Feature Selection of the Combination of Porous Trabecular with Anthropometric Features for Osteoporosis Screening

Enny Itje Sela, Sri Hartati, Agus Harjoko, Retantyo Wardoyo, Munakhir Mudjosemedi

Abstract


This study aims to select the important features from the combination of porous trabecular pattern with anthropometric features for osteoporosis screening. The study sample has their bone mineral density (BMD) measured at the proximal femur/lumbar spine using dual-energy X-ray absorptiometry (DXA). Morphological porous features such as porosity, the size of porous, and the orientation of porous are obtained from each dental radiograph using digital image processing. The anthropometric features considered are age, height, weight, and body mass index (BMI). Decision tree (J.48 method) is used to evaluate the accuracy of morphological porous and anthropometric features for selection data. The study shows that the most important feature is age and the considered features for osteoporosis screening are porosity, vertical pore, and oblique pore. The decision tree has considerably high accuracy, sensitivity, and specificity.

Keywords


dental periapical X-Ray; osteoporosis; porous extraction; anthropometric features

Full Text:

PDF


DOI: http://doi.org/10.11591/ijece.v5i1.pp78-83

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Electrical and Computer Engineering (IJECE)
p-ISSN 2088-8708, e-ISSN 2722-2578

This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).