A comparative study on detection of osteoporosis using deep learning methods: A review
Kavita Avinash Patil, K Prashanth, A Ramalingaiah
Abstract
Osteoporosis is a silent bone disease characterized by low bone mass and loss of bone tissue that may lead to weak and fragile bones and decreases in bone strength which increases the risk of fractures.It is more common in women rather than men. DEXA that is Dual Energy X-ray Absorptiometry is a model to diagnose osteoporosis although its low-availability, expensive, and high radiation exposure. The CAD (Computer-Aided Diagnosis) has enhanced the analysis to a higher level. The advanced learning paradigm that is Deep-Learn, Machine-Learn and Artificial Intelligence has exposed a turning point in the medical field which leads to accurate diagnosis of osteoporosis. The review is based on various anatomical sites such as lumbar spine, hip, forearm, calcaneus, and dental are assisted and examined based on validation, pre-trained networks, and accuracy. The combination of clinical data and images are fed to deep leaning models specifically CNN-Convolutional Neural Network, RNN-Recurrent Neural Network may result in completely automatic detection and diagnosis of osteoporosis.