Improved Osteoporosis Detection Process using Lightweight Deep Features

Authors

Meriem Mebarkia
Laboratory of Electrical Engineering (LABGET), Larbi Tebessi University - Tebessa, ALGERIA
Abdallah Meraoumia
Laboratory of Mathematics, Informatics and Systems (LAMIS), Larbi Tebessi University - Tebessa
Lotfi Houam
Laboratory of Mathematics, Informatics and Systems (LAMIS), University of Larbi Tebessi, Tebessa
Seddik Khemaissia
Laboratory of Electrical Engineering (LABGET), Larbi Tebessi University - Tebessa

Synopsis

In response to the prevalence of Osteoporosis, a debilitating bone disease, this paper introduces an efficient detection system utilizing Deep Image Features. The approach involves segmenting Osteoporosis images into blocks and applying PCANet Deep Learning for Feature Extraction. These features are then concatenated and subjected to Feature Selection, followed by SVM classification. The method demonstrates effectiveness and reliability in detecting Osteoporosis, potentially aiding medical experts in assessing patient’s risk during examinations.

ICAECE2023
Published
February 5, 2024