Systematic Review and Meta-Analysis of Aortic Dissection Diagnosis via CT: Evaluating Deep Learning for Detection Against Expert Analysis and Its Application in Detection and Segmentation

Abstract

Main outcome(s)The primary outcomes will include diagnostic accuracy metrics: sensitivity, specificity, dice score. Quality assessment / Risk of bias analysisFor the quality assessment and risk of bias analysis of primary studies included in this systematic review and meta-analysis, we will employ two wellrecognized tools: the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) and the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Strategy of data synthesisA narrative synthesis will provide an overview of the findings.Where appropriate, meta-analytic techniques will be used to combine results from multiple studies, employing random-effects models to account for between-study heterogeneity.Subgroup analysis Geographic region, validation method, imaging dimensionality, and algorithm type. Sensitivity analysisLeave one out method.Country(ies) involved Taiwan.

Ähnliche Arbeiten