Automatic Classifying of Patients With Non-Traumatic Fractures Based on Ultrasonic Guided Wave Spectrum Image Using a Dynamic Support Vector Machine

Jean-Gabriel Minonzio,Donatien Ramiandrisoa,Rodrigo Olivares,Bryan Cataldo,Broderick Crawford,Victor Hugo C De Albuquerque,Ricardo Soto,Roberto Munoz

doi:10.1109/access.2020.3033480

Abstract

Bone fractures are caused by diseases or accidents and are a widespread problem throughout the globe. Worldwide, 1.6 millions of hip fractures occur every year and are expected to rise to 6.3 millions in 2050. The current gold standard to assess fracture risk is the Dual-energy X-ray Absorptiometry (DXA), which provides a projected image of the bone from which areal bone mineral density is extracted. Ultrasound techniques have been proposed as non invasive alternatives. Recently, estimates of cortical thickness and porosity, obtained by Bi-Directional Axial Transmission (BDAT) in a pilot clinical study, have been shown to be associated with non-traumatic fractures in post menopausal women. Cortical parameters were derived from the comparison between experimental and theoretical guided modes. This model-based inverse approach failed for the patients associated with poor guided mode information. Moreover, even if the fracture discrimination ability was found similar to DXA, it remained moderate. The goal of this paper is to explore if these two limitations could be overcome by using automatic classification tools, independent of any waveguide model. To this end, a dynamic machine learning approach based on a Support Vector Machine (SVM) has been used to classify ultrasonic guided wave spectrum images measured by BDAT on post menopausal women with or without non-traumatic fractures. This approach has then been improved using parameters tuned by Bat Algorithm Optimization (BOA). The applied methodology focused on the extraction of texture features through a gray level co-occurrence matrix, structural comparison and histograms. The results accuracy was assessed using a confusion matrix. The effectiveness of the learning approach reached an accuracy of 92.31%.

Highlights

B ONE fractures are a widespread problem around the world, 1.6 millions of hip fractures occur every year worldwide and are expected to rise to 6.3 millions in2050 [1]
The context of this work is the development of novel medical devices aiming to complement the current gold standard for bone status assessment, i.e., Dual-energy X-ray Absorptiometry (DXA)
1https://scikit-learn.org/stable/ 2For further detail in the proposed approach and its replicability, we done available in https://github.com/Rainvert/ Clasificacion-de-Imagenes-Bi-Directional Axial Transmission (BDAT)-Fracturas

Summary

Introduction

B ONE fractures are a widespread problem around the world, 1.6 millions of hip fractures occur every year worldwide and are expected to rise to 6.3 millions in2050 [1]. 1 in 3 women and 1 in 5 men over 50 years old are expected to suffer an osteoporotic fracture [2]. In the case of Latin America, the projections from 1990 to 2050 suggest that the number of hip fractures for both men. The current gold standard to assess fracture risk is the Dual-energy X-ray Absorptiometry (DXA), providing areal Bone Mineral Density (aBMD in g.cm−2) as well as its normalized and adimensional counterpart T-score [4]. Due to its projective nature, this technique provides little information about the composition and the 3D-geometric properties determining bone strength. The context of this work is the development of novel medical devices aiming to complement the current gold standard for bone status assessment, i.e., DXA

Objectives

Results

Discussion

Conclusion