Make Your Bone Great Again : A study on Osteoporosis Classification
This work addresses the challenge of distinguishing between healthy and osteoporotic bones in medical imaging, though it is incremental as it compares existing feature extraction methods without introducing a new technique.
The study tackled osteoporosis classification from 2D X-ray images by comparing deep features from convolutional neural networks against traditional texture features like LBP and GLCM, finding that classifiers using deep features consistently outperformed those using traditional features.
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.