• Jason D Balkman, Sonali Mehandru, Elena DuPont, Ronald D Novak, and Robert C Gilkeson.
• Department of Radiology, University Hospitals of Cleveland, 11100 Euclid Avenue, Cleveland, OH 44106-5000, USA. jdb60@case.edu
• J Thorac Imaging. 2010 Feb 1;25(1):41-7.

PurposeComputer-aided detection (CAD) has shown potential to assist physicians in the detection of lung nodules on chest radiographs, but widespread acceptance has been stymied by high false-positive rates. Few studies have examined the potential for dual energy subtraction (DES) to improve CAD performance.Materials And MethodsInstitutional review board approval was obtained, the requirement for informed consent was waived because the study was retrospective, and practices conformed to Health Insurance Portability and Accountability Act regulations. The CAD program was applied retrospectively to dual energy posteroanterior (PA) chest radiographs of 36 patients (17 women, 19 men, mean age 69 y) with 48 pathology proven lung nodules. Results were analyzed to determine the stand-alone CAD program false-positive rates, and sensitivity by nodule subtlety and location. Statistical analysis was performed using the chi(2) or Fisher exact tests for independence of sensitivities between standard PA and DES radiography. Differences in the mean false-positives per image (FPPI) between radiographic modalities were determined using the paired Students t test, and bootstrap confidence intervals were obtained to confirm results.ResultsThe sensitivity of the CAD program with the standard PA was 46% (22 of 48 nodules) compared with 67% (32 of 48 nodules) using the DES soft tissue or bone-subtracted view (P=0.064). The average number of FPPI identified by CAD was significantly lower using DES (FPPI(soft tissue) = 1.64) when compared with the standard PA chest radiograph (FPPI(PA) = 2.39) (P<0.01).ConclusionsDES has the potential to improve stand-alone CAD performance by both increasing sensitivity for certain subtle lung cancer lesions and decreasing overall CAD false-positive rates.

38 keywords...

hide…