Abstract
BACKGROUND: For ((123)I)FP-CIT imaging, a number of algorithms have shown high performance in distinguishing normal patient images from those with disease, but none have yet been tested as part of reporting workflows. This study aims to evaluate the impact on reporters' performance of a computer-aided diagnosis (CADx) tool developed from established machine learning technology. Three experienced ((123)I)FP-CIT reporters (two radiologists and one clinical scientist) were asked to visually score 155 reconstructed clinical and research images on a 5-point diagnostic confidence scale (read 1). Once completed, the process was then repeated (read 2). Immediately after submitting each image score for a second time, the CADx system output was displayed to reporters alongside the image data. With this information available, the reporters submitted a score for the third time (read 3). Comparisons between reads 1 and 2 provided evidence of intra-operator reliability, and differences between reads 2 and 3 showed the impact of the CADx. RESULTS: The performance of all reporters demonstrated a degree of variability when analysing images through visual analysis alone. However, inclusion of CADx improved consistency between reporters, for both clinical and research data. The introduction of CADx increased the accuracy of the radiologists when reporting (unfamiliar) research images but had less impact on the clinical scientist and caused no significant change in accuracy for the clinical data. CONCLUSIONS: The outcomes for this study indicate the value of CADx as a diagnostic aid in the clinic and encourage future development for more refined incorporation into clinical practice.