AI Model for Bone Mineral Density Prediction From X-Ray Images
Trial Parameters
Brief Summary
Osteoporosis, a pervasive skeletal disorder characterized by diminished bone strength predisposing individuals to an increased risk of fractures, presents a substantial public health challenge globally. It's estimated that osteoporosis and its consequent increase in fracture risk significantly contribute to morbidity, mortality, and economic costs. Despite the availability of effective treatments, the condition often remains undiagnosed and untreated until a fracture occurs, underscoring the critical need for early detection and intervention. Dual-energy X-ray absorptiometry (DEXA) is the gold standard for assessing bone mineral density (BMD) and fracture risk. However, its utility is hampered by limited availability, especially in rural and low-resource settings, such as Bangladesh, where osteoporosis prevalence is notably high. The scarcity of DEXA units exacerbates the challenge of osteoporosis screening and management, leaving a significant portion of the population at risk In this context, plain X-ray imaging, widely available even in resource-constrained settings, emerges as a promising alternative for osteoporosis screening. Recent advancements in deep learning and computer vision offer the potential to automate the analysis of X-ray images for BMD estimation. The primary objective is to curate a comprehensive dataset of X-ray images of hip and spine as well as BMD reports and relevant clinical information sourced from local health facilities in Bangladesh encompassing diverse demographic data. The objective of this thesis is to develop and evaluate an Artificial Intelligence (AI)-based model that predicts BMD from plain X-ray images of the lumbar spine and pelvis. The proposed AI model processes X-ray images to detect subtle changes in bone texture and density, potentially offering a rapid, non-invasive, and cost-effective tool for large-scale osteoporosis screening, particularly beneficial in regions like Bangladesh where DEXA is scarcely available. This research addresses the critical gap in osteoporosis screening and diagnosis, aiming to contribute significantly to public health by enabling earlier detection and management of osteoporosis, thereby reducing the incidence of fractures and associated healthcare costs.
Eligibility Criteria
▪ Inclusion criteria: * Female and male patients aged 18 and above * Individuals willing to participate and who have provided informed consent for the use of their X-ray images and clinical data for research purposes. * Subjects with both X-ray images of hip and spine and DEXA scan results. * Accessibility to supplementary medical records that may contribute to the model's predictive accuracy, such as historical data on fractures, pregnancies, relevant medical conditions and other osteoporosis-related factors. * Exclusion criteria: * Subjects for whom X-ray images or clinical data are incomplete or of insufficient quality for analysis. * Individuals with medical conditions that could significantly alter bone density independently of osteoporosis, such as bone cancers or certain metabolic diseases. * Subjects who have undergone treatments or procedures that might significantly impact bone density measurement, such as long-term steroid use or recent orthopaedic surgeries. * Pregnant wome