Citations

To evaluate deep learning-based calcium segmentation and quantification on ECG-gated cardiac CT scans compared with manual evaluation. Automated calcium quantification was performed using a neural network based on mask regions with convolutional neural networks (R-CNNs) for multi-organ segmentation. Manual evaluation of calcium was carried out using proprietary software. This is a retrospective study of archived data. This study used 40 patients to train the segmentation model and 110 patients were used for the validation of the algorithm. The Pearson correlation coefficient between the reference actual and the computed predictive scores shows high level of correlation (0.84; P < .001) and high limits of agreement (±1.96 SD; −2000, 2000) in Bland–Altman plot analysis. The proposed method correctly classifies the risk group in 75.2% and classifies the subjects in the same group. In total, 81% of the predictive scores lie in the same categories and only seven patients out of 110 were more than one category off. For the presence/absence of coronary artery calcifications, the deep learning model achieved a sensitivity of 90% and a specificity of 94%. Fully automated model shows good correlation compared with reference standards. Automating process reduces evaluation time and optimizes clinical calcium scoring without additional resources.

Abstract Background Adalimumab is a fully human monoclonal antibody developed against tumor necrosis factor (TNF), used for the treatment of autoimmune and chronic inflammatory diseases. Immunogenicity to this drug may lead to therapeutic failure. Various laboratory assays are used for measuring serum adalimumab and anti-drug antibodies (ADA) to adalimumab, for therapeutic monitoring and evaluation of clinical non-responsiveness. This study compared the performance of 2 clinical assays used by different reference laboratories. Methods In total, 120 residual clinical samples were tested at both laboratories. A sandwich ELISA for adalimumab detecting free drug and a bridging ELISA capable of detecting both free and bound ADA were performed at the Mayo Clinic. A functional cell-based reporter gene assay (RGA) was used at ARUP Laboratories for measuring bioactive serum drug concentrations, and neutralizing ADA. Results Seventy-eight samples had measurable concentrations of adalimumab by both methods and yielded a correlation coefficient r = 0.93, slope = 0.886, and intercept = 0.950. Overall agreement of 92.5% was observed between the assays, with most discrepant drug results being attributed to a higher positivity rate with ELISA (8/9). One outlier positive with RGA and negative with ELISA was confirmed by LC-MS/MS to be attributed to infliximab. Overall agreement of 79.2% was observed between the ADA assays. Differences in ADA results may be due to the bridging ELISA detecting total ADA (free, drug-bound, neutralizing, and non-neutralizing), while RGA detects free, neutralizing ADA only. Conclusions Although the assays are fundamentally different, the results show significant concordance between the clinically validated tests performed in different laboratories.