Automated Pulmonary Lung Nodule Detection Using an Optimal Manifold Statistical Based Feature Descriptor and SVM Classifier

Abstract

The pulmonary lung nodule is the most common indicator of lung cancer. An efficient automated pulmonary nodule detection system aids the radiologists to detect the lung abnormalities at an early stage. In this paper, an automated lung nodule detection system using a feature descriptor based on optimal manifold statistical thresholding to segment lung nodules in Computed Tomography (CT) scans is presented. The system comprises three processing stages. In the first stage, the lung region is extracted from thoracic CT scans using gray level thresholding and 3D connected component labeling. After that novel lung contour correction method is proposed using modified convex hull algorithm to correct the border of a diseased lung. In the second stage, optimal manifold statistical image thresholding is described to minimize the discrepancy between nodules and other tissues of the segmented lung region. Finally, a set of 2D and 3D features are extracted from the nodule candidates, and then the system is trained by employing support vector machines (SVM) to classify the nodules and non-nodules. The performance of the proposed system is assessed using Lung TIME database. The system is tested on 148 cases containing 36408 slices with total sensitivity of 94.3%, is achieved with only 2.6 false positives per scan.

Segmentation of the pulmonary nodule and the attached vessels in the CT scan of the chest using morphological features and topological skeleton of the nodule

“…The current methods in this stage can be divided into four groups: methods based on the thresholding, deformable models, shape‐based models, and edge‐based models [9]. Region growing [10–12] and thresholding [13–17] with morphological operations and 3D blob algorithm are the most common methods in this stage. Watershed segmentation [18], contour model with fuzzy C‐means clustering [19], graph cut [20], and random forest [21] are also used.…”

“…As a result, the boundary correction sub‐stage is used to recover the nodule area. In this sub‐stage, rolling ball [19], morphological operations [11–13], convex hull [14], code chain [22], adaptive border marching [17], and multi‐scale edge detection [21] are proposed in the literatures.…”