Opportunistic assessment of osteoporosis using hip and pelvic X-rays with OsteoSight™: validation of an AI-based tool in a US population

Identifying patients at risk of low bone mineral density (BMD) from X-rays presents an attractive approach to increase case finding. This paper showed the diagnostic accuracy, reproducibility, and robustness of a new technology: OsteoSight™. OsteoSight could increase diagnosis and preventive treatment rates for patients with low BMD.

PURPOSE

This study aimed to evaluate the diagnostic accuracy, reproducibility, and robustness of OsteoSight™, an automated image analysis tool designed to identify low bone mineral density (BMD) from routine hip and pelvic X-rays. Given the global rise in osteoporosis-related fractures and the limitations of current diagnostic paradigms, OsteoSight offers a scalable solution that integrates into existing clinical workflows.

METHODS

Performance of the technology was tested across three key areas: (1) diagnostic accuracy in identifying low BMD as compared to dual-energy X-ray absorptiometry (DXA), the clinical gold standard; (2) reproducibility, through analysis of two images from the same patient; and (3) robustness, by evaluating the tool's performance across different patient demographics and X-ray scanner hardware.

RESULTS

The diagnostic accuracy of OsteoSight for identifying patients at risk of low BMD was area under the receiver operating characteristic curve (AUROC) 0.834 [0.789-0.880], with consistent results across subgroups of clinical confounders and X-ray scanner hardware. Specificity 0.852 [0.783-0.930] and sensitivity 0.628 [0.538-0.743] met pre-specified acceptance criteria. The pre-processing pipeline successfully excluded unsuitable cases including incorrect body parts, metalwork, and unacceptable femur positioning.

CONCLUSION

The results demonstrate that OsteoSight is accurate in identifying patients with low BMD. This suggests its utility as an opportunistic assessment tool, especially in settings where DXA accessibility is limited or not recently performed. The tool's reproducibility and robust performance across various clinical confounders further supports its integration into routine orthopedic and medical practices, potentially broadening the reach of osteoporosis assessment and enabling earlier intervention for at-risk patients.

Musculoskeletal Radiology Education: A National Survey by the Italian College of Musculoskeletal Radiology

BACKGROUND

Our aim was to understand how musculoskeletal training is structured in Italian residency programmes and the needs of young trainees.

METHODS

We sent out an online questionnaire (17 questions) to Italian Society of Radiology residents and board-certified radiologists aged up to 39 years.

RESULTS

A total of 1144 out of 4210 (27.2%) members participated in the survey; 64.7% were residents and 35.3% were board-certified radiologists. Just 26.6% of participants had dedicated rotations for musculoskeletal training during their residency, although this percentage substantially increased in replies from northern Italy. One-fourth of residents had a scheduled period of musculoskeletal ultrasound. Most participants (76.3%) had <20 h per year of musculoskeletal lessons. The majority considered their musculoskeletal education poor (57.7%) or average (21.9%). According to 84.8% of replies, no dedicated training period about interventional musculoskeletal procedures was scheduled. Further, just 12.8% of residents took active part in such interventions. Nearly all participants believed that the musculoskeletal programme during residency needs to be improved, particularly concerning practices in ultrasound (92.8%), MRI cases interpretation/reporting (78.9%), and practice in ultrasound-guided interventional procedures (64.3%).

CONCLUSIONS

Despite some differences in the structure of musculoskeletal education provided by different regions, there is a shared demand for improvement in musculoskeletal training.

The promise and limitations of artificial intelligence in musculoskeletal imaging

With the recent developments in deep learning and the rapid growth of convolutional neural networks, artificial intelligence has shown promise as a tool that can transform several aspects of the musculoskeletal imaging cycle. Its applications can involve both interpretive and non-interpretive tasks such as the ordering of imaging, scheduling, protocoling, image acquisition, report generation and communication of findings. However, artificial intelligence tools still face a number of challenges that can hinder effective implementation into clinical practice. The purpose of this review is to explore both the successes and limitations of artificial intelligence applications throughout the muscuskeletal imaging cycle and to highlight how these applications can help enhance the service radiologists deliver to their patients, resulting in increased efficiency as well as improved patient and provider satisfaction.

Artificial Intelligence in Spinal Imaging: Current Status and Future Directions

Spinal maladies are among the most common causes of pain and disability worldwide. Imaging represents an important diagnostic procedure in spinal care. Imaging investigations can provide information and insights that are not visible through ordinary visual inspection. Multiscale in vivo interrogation has the potential to improve the assessment and monitoring of pathologies thanks to the convergence of imaging, artificial intelligence (AI), and radiomic techniques. AI is revolutionizing computer vision, autonomous driving, natural language processing, and speech recognition. These revolutionary technologies are already impacting radiology, diagnostics, and other fields, where automated solutions can increase precision and reproducibility. In the first section of this narrative review, we provide a brief explanation of the many approaches currently being developed, with a particular emphasis on those employed in spinal imaging studies. The previously documented uses of AI for challenges involving spinal imaging, including imaging appropriateness and protocoling, image acquisition and reconstruction, image presentation, image interpretation, and quantitative image analysis, are then detailed. Finally, the future applications of AI to imaging of the spine are discussed. AI has the potential to significantly affect every step in spinal imaging. AI can make images of the spine more useful to patients and doctors by improving image quality, imaging efficiency, and diagnostic accuracy.

Impact of a Musculoskeletal "Mini-Residency" Professional Development Program on Knee Magnetic Resonance Imaging Orders by Primary Care Providers

BACKGROUND

The US Department of Veterans Affairs has created a portfolio of educational programs to train primary care providers (PCPs) in the evaluation and management of common musculoskeletal (MSK) conditions. Appropriate resource utilization for evaluation of knee pain, including limiting unnecessary magnetic resonance imaging (MRI) studies, is an important theme of these initiatives. The objective of this study was to report the utilization of knee MRI by PCP providers before and after the MSK education program and to determine the appropriateness of these MRI orders.

METHODS

Twenty-six PCPs participated in the MSK Mini-Residency educational program held in Salt Lake City between April 2012 and October 2014. Knee MRI orders submitted by these providers 12 months before and 12 months after their participation were reviewed. Magnetic resonance imaging orders were categorized as "inappropriate," "probably inappropriate," or "possibly appropriate," based on accepted guidelines for knee MRI utilization. Differences in the numbers of precourse and postcourse MRI orders for each of these categories were compared using Student t test.

RESULTS

Following our program, MRI orders decreased from 130 (precourse) to 93 (postcourse), a reduction of 28% ( p = 0.04). This reduction was observed entirely within the "inappropriate" and "probably inappropriate" categories; the number of orders categorized as "possibly appropriate" increased, but not significantly.

CONCLUSIONS

The MSK Mini-Residency training program was a successful educational intervention and was associated with a reduction in inappropriate knee MRI utilization for some participants, while keeping appropriate MRI utilization stable.

Implementation of a speech and language therapy-led referring model for videofluoroscopic swallow studies: An evaluation of service outcomes

BACKGROUND

Videofluoroscopic swallow studies (VFSS) are integral to diagnosing and supporting dysphagia management. However, in many countries, only doctors are authorized to complete medical imaging request forms, in accordance with radiation safety regulations. This can impact workflow and timely access to VFSS. Enhanced scope of practice (ESP) models of care exist, where speech and language therapists (SLTs) are authorized to complete VFSS request forms. However, formal evaluations of these ESP models are currently lacking.

AIMS

The primary aim of this study was to examine service outcomes regarding the safety and efficiency of SLTs completing VFSS request forms compared with the medical referring model (standard care). The secondary aim was to ascertain the impacts on SLTs' daily workflow and the utility of training for SLTs to complete VFSS requests.

METHODS & PROCEDURES

The study involved a mixed-method design. First, referrals completed using standard care versus those completed under the new SLT-led VFSS referring model were compared for efficiency (days to request completion, number of contacts between staff to complete requests and delay to VFSS appointments) and safety (compliance with radiation safety standards for requests, adverse events and change to dysphagia management to justify radiation exposure). Semi-structured interviews were then conducted with SLT referrers (n = 7) exploring the impacts of the model on daily workflow and the utility of training.

OUTCOMES & RESULTS

VFSS inpatient requests were examined across a 3-month period (n = 61 requests) using the standard model, and for 6 months (n = 109 requests) following the introduction of SLT-led VFSS referring. Regarding efficiency, there was no significant difference between the two models, with most request forms taking less than or equal to 1 day to be completed. Adherence to radiation safety requirements was significantly greater in the SLT-led VFSS referring model compared with the standard model (p < 0.001) in relation to the overall requisite clinical information being documented on the request forms. No adverse events occurred and 100% of VFSSs led to changed dysphagia management. Interviews of VFSS referring SLTs revealed that completing requests was not complex or onerous, and that the training equipped them well to undertake the role.

CONCLUSIONS & IMPLICATIONS

The SLT-led VFSS referring model was feasible for SLTs and resulted in satisfactory efficiency and greater adherence to radiation safety requirements for VFSS request forms than the standard model. Improved information on VFSS request forms provides clearer justification for the radiation procedure and helps optimize the diagnostic yield of VFSS. The evidence supports further widespread adoption of this model.

WHAT THIS PAPER ADDS

What is already known on the subject Models of care permitting selected allied health professionals to refer patients for diagnostic radiology procedures have been established to achieve healthcare efficiencies. Evidence supports the safety and efficiency of physiotherapists referring to radiology. However, limited published outcome data exist regarding models of SLTs referring for radiology procedures, such as VFSS. What this paper adds to existing knowledge This study describes the implementation of a SLT-led VFSS inpatient referring model in a quaternary hospital and examines service outcomes. The findings reveal that VFSS request forms completed in the SLT-led referring model had greater adherence to radiation safety standards compared with the standard referring model. Efficiency was similar across both models and there were no adverse events. Completing VFSS requests did not disrupt daily workflow for SLTs and training was effective preparation for the role. What are the potential or actual clinical implications of this work? Results demonstrate that the SLT-led VFSS referral model can be safely and appropriately implemented in the inpatient setting. Improved quality of information documented on request forms by SLTs increases adherence with radiation safety standards, providing clearer justification for radiation assessments and potentially eliciting more targeted diagnostic information to inform dysphagia treatment planning. These findings may support other hospital services to establish this type of referring model.

Gender Differences in Modality Interpretation Among Radiologists: An Exploratory Study of Occupational Horizontal Segregation

RATIONALE AND OBJECTIVES

Occupational "horizontal segregation," defined as disparity in the distribution of responsibilities between genders, could discourage women from seeking careers in radiology, as well as impact women within radiology in terms of compensation, promotion, and career advancement. We aimed to explore the existence of horizontal workplace segregation in radiology, as potentially manifested as intergender differences in the distribution of clinical work effort among imaging modalities for radiologists.

MATERIALS AND METHODS

Medicare-participating general radiologists, neuroradiologists, abdominal, cardiothoracic, and musculoskeletal radiologists were identified from the 2016 Medicare Physician and Other Supplier Public Use File. Work effort in radiography, ultrasound, CT, and MRI was stratified by gender. Univariable and multivariable analyses were performed.

RESULTS

22,445 radiologists were included (19.0% female; 19.6% in academic practices). At univariable analysis, female (vs. male) generalists had lower work effort in MRI (10.2% vs. 13.2%) (p < 0.001); abdominal radiologists had higher work effort in ultrasound (27.1% vs. 21.9%), with lower work effort in CT (53.7%. vs. 56.0%) and MRI (8.1%. vs. 9.4%) (p < 0.001); and musculoskeletal radiologists had higher work effort in radiography (41.6% vs. 34.8%) and less in MRI (44.8% vs. 49.6%) (p = 0.007). In multivariable analyses, female gender was independently associated with lower work effort in advanced imaging (CT and MRI) for generalists (coefficient, -0.020; p < 0.001), abdominal radiologists (coefficient, -0.042; p < 0.001), and neuroradiologists (coefficient -0.010; p = 0.035).

CONCLUSION

Horizontal occupational segregation exists in radiology with female radiologists devoting lower work effort to advanced imaging modalities. Further investigation is warranted to better understand the sources and downstream implications of such variation.

Artificial Intelligence in Musculoskeletal Imaging: Current Status and Future Directions

OBJECTIVE. The objective of this article is to show how artificial intelligence (AI) has impacted different components of the imaging value chain thus far as well as to describe its potential future uses. CONCLUSION. The use of AI has the potential to greatly enhance every component of the imaging value chain. From assessing the appropriateness of imaging orders to helping predict patients at risk for fracture, AI can increase the value that musculoskeletal imagers provide to their patients and to referring clinicians by improving image quality, patient centricity, imaging efficiency, and diagnostic accuracy.