Background Delay of as much as 5 months between ACL injury and surgery is known to be associated with increased risk of a medial meniscal tear, but the risk of additional meniscal tear progression with a longer delay to surgery is unclear. Questions/purposes We determined the (1) times of injury, MRI, and surgery in adolescents with ACL tears, and whether (2) timing of surgery, or (3) initial integrity of the meniscus seen on MR images predicted development of meniscal tears. Methods We reviewed 112 adolescents who were 15 ± 1 years old (mean ± SD) (range, 11-16 years) with a torn ACL. These patients underwent surgical repair from 2005 to 2011 in a Canadian city. We compared dates of injury, MRI, and surgery. A pediatric and musculoskeletal fellowship-trained radiologist reread the MR images, and meniscal injuries were graded according to severity. This was compared with surgical findings described in the operative report. Results Time after injury to MRI and surgery averaged 77 days (range, 1-377 days) and 342 days (range, 42-1637 days), respectively. Patients with new or worsened medial meniscal tears had waited longer for surgery (445 versus 290 days; p = 0.002). Bucket handle medial meniscal tears were more common in patients with surgery more than 1 year after injury than others (15 of 34 versus 14 of 75; p = 0.013). A medial meniscal tear observed on MR images was a significant covariate for a torn meniscus at surgery (relative risk, 5.7; 95% CI, 2.8-11.6). Medial meniscal survival continued to decline sharply greater than 1 year after injury. Conclusions Medial meniscal tears, especially bucket handle tears, increased steadily in frequency more than 1 year after ACL injury. Timely ACL reconstruction may be warranted to reduce the risk of further medial meniscal damage even in patients whose original injury occurred more than 1 year before. Level of Evidence Level IV, prognostic study. See the Instructions for Authors for a complete description of levels of evidence.

BACKGROUND: Pulmonary complications, including infections, are highly prevalent in patients after hematopoietic cell transplantation with chronic graft-vs-host disease. These comorbid diseases can make the diagnosis of early lung graft-vs-host disease (bronchiolitis obliterans syndrome) challenging. A quantitative method to differentiate among these pulmonary diseases can address diagnostic challenges and facilitate earlier and more targeted therapy. STUDY DESIGN AND METHODS:We conducted a single-center study of 66 patients with CT chest scans analyzed with a quantitative imaging tool known as parametric response mapping. Parametric response mapping results were correlated with pulmonary function tests and clinical characteristics. Five parametric response mapping metrics were applied to K-means clustering and support vector machine models to distinguish among posttransplantation lung complications solely from quantitative output.RESULTS: Compared with parametric response mapping, spirometry showed a moderate correlation with radiographic air trapping, and total lung capacity and residual volume showed a strong correlation with radiographic lung volumes. K-means clustering analysis distinguished four unique clusters. Clusters 2 and 3 represented obstructive physiology (encompassing 81% of patients with bronchiolitis obliterans syndrome) in increasing severity (percentage air trapping 15.6% and 43.0%, respectively). Cluster 1 was dominated by normal lung, and cluster 4 was characterized by patients with parenchymal opacities. A support vector machine algorithm differentiated bronchiolitis obliterans syndrome with a specificity of 88%, sensitivity of 83%, accuracy of 86%, and an area under the receiver operating characteristic curve of 0.85. INTERPRETATION:Our machine learning models offer a quantitative approach for the identification of bronchiolitis obliterans syndrome vs other lung diseases, including late pulmonary complications after hematopoietic cell transplantation.

ObjectiveMagnetic resonance imaging (MRI) findings in anterior cruciate ligament (ACL) injury are well known, but most published reviews show obvious examples of associated injuries and give little focus to paediatric patients. Here, we demonstrate the spectrum of MRI appearances at common sites of associated injury in adolescents with ACL tears, emphasising age-specific issues.MethodsPictorial review using images from children with surgically confirmed ACL tears after athletic injury.ResultsACL injury usually occurs with axial rotation in the valgus near full extension. The MRI findings can be obvious and important to management (ACL rupture), subtle but clinically important (lateral meniscus posterior attachment avulsion), obvious and unimportant to management (femoral condyle impaction injury), or subtle and possibly important (medial meniscocapsular junction tear). Paediatric-specific issues of note include tibial spine avulsion, normal difficulty visualising a thin ACL and posterolateral corner structures, and differentiation between incompletely closed physis and impaction fracture.ConclusionACL tear is only the most obvious sign of a complex injury involving multiple structures. Awareness of the spectrum of secondary findings illustrated here and the features distinguishing them from normal variation can aid in accurate assessment of ACL tears and related injuries, enabling effective treatment planning and assessment of prognosis.Teaching points• The ACL in children normally appears thin or attenuated, while thickening and oedema suggest tear.• Displaced medial meniscal tears are significantly more common later post-injury than immediately.• The meniscofemoral ligaments merge with the posterior lateral meniscus, complicating tear assessment.• Tibial plateau impaction fractures can be difficult to distinguish from a partially closed physis.• Axial MR sequences are more sensitive/specific than coronal for diagnosis of medial collateral ligament (MCL) injury.

To test the performance of a deep learning (DL) model in predicting atrial fibrillation (AF) at routine nongated chest CT. Materials and Methods:A retrospective derivation cohort (mean age, 64 years; 51% female) consisting of 500 consecutive patients who underwent routine chest CT served as the training set for a DL model that was used to measure left atrial volume. The model was then used to measure atrial size for a separate 500-patient validation cohort (mean age, 61 years; 46% female), in which the AF status was determined by performing a chart review. The performance of automated atrial size as a predictor of AF was evaluated by using a receiver operating characteristic analysis.Results: There was good agreement between manual and model-generated segmentation maps by all measures of overlap and surface distance (mean Dice = 0.87, intersection over union = 0.77, Hausdorff distance = 4.36 mm, average symmetric surface distance = 0.96 mm), and agreement was slightly but significantly greater than that between human observers (mean Dice = 0.85 [automated] vs 0.84 [manual]; P = .004). Atrial volume was a good predictor of AF in the validation cohort (area under the receiver operating characteristic curve = 0.768) and was an independent predictor of AF, with an age-adjusted relative risk of 2.9. Conclusion:Left atrial volume is an independent predictor of the AF status as measured at routine nongated chest CT. Deep learning is a suitable tool for automated measurement.