Improved detection of pulmonary nodules on energy-subtracted chest radiographs with a commercial computer-aided diagnosis software: comparison with human observers

Abstract

Improved detection of pulmonary nodules on energy-subtracted chest radiographs with a commercial computer-aided diagnosis software: comparison with human observers Abstract Objective: To retrospectively analyze the performance of a commercial computer-aided diagnosis (CAD) software in the detection of pulmonary nodules in original and energy-subtracted (ES) chest radiographs. Methods: Original and ES chest radiographs of 58 patients with 105 pulmonary nodules measuring 5-30 mm and images of 25 control subjects with no nodules were randomized. Five blinded readers evaluated firstly the original postero-anterior images alone and then together with the subtracted radiographs. In a second phase, original and ES images were analyzed by a commercial CAD program. CT was used as reference standard. CAD results were compared to the readers' findings. True-positive (TP) and false-positive (FP) findings with CAD on subtracted and nonsubtracted images were compared. Results: Depending on the reader's experience, CAD detected between 11 and 21 nodules missed by readers. Human observers found three to 16 lesions missed by the CAD software. CAD used with ES images produced significantly fewer FPs than with nonsubtracted images: 1.75 and 2.14 FPs per image, respectively (p=0.029). The difference for the TP nodules was not significant (40 nodules on ES images and 34 lesions in nonsubtracted radiographs, p=0.142). Conclusion: CAD can improve lesion detection both on energy subtracted and non-subtracted chest images, especially for less experienced readers. The CAD program marked less FPs on energy-subtracted images than on original chest radiographs.

Comparison of Dual-Energy Subtraction and Electronic Bone Suppression Combined With Computer-Aided Detection on Chest Radiographs: Effect on Human Observers' Performance in Nodule Detection

“…However, Balkman et al [15] found more nodules when CAD was combined with dual-energy subtraction radiography instead of conventional chest radiography. The FP rate of 1.27 per image with the CAD program on chest radiography was notably lower in our collective than reported in former studies, which ranged from 2.14 to 5.9 FPs per image [11,14].…”

“…The fact that the combination of dual-energy subtraction with CAD failed to improve the nodule detection rate is consonant with former results [14]. However, Balkman et al [15] found more nodules when CAD was combined with dual-energy subtraction radiography instead of conventional chest radiography.…”

“…

very few series have dealt with a combination of these techniques [14,15]. The feasibility of software-only bone suppression on conventional chest radiography in combination with CAD has not been tested to date.

…”

A Comparison of Computer-Aided Detection (CAD) Effectiveness in Pulmonary Nodule Identification Using Different Methods of Bone Suppression in Chest Radiographs

“…While previous research had evaluated the use of CAD and either hardware-or software-based methods separately, the two methods of bone suppressed image generation had not been directly compared. The results of this study suggest that the number of ROI and FPPI has been dramatically reduced from earlier versions of CAD used in conjunction with DESR [11,12,14] and also when compared to earlier software-based methods of bone suppression [13]. Additionally, sensitivity and specificity were found to be improved over previous versions evaluated in the literature [11,13,14].…”

“…Other authors, [10][11][12] indicated that hardware-based bone suppression (DESR) removed the presence of bony structures in digital chest radiographs and significantly improved the sensitivity of CAD performance in pathology-proven cases with pulmonary nodules while reducing the false-positive rate. Similarly, Freedman et al [13] suggested that softwarebased removal of bony structures also improved the rate of lung cancer detection.…”