Is the Computer-Aided Detection Scheme for Lung Nodule Also Useful in Detecting Lung Cancer?

Abstract

To evaluate the impact of a computer-aided diagnosis (CAD) system on the performance of observers for the detection of both lung nodules and lung cancers. One hundred fifty computed tomographic scans were evaluated. Database included 23 lung cancers (long diameter <20 mm), nodules stable for at least 2 years, and normal cases. Five chest radiologists and 5 radiology residents each independently recorded the locus of each nodule candidate and assigned a confidence score for the likelihood of nodule and malignancy without CAD; then, the interpretation was repeated with the use of CAD. A consensus panel of 2 chest radiologists served as a reference standard for the nodules. Histological confirmation was a reference standard for the cancers. The performances of the observers for the detection of nodules and cancer with and without CAD were compared using jackknife free-response receiver operating characteristic analysis. The performance of detecting lung nodules was increased significantly with CAD for all radiologists and subgroups (P < 0.01). Although the overall performance of detecting lung cancers was not affected significantly with the use of CAD (P > 0.05), 4 lung cancers missed by 3 residents on their initial observation were additionally detected with CAD. Eighteen of 23 lung cancers were detected by CAD itself. The overall radiologists' performance of detecting lung nodules was improved significantly with the use of CAD, whereas no statistical significance was observed for the detection of lung cancers. The use of CAD, however, contributed to the detection of additional lung cancers for less experienced readers.