Objective: To correlate the thickness of the axillary recess capsule measured by ultrasound with magnetic resonance imaging signs of adhesive capsulitis in patients with shoulder pain. Materials and methods: We prospectively evaluated 193 consecutive patients (141 women and 52 men, aged 40–69 years) with shoulder pain lasting 1–9 months from January 2015 to December 2016 who underwent shoulder ultrasound. All participants had routine shoulder ultrasound with additional measurement of axillary recess capsule thickness. After examinations, two groups were formed: negative ultrasound group, composed of patients with a capsule thickness of 2.0 mm or less, and positive ultrasound group, composed of individuals with a capsule thickness greater than 2.0 mm. All patients from the positive ultrasound group and 27 randomly chosen patients from the negative ultrasound group underwent shoulder magnetic resonance imaging. Results: In all, 169/193 patients (88%) had an axillary recess capsule thickness of 2.0 mm or less (negative ultrasound group) and 24/193 patients (12%) had a capsule thickness greater than 2.0 mm (positive ultrasound group). Twenty-seven patients from negative ultrasound group (27/169) were randomly selected to undergo shoulder magnetic resonance imaging. None of them had magnetic resonance imaging criteria for adhesive capsulitis. All patients from positive ultrasound group (24/24) underwent shoulder magnetic resonance imaging and 23 of them (23/24) had magnetic resonance imaging signs of adhesive capsulitis, with a sensitivity of 100% and a specificity of 96%. Conclusion: In patients with shoulder pain, a thickness greater than 2.0 mm of the axillary recess capsule measured by ultrasound correlates to magnetic resonance imaging signs of adhesive capsulitis with good sensitivity and specificity.
Objective: To describe the accuracy of HealthVCF, a software product that uses artificial intelligence, in the detection of incidental moderate-to-severe vertebral compression fractures (VCFs) on chest and abdominal computed tomography scans. Materials and Methods: We included a consecutive sample of 899 chest and abdominal computed tomography scans of patients 51–99 years of age. Scans were retrospectively evaluated by the software and by two specialists in musculoskeletal imaging for the presence of VCFs with vertebral body height loss > 25%. We compared the software analysis with that of a general radiologist, using the evaluation of the two specialists as the reference. Results: The software showed a diagnostic accuracy of 89.6% (95% CI: 87.4–91.5%) for moderate-to-severe VCFs, with a sensitivity of 73.8%, a specificity of 92.7%, and a negative predictive value of 94.8%. Among the 145 positive scans detected by the software, the general radiologist failed to report the fractures in 62 (42.8%), and the algorithm detected additional fractures in 38 of those scans. Conclusion: The software has good accuracy for the detection of moderate-to-severe VCFs, with high specificity, and can increase the opportunistic detection rate of VCFs by radiologists who do not specialize in musculoskeletal imaging.