Interobserver variability, and visual and quantitative parameters of 123I-FP-CIT SPECT (DaTSCAN) studies

To evaluate the degree of interobserver agreement in the visual interpretation of I-123-FP-CIT studies and to investigate for potential associations between visual and semi-quantitative parameters. Eighty-nine I-123-FP-CIT studies were blindly reviewed by 3 independent observers: a consultant, a resident doctor and a radiographer. They classified every study as either "normal" or "abnormal" and assigned visual I-123-FP-CIT uptake scores (2: normal, 1: reduced and 0: no uptake) in basal ganglia nuclei (right and left putamina and caudate nuclei) on every scan. Striatal I-123-FP-CIT binding ratios were calculated using crescent-ROI software. The interobserver agreement for the interpretation of studies and for visual score assignment was evaluated by means of kappa statistics. We investigated for associations of binding ratios with visual scores and clinical parameters; patients' clinical diagnoses served as the reference standard. There was excellent interobserver agreement (kappa 0.89-0.93) in classifying studies as "normal" or "abnormal" and fine agreement in assignment of visual scores (kappa 0.71-0.80 for putamina and 0.50-0.79 for caudate nuclei). Nuclei with scores of 1 and 0 showed significantly reduced binding ratios (about 30 and 50%, respectively) compared with the nuclei scored as 2. ROC analysis indicated the optimal cutoff point of striatal binding ratio at 3.8 (sensitivity 98.5%, specificity 95%) for the detection of parkinsonian syndromes. Striatal binding ratios were negatively associated with age in normal subjects and disease duration in Parkinson's disease patients. Visual interpretation of I-123-FP-CIT studies showed very good interobserver agreement. We found significant associations among visual, semi-quantitative and clinical parameters.