Detection of the usual interstitial pneumonia pattern in chest CT: effect of computer-aided diagnosis on radiologist diagnostic performance.

Abstract

Anti-fibrotic drugs for interstitial pulmonary fibrosis (IPF) have been developed. Physicians are becoming increasingly aware of the need for better diagnosis of IPF. To evaluate whether a computer-aided system can improve the diagnostic performance of general radiologists in detecting the usual interstitial pneumonia (UIP) pattern on computed tomography (CT). We included 60 CT datasets from 30 patients with IPF and 30 with idiopathic fibrosing non-specific interstitial pneumonia (fNSIP), all diagnosed by a multidisciplinary diagnosis (MDD) procedure that included surgical biopsy. We analyzed the CT data using a computer-aided system (Gaussian histogram normalized correlation: GHNC). Five general radiologists with <6 years of experience each interpreted these CT scans with and without the GHNC results. We compared the likelihoods of a UIP-pattern diagnosis with the likelihood of the same diagnosis by MDD using the average area under the curve (AUC) of the receiver operating characteristics (ROC). We also evaluated the association between the radiologists' diagnosis and survival using the Kaplan-Meier method. In the ROC analysis, the AUC increased significantly from 0.731 without GHNC to 0.829 with GHNC (P = 0.0396). The diagnosis without GHNC was not significantly associated with survival for any radiologist, but the UIP diagnosis with GHNC was significantly associated with a worse prognosis for four out of five radiologists. The computer-aided system could increase the confidence level of UIP-pattern diagnosis by non-expert radiologists.