Title :
Osteoporosis Diagnosis Using Fractal Analysis and Support Vector Machine
Author :
Tafraouti, Abdessamad ; El Hassouni, Mohammed ; Toumi, Hechmi ; Lespessailles, Eric ; Jennane, Rachid
Author_Institution :
Fac. of Sci., Univ. of Mohammed V, Rabat, Morocco
Abstract :
The objective of this paper lies on the characterization of osteoporosis disease using fractal analysis of X-Ray images. The method consists of a pre-processing step followed by a feature extraction based on the fractional Brownian motion (fBm) model. The Support Vector Machine (SVM) was used as a classifier to distinguish between two populations composed of Osteoporotic Patients (OP) and Control Cases (CC). Our proposed method achieved an accuracy classification rate of 95%, which means that it offers a good discrimination between OP patients and CC subjects.
Keywords :
bone; diagnostic radiography; diseases; feature extraction; fractals; medical disorders; medical image processing; support vector machines; SVM; X-ray images; accuracy classification rate; fBm model; feature extraction; fractal analysis; fractional Brownian motion model; osteoporosis diagnosis; osteoporosis disease; osteoporotic patients; support vector machine; Accuracy; Bones; Feature extraction; Kernel; Quantization (signal); Support vector machines; X-ray imaging; Fractional Brownian Motion; Fractional Gaussian Noise; Osteoporosis; SVM; Texture;
Conference_Titel :
Signal-Image Technology and Internet-Based Systems (SITIS), 2014 Tenth International Conference on
DOI :
10.1109/SITIS.2014.49
