Status
Conditions
Treatments
Study type
Funder types
Identifiers
About
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.
Full description
This study aims to develop a robust artificial intelligence (AI) model for predicting Bone Mineral Density (BMD) from X-ray images using deep learning techniques, with a particular focus on improving the model's generalizability across diverse populations. The purpose is to provide an accessible, non-invasive screening tool for osteoporosis, reducing dependency on dual-energy X-ray absorptiometry (DEXA) scans, which are often unavailable or unaffordable in low-resource settings such as Bangladesh. Leveraging the convolutional neural network (CNN) architecture, this AI model is expected to assist in early osteoporosis diagnosis and management, ultimately improving clinical decision-making and healthcare efficiency.
This case-control observational study will be conducted in the Radiology Department of Ibn Sina Diagnostic and Consultation Center, Uttara. The study comprises both prospective and retrospective data collection phases, allowing for comprehensive data aggregation. During the prospective phase, data will be collected directly from eligible patients undergoing X-ray imaging and DEXA scans. For the retrospective phase, historical data will be extracted from clinical databases, including X-ray images and corresponding BMD reports. The study aims to address variations in bone health across a broad demographic, reflecting the prevalence of osteoporosis among different ages, genders, and clinical backgrounds in Bangladesh.
In Bangladesh, osteoporosis remains underdiagnosed due to the limited availability of DEXA scanners and trained personnel, particularly in rural and resource-constrained areas. The standard diagnostic pathway often begins with symptomatic X-ray imaging, followed by a DEXA scan if osteoporosis is suspected. This two-step process is costly and time-consuming, delaying diagnosis and treatment, which can lead to serious complications, including fractures. AI-driven predictions of BMD from X-ray images have the potential to streamline this pathway, enabling cost-effective screening and prioritization of patients who may need further DEXA-based testing. The AI model will be trained using a comprehensive dataset that includes demographic and clinical covariates-such as age, gender, menopausal status, and comorbid conditions like diabetes and cardiovascular disease-capturing correlations that could enhance prediction accuracy. Ultimately, the goal is to offer a reliable, scalable solution for osteoporosis screening that could be integrated into existing clinical workflows and alleviate the need for DEXA in settings where it is unavailable.
The study targets a diverse population group, including individuals with normal bone density, osteopenia, and osteoporosis as defined by DEXA measurements. This diversity ensures that the AI model can account for a wide spectrum of patient profiles and enhance its predictive robustness. The population will consist of adults across all age groups and genders, including both symptomatic and asymptomatic individuals.
The study will follow a structured protocol for data collection, aiming to gather comprehensive information on patients that may influence bone health. Key variables will include demographic details such as age, gender, and menopausal status; clinical variables like the presence of comorbidities such as diabetes and cardiovascular disease, BMI, and history of fractures; and imaging and diagnostic results, specifically X-ray images (spine or hip) and DEXA scan results for ground truth BMD values. In the prospective phase, eligible patients undergoing X-ray or DEXA scans will be approached for consent, and upon agreement, their clinical and demographic data will be recorded, including a unique identifier to ensure data integrity and confidentiality. Anonymized X-ray and DEXA images will then be collected, forming the primary dataset for AI training. The retrospective phase will involve data extraction from existing clinical records, focusing on spine and hip X-ray images and corresponding BMD results. Identifiable patient information will be removed to protect privacy. This historical dataset will complement the prospective data, providing a broader spectrum of cases and contributing to model generalizability.
The AI model will be developed using CNN architecture tailored for image-based prediction. Exploratory data analysis will be conducted initially to understand the distribution of key demographics and clinical factors, which will inform the balance and structure of the dataset. Once the data is cleaned and processed, the CNN model will be trained to predict BMD values directly from X-ray images, with actual DEXA measurements serving as ground truth. Model performance will be evaluated using metrics critical for clinical application, including Mean Absolute Error (MAE) and Pearson Correlation Coefficient (PCC) to assess prediction accuracy, as well as Area Under the Precision-Recall Curve (AUPRC) and overall accuracy to measure diagnostic robustness. To further ensure accuracy, a k-fold cross-validation technique will be applied, generating mean values and standard deviations for each metric, thereby providing insight into the model's consistency. Comparisons between various CNN architectures and training methodologies will identify the optimal approach for BMD prediction.
Upon completion, the AI model will serve as an assistive diagnostic tool for BMD assessment from X-ray images, with several anticipated applications. First, the model will support early detection of osteoporosis by identifying low BMD values, enabling clinicians to detect osteoporosis earlier in the diagnostic pathway and potentially improving patient outcomes. Second, it will aid clinical decision-making by allowing healthcare professionals to prioritize patients for further testing, particularly in resource-limited settings. Third, the analysis of clinical covariates such as age, gender, and comorbidities with BMD could refine risk assessment, supporting more personalized osteoporosis management strategies. Lastly, the structured storage of images, BMD values, and clinical data will support future bone health research, enhancing osteoporosis screening and preventive care capabilities.
This study requires no additional facilities beyond those already available within the clinical radiology departments for X-ray and DEXA scanning. Existing data storage capabilities will support data management, ensuring compliance with privacy and security standards for patient information. In summary, this study's AI model seeks to deliver a viable, scalable solution for osteoporosis screening by offering accurate, non-invasive BMD predictions from X-ray images. This approach has the potential to improve healthcare access, especially in rural and low-resource settings, where it can function as a screening tool that mitigates the dependence on costly DEXA scans.
Enrollment
Sex
Ages
Volunteers
Inclusion and exclusion 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:
600 participants in 1 patient group
Loading...
Central trial contact
Farihin Rahman, B.Sc; Taufiq Hasan, PhD
Data sourced from clinicaltrials.gov
Clinical trials
Research sites
Resources
Legal