Correlative Assessment of Machine Learning-Based Cobb Angle Measurements and Human-Based Measurements in Adolescent Idiopathic and Congenital Scoliosis.

Purpose: Scoliosis is a complex spine deformity with direct functional and cosmetic impacts on the individual. The reference standard for assessing scoliosis severity is the Cobb angle which is measured on radiographs by human specialists, carrying interobserver variability and inaccuracy of measurements. These limitations may result in lack of timely referral for management at a time the scoliotic deformity progression can be saved from surgery. We aimed to create a machine learning (ML) model for automatic calculation of Cobb angles on 3-foot standing spine radiographs of children and adolescents with clinical suspicion of scoliosis across 2 clinical scenarios (idiopathic, group 1 and congenital scoliosis, group 2). Methods: We retrospectively measured Cobb angles of 130 patients who had a 3-foot spine radiograph for scoliosis within a 10-year period for either idiopathic or congenital anomaly scoliosis. Cobb angles were measured both manually by radiologists and by an ML pipeline (segmentation-based approach-Augmented U-Net model with non-square kernels). Results: Our Augmented U-Net architecture achieved a Symmetric Mean Absolute Percentage Error (SMAPE) of 11.82% amongst a combined idiopathic and congenital scoliosis cohort. When stratifying for idiopathic and congenital scoliosis individually a SMAPE of 13.02% and 11.90% were achieved, respectively. Conclusion: The ML model used in this study is promising at providing automated Cobb angle measurement in both idiopathic scoliosis and congenital scoliosis. Nevertheless, larger studies are needed in the future to confirm the results of this study prior to translation of this ML algorithm into clinical practice.

Comparison of roentgenographic manifestations of active pulmonary tuberculosis between migrant and non-migrant populations in the Hunter Region.

INTRODUCTION: Active pulmonary tuberculosis in Australia is considered more common in migrants and the immunocompromised, but little data exist on how it manifests in non-migrants. This study identified the radiographic findings of active pulmonary tuberculosis in the Hunter Region, NSW, Australia, and determined whether this manifests differently in non-migrant and migrant populations. METHODS: We retrospectively analysed 64 patients over 8 years from the Hunter Region, who had positive Mycobacterium tuberculosis cultures and contemporaneous thoracic imaging. Recorded data included age, gender, country of origin and chest radiographic findings, the latter categorised into apical fibrocavitatory disease, mixed apical fibrocavitation and consolidation, consolidation, lymphadenopathy, pleural effusions, tree-in-bud, empyema and miliary nodules. RESULTS: Sixty-four patients (men = 37, women = 27) had available thoracic imaging, of which 34 were Australian born. There was no statistically significant difference in the age between Australian-born and migrants (49.1 years (95% confidence interval, CI 42.8-55.5) vs 48.2 years (95% CI 41.1-55.3), P = 0.71). The most common radiographic manifestations were purely apical fibrocavitatory lesions (22%), mixed apical fibrocavitation and consolidation (6%) and purely consolidation (27%). Migrants were more likely to have consolidation (40%), while Australian-born individuals were more likely to have apical fibrocavitatory lesions (26%). Australian-born individuals were slightly more likely to have a normal chest radiograph (18% vs 10%). CONCLUSION: There are radiographic differences between Australian-born and migrant populations with active pulmonary tuberculosis. Migrants are more likely to present with consolidation, and Australian-born with fibrocavitatory lesions. A normal chest radiograph does not exclude active tuberculosis, and while thoracic computed tomography may be useful to detect tree-in-bud opacities, neither should not detract from commencing treatment of a positive culture for tuberculosis.