Fully Automated Measurement of the Insall-Salvati Ratio with Artificial Intelligence.

Patella alta (PA) and patella baja (PB) affect 1-2% of the world population, but are often underreported, leading to potential complications like osteoarthritis. The Insall-Salvati ratio (ISR) is commonly used to diagnose patellar height abnormalities. Artificial intelligence (AI) keypoint models show promising accuracy in measuring and detecting these abnormalities.An AI keypoint model is developed and validated to study the Insall-Salvati ratio on a random population sample of lateral knee radiographs. A keypoint model was trained and internally validated with 689 lateral knee radiographs from five sites in a multi-hospital urban healthcare system after IRB approval. A total of 116 lateral knee radiographs from a sixth site were used for external validation. Distance error (mm), Pearson correlation, and Bland-Altman plots were used to evaluate model performance. On a random sample of 2647 different lateral knee radiographs, mean and standard deviation were used to calculate the normal distribution of ISR. A keypoint detection model had mean distance error of 2.57 ± 2.44 mm on internal validation data and 2.73 ± 2.86 mm on external validation data. Pearson correlation between labeled and predicted Insall-Salvati ratios was 0.82 [95% CI 0.76-0.86] on internal validation and 0.75 [0.66-0.82] on external validation. For the population sample of 2647 patients, there was mean ISR of 1.11 ± 0.21. Patellar height abnormalities were underreported in radiology reports from the population sample. AI keypoint models consistently measure ISR on knee radiographs. Future models can enable radiologists to study musculoskeletal measurements on larger population samples and enhance our understanding of normal and abnormal ranges.

Dynamic MR imaging analysis of instability in the injured Lisfranc joint with an MRI-compatible foot stressor device.

PURPOSE: To evaluate the applicability of an MRI-compatible foot stressor device in patients with image-proven or clinically suspected Lisfranc joint injuries. METHOD: This prospective study evaluated Lisfranc joint injury by utilizing a joint-specific, stress device that was engineered to replicate weightbearing and physical examination maneuvers. Sixteen patients with either clinically suspected or image-proven Lisfranc joint injuries were recruited from September 2018 to November 2019 (9 men, 7 women; mean age, 39.3 years; age range, 14-68 years). Resting and stressed MR sequences of the injured and non-injured feet were obtained. Measured values for Lisfranc interval widths, dorsal tarsometatarsal subluxations, and lambda-angles were subtracted between the stressed and resting images to calculate net stress-induced changes. A graded injury schema was used to measure significance. RESULTS: The foot stressor device reliably generated stress-induced changes in the Lisfranc joint during dynamic MRI examination. All morphologically abnormal ligaments on resting images demonstrated stress-induced changes, whereas all morphologically normal ligaments lacked evidence of instability. More severely injured Lisfranc ligaments allowed greater Lisfranc joint widening (IOL, p < 0.001; PCL, p < 0.001; DCL, p < 0.001). More highly graded DCL injuries allowed greater dorsal TMT subluxation when present (p < 0.001). Angular gain in the midfoot (lambda-angle) correlated with the graded IOL score (p < 0.001). Acute-to-subacute injuries demonstrated greater inducible changes than chronic injuries (p = 0.047). Seven patients underwent surgery and nine patients received physical therapy. CONCLUSIONS: Stress-induced changes in the midfoot provided information on the degree of ligament pathology and associated joint instability in Lisfranc joint injuries.

Hand ultrasound for osteoporosis screening in postmenopausal women.

There is a need for low-cost screening methods to detect low bone mass (osteopenia or osteoporosis) in postmenopausal women. The utility of quantitative ultrasonography (QUS) of the hand was assessed for osteoporosis screening using the WHO criteria. Bone mineral density (BMD) was measured in 206 postmenopausal Mexican-American women at the total hip and lumbar spine by dual-energy X-ray absorptiometry (DXA). The amplitude-dependent speed of sound (AD-SoS) was measured in the phalanges by QUS. Subjects identified by DXA as having osteopenia or osteoporosis had significantly lower AD-SoS values in comparison with normals. Estrogen users had significantly higher spine and hip BMD and AD-SoS values compared with non-estrogen users. The areas under the receiver operating characteristic (ROC) curves (AUC) for AD-SoS to screen for osteoporosis (T-score < or = -2.5) at the spine or hip were 0.73 for all subjects, 0.74 for estrogen users and 0.68 for non-estrogen users. The AUC for non-estrogen users to screen for osteopenia (T-score -1 to -2.5) was 0.77. Performance comparisons of AD-SoS with SCORE (a risk factor questionnaire) and body weight showed AUC values of 0.73, 0.69 and 0.65, respectively. QUS was the superior screening test when considering both the AUC and the shape of the ROC curves. For non-estrogen users, the group at higher risk for osteoporosis, QUS correctly identified 31% as normal, and 62% as having low bone mass and needing DXA referral; and the remaining 7% were false negatives. These data suggest phalangeal QUS can be effectively used for screening osteoporosis in postmenopausal women.