AI Model for Bone Mineral Density Prediction From X-Ray Images

NCT06652061 | Recruiting

• 2 other identifiers: ISMC/EC/2024/012S2024-01-008
• Study Type: observational
• Target: 600
• Locations: 1 country
• Sites: 1

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.

Conditions

Osteoporosis

Keywords

Osteoporosis; Bone Mineral Density; AI; Radiography; Deep Learning; Hip and Spine X-Rays

Outcome Measures

Primary Outcomes (1)

• Bone Mineral Density (BMD) - Hip and Spinal (L1-L4)

  Measurement of bone mineral density in the hip and spinal regions (L1-L4) as an indicator for assessing bone strength. The BMD values will be used as key metrics to train the AI model for predicting osteoporosis risk from x-ray data.

  Day 1

Secondary Outcomes (2)

• WHO Classification (Normal, Low Bone Mass, Osteoporosis)

  Through study completion, an average of 6 months

• Fracture risk assessment

  Through study completion, an average of 6 months

Study Arms (1)

Patients presenting for DEXA scan

The study group consists of patients presenting for Bone Mineral Density (BMD) testing using DEXA scans in the Radiology Department, as well as those with available spine and hip X-ray images. This group includes individuals with suspected osteoporosis referred for a BMD test by an attending orthopedic specialist, along with patients undergoing routine testing. The group encompasses a diverse demographic, including males, premenopausal women, and postmenopausal women across various age groups. This diversity enables the evaluation of the AI model across a broad range of conditions and patient backgrounds, enhancing its generalizability and clinical utility.

Diagnostic Test: Dual Energy X-Ray Absorptiometry Scan (DEXA Scan); Diagnostic Test: X-Ray (Hip and Spine)

Interventions

Dual Energy X-Ray Absorptiometry Scan (DEXA Scan) DIAGNOSTIC_TEST

A DEXA scan, or Dual-Energy X-ray Absorptiometry, is a specialized imaging technique used to measure Bone Mineral Density (BMD). It is commonly employed to diagnose osteoporosis and assess the risk of fractures, especially in areas prone to bone density loss, such as the spine, hip, and forearm. The scan works by using two low-energy X-ray beams that pass through the bone, allowing it to differentiate between bone and soft tissue and calculate the bone's density. DEXA is considered the gold standard for osteoporosis diagnosis due to its high accuracy and precision. The DEXA scan is a non-invasive, out-patient and painless procedure. Patients lie on an examination table while the scanner passes over the targeted area, typically the hip and spine. The entire procedure is straightforward, taking around 10 to 30 minutes depending on the areas being scanned.

Also known as: BMD Test

Patients presenting for DEXA scan

X-Ray (Hip and Spine) DIAGNOSTIC_TEST

Hip and spine X-rays are specific types of radiographic imaging used primarily to evaluate bone health, joint integrity, and alignment in these crucial areas. In the context of osteoporosis assessment, hip and spine X-rays can reveal signs of bone thinning or fractures, serving as an initial screening tool before more detailed imaging like a DEXA scan. During a hip X-ray, the patient typically lies on an examination table with the hip positioned for a clear view of the pelvis and femur. In a spine X-ray, the patient's posture may vary, often lying on the table in either a supine or lateral position to capture views of the vertebrae in the lower back (lumbar spine). Patients may be asked to remain very still, or even hold their breath momentarily, to prevent motion blur, which can obscure important details. Both hip and spine X-rays are quick and painless, generally taking only a few minutes, with the X-ray exposure itself lasting less than a second.

Patients presenting for DEXA scan

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population comprises individuals presenting for DEXA scans at the Ibn Sina Diagnostic Centre in Uttara. These patients are either referred by orthopaedic specialists and radiologists due to orthopaedic issues, such as back pain, or are attending routine check-ups, particularly postmenopausal women or individuals with other risk factors. The study includes subjects with varying bone densities, as measured by DEXA scans, which serve as the gold standard for Bone Mineral Density (BMD) assessment. Participants will include adults aged 18 and above, of any gender, with available X-ray imaging of relevant skeletal sites, such as the spine and hip. They are required to provide informed consent for the use of their X-ray images and clinical data in the study. Additionally, participants must have both X-ray and DEXA scan results, along with supplementary medical records when available.

You may qualify if:

• 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.

You may not qualify if:

• 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 women, given the potential impact on screening results and the need for special considerations during pregnancy.
• Patients with implant in hip or spine

Sponsors & Collaborators

• Bangladesh University of Engineering and Technology: lead
• Ibn Sina Hospital: collaborator

Study Sites (1)

Ibn Sina Diagnostic Centre, Uttara

Dhaka, 1230, Bangladesh

RECRUITING

MeSH Terms

Conditions

Osteoporosis

Interventions

Absorptiometry, Photon; X-Rays

Condition Hierarchy (Ancestors)

Bone Diseases, Metabolic; Bone Diseases; Musculoskeletal Diseases; Metabolic Diseases; Nutritional and Metabolic Diseases

Intervention Hierarchy (Ancestors)

Radiography; Diagnostic Imaging; Diagnostic Techniques and Procedures; Diagnosis; Densitometry; Photometry; Chemistry Techniques, Analytical; Investigative Techniques; Electromagnetic Radiation; Electromagnetic Phenomena; Magnetic Phenomena; Physical Phenomena; Radiation; Radiation, Ionizing

Study Officials

• Taufiq Hasan, PhD

  Department of Biomedical Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka - 1205.

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Taufiq Hasan, PhD

CONTACT

+8801817579844; taufiq@bme.buet.ac.bd

Farihin Rahman, B.Sc

CONTACT

+8801315091686; farihinrahman34@gmail.com

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor

Study Record Dates

• First Submitted: October 16, 2024
• First Posted: October 22, 2024
• Study Start: September 12, 2024
• Primary Completion: March 12, 2025
• Study Completion: March 12, 2025
• Last Updated: October 22, 2024

Record last verified: 2024-10

Locations

BA (1)