Make Your Bone Great Again : A study on Osteoporosis Classification

TL;DR

This paper compares traditional texture features and deep learning features for osteoporosis classification from bone X-ray images, demonstrating that deep features offer superior discriminative power.

Contribution

The study provides a comparative analysis showing deep features outperform traditional texture features in osteoporosis classification from X-ray images.

Findings

Deep features outperform traditional features in classification accuracy.

Classifiers trained on deep features show higher discriminative power.

Traditional features like LBP and GLCM are less effective than CNN-based features.

Abstract

Osteoporosis can be identified by looking at 2D x-ray images of the bone. The high degree of similarity between images of a healthy bone and a diseased one makes classification a challenge. A good bone texture characterization technique is essential for identifying osteoporosis cases. Standard texture feature extraction techniques like Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM) have been used for this purpose. In this paper, we draw a comparison between deep features extracted from convolution neural network against these traditional features. Our results show that deep features have more discriminative power as classifiers trained on them always outperform the ones trained on traditional features.