Reduction of false positives at vessel bifurcations in computerized detection of lung nodules

Abstract

Objective: We describe a new false positive (FP) reduction method based on surface features in our computerized detection system for lung nodules and evaluate the method using clinical chest computed tomography (CT) scans. Methods:In our detection method, nodule candidates are extracted using volumetric curvature-based thresholding and region growing. For various sizes of nodules, we adopt multiscale integration based on Hessian eigenvalues. For each nodule candidate, two surface features are calculated to differentiate nodules and FPs at vessel bifurcations. These features are fed into a quadratic classifier based on the Mahalanobis distance ratio. Results:In an experimental study involving 16 chest CT scans, the average number of FPs was reduced from 107.5 to 14.1 per case at 90% sensitivity. Conclusions:This proposed FP reduction method is effective in removing FPs at vessel bifurcations.

Computer-assisted detection of metastatic lung tumors on computed tomography

“…We used our academic CAD software (Lung-CAD version 1.3) that applies a modified version of the algorithm devised by Nomura and colleagues. 10 , 11 The software was installed as a plug-in for a web-based CAD processing server named CIRCUS CS and developed by Nomura and colleagues. 12 This CAD software detects nodule candidates based on the shape index after segmentation of the lungs in whole CT images, and then calculates the likelihood of nodules using a quadratic classifier.…”

Novel platform for development, training, and validation of computer-assisted detection/diagnosis software

“…• Cerebral aneurysm detection in magnetic resonance (MR) angiograms based on 3D local intensity structure analysis [7] (hereafter, MRA-local) • Lung nodule detection in chest computed tomography (CT) images [19,20] (hereafter, Lung-CAD)…”

Tensor Voting Based Vascular Bifurcation Detection in CT Images of Lung

“…This method was just tested on synthesized data not the medical images. Nomura, et al [6] built a detection function by Hessian matrix of vessel segmented by region-growing algorithm. This method mainly focuses on vascular nodules and pays not much attention to bifurcations.…”