RESUMO
Background: The influence of computed tomography (CT) slice thickness on the accuracy of deep learning (DL)-based, automatic coronary artery calcium (CAC) scoring software has not been explored yet. Methods: This retrospective study included 844 subjects (477 men, mean age of 58.9±10.7 years) who underwent electrocardiogram (ECG)-gated CAC scoring CT scans with 1.5 and 3 mm slice thickness values between September 2013 and October 2020. Automatic CAC scoring was performed using DL-based software (3D patch-based U-Net architectures). Manual CAC scoring was set as the reference standard. The reliability of automatic CAC scoring was evaluated using intraclass correlation coefficients (ICCs) for both the 1.5 and 3 mm datasets. The agreement of CAC severity categories [Agatston score (AS) 0, 1-100, 101-400, >400] between automatic CAC scoring and the reference standard was analyzed using weighted kappa (κ) statistics for both 1.5 and 3 mm datasets. Results: The CAC scoring agreement between the automatic CAC scoring and reference standard was excellent (ICC 0.982 for 1.5 mm, 0.969 for 3 mm, respectively). The categorical agreement of CAC severity between two methods was excellent for both 1.5 and 3 mm scans, with better agreement for 3 mm scans (weighted κ: 0.851 and 0.961, 95% confidence intervals: 0.823-0.879 and 0.945-0.974, respectively). Conclusions: Automatic CAC scoring shows excellent agreement with the reference standard for both 1.5 and 3 mm scans but results in lower agreement in the CAC severity category for 1.5 mm scans.
RESUMO
BACKGROUND: Tunnel misplacement is a common cause of failed anterior cruciate ligament (ACL) reconstruction. In this study, the accuracy of the femoral tunnel position was evaluated in robot-assisted ACL reconstruction using a magnetic resonance imaging (MRI)-based navigation system. We hypothesized that a difference of less than 2 mm between the planned femoral tunnel position and the created one was achievable. METHODS: Four cadaveric knees underwent robot-assisted ACL reconstruction. A 3-dimensional model using pre-operative MRI images was used for preoperative planning, and a computed tomography (CT) scan was performed postoperatively. The planned and the created femoral tunnels were compared to assess the accuracy of the femoral tunnel position. RESULTS: The distance between the intra-articular points of the planned and the created tunnels was 7.78 mm in the first experiment and 1.47 mm in the last one. The difference in tunnel length was 4.62 mm in the first experiment and 0.99 mm in the last one. CONCLUSIONS: Accuracy of the femoral tunnel position improved with each robot-assisted ACL reconstruction using an MRI-based navigation system. In the last experiment, the accuracy of the femoral tunnel position was satisfactory.
