A Comprehensive Framework for Automatic Detection of Pulmonary Nodules in Lung Ct Images

Abstract

Solitary pulmonary nodules may indicate an early stage of lung cancer. Hence, the early detection of nodules is the most efficient way for saving the lives of patients. The aim of this paper is to present a comprehensive Computer Aided Diagnosis (CADx) framework for detection of the lung nodules in computed tomography images. The four major components of the developed framework are lung segmentation, identification of candidate nodules, classification and visualization. The process starts with segmentation of lung regions from the thorax. Then, inside the segmented lung regions, candidate nodules are identified using an approach based on multiple thresholds followed by morphological opening and 3D region growing algorithm. Finally, a combination of a rule-based procedure and support vector machine classifier (SVM) is utilized to classify the candidate nodules. The proposed CADx method was validated on CT images of 60 patients, containing the total of 211 nodules, selected from the publicly available Lung Image Database Consortium (LIDC) image dataset. Comparing to the other state of the art methods, the proposed framework demonstrated acceptable detection performance (Sensitivity: 0.80; Fp/Scan: 3.9). Furthermore, we visualize a range of anatomical structures including the 3D lung structure and the segmented nodules along with the Maximum Intensity Projection (MIP) volume rendering method that will enable the radiologists to accurately and easily estimate the distance between the lung structures and the nodules which are frequently difficult at best to recognize from CT images.

Lung Cancer Detection Using Fuzzy Auto-Seed Cluster Means Morphological Segmentation and SVM Classifier

“…Usually the 2-D lung nodule analysis produces more false positives; therefore accuracy of the algorithm will be less. To overcome these issues three dimensional (3-D) analysis was carried out in recent literatures, which usually results in less false positives [6,13,14].…”

Using Deep Learning for Classification of Early Lung Nodules on Computed Tomography Images

“…But the process to identify lung nodules in early stages, those less than 10mm in diameter, is a challenging task even for the experienced radiologist. Besides small size, the early nodules have low contrast in comparison to the lung tissue and can be attached to other complex lung structures (Figure 1) [Hua K-L and Y-J 2015] [ Alilou et al 2014].…”

“…Figure 1. Lung nodules (circulated in gray) with their sizes and anatomical structures connected to them, respectively [Alilou et al 2014].…”

Computerized detection of lung nodules through radiomics

“…Rule-based classifier, support vector machine, Fisher linear discriminant classifier, and fixed-topology ANN classification can be used to distinguish real nodules from false positive detections and to analyze extracted features. 6,8,9,13 To improve classification performance, Li et al 6 utilized an automated rule-based classifier by iteratively determining the optimal threshold to design processes that can minimize the overtraining effect. Tan et al 8 employed feature-deselective neuro-evolving augmenting of topologies (FD-NEAT) to reduce false positive detections.…”