quality of the bone based on the texture variations of the images obtained from the implant site using wavelet, curvelet and contourlet.The approach consists of three steps: automatic extraction of the most discriminative texture features of regions of interest , creation of a classifier that automatically grades the bone depends on the quality and correlating significant texture parameters with Insertion Torque Values. Since this is medical domain, the validation against the human experts is carried out. The results indicate that the combination of the statistical and multiscale representation of the bone image gives adequate information to classify the different bone groups compared to gray level features at single scale.

Index Terms—Multiresolution analysis, texture classification, wavelets, ridgelets, curvelets, contourlets, dental computed tomography.

Dr. T. Kalpalatha Reddy, T. Kaliraja, B. Ramesh and G Gurumurthy are with the Department of Electronics and Communications Engineering,SKR Engineering College affiliated to Anna University, Chennai, India (Email-drkalpalatha.thokala@gmail.com).

Cite: Dr. T. Kalpalatha Reddy, T. Kaliraja, B. Ramesh, and G. Gurumurthy, "Computer Aided Diagnosis of Dental CT images for Bone Quality Assessment," International Journal of Bioscience, Biochemistry and Bioinformatics vol. 1, no. 3, pp. 226-233, 2011.