CT triage for lung malignancy: coronal multiplanar reformation versus images in three orthogonal planes

Background: Generation of multiplanar reformation (MPR) images has become automatic on most modern computed
tomography (CT) scanners, potentially increasing the workload of the reporting radiologists. It is not always clear if this
increases diagnostic performance in all clinical tasks.
Purpose: To assess detection performance using only coronal multiplanar reformations (MPR) when triaging patients for
lung malignancies with CT compared to images in three orthogonal planes, and to evaluate performance comparison of
novice and experienced readers.
Material and Methods: Retrospective study of 63 patients with suspicion of lung cancer, scanned on 64-slice multidetector
computed tomography (MDCT) with images reconstructed in three planes. Coronal images were presented to
four readers, two novice and two experienced. Readers decided whether the patients were suspicious for malignant
disease, and indicated their confidence on a five-point scale. Sensitivity and specificity on per-patient basis was calculated
with regards to a reference standard of histological diagnosis, and compared with the original report using McNemar’s
test. Receiver operating characteristic (ROC) curves were plotted to compare the performance of the four readers,
using the area under the curve (AUC) as figure of merit.
Results: No statistically significant difference of sensitivity and specificity was found for any of the readers when
compared to the original reports. ROC analysis yielded AUCs in the range of 0.92–0.93 for all readers with no significant
difference. Inter-rater agreement was substantial (kappa¼0.72).
Conclusion: Sensitivity and specificity were comparable to diagnosis using images in three planes. No significant
difference was found between experienced and novice readers.