Classification of benign and malignant lung nodules from CT images based on hybrid features

Abstract

The classification of benign and malignant lung nodules has great significance for the early detection of lung cancer, since early diagnosis of nodules can greatly increase patient survival. In this paper, we propose a novel classification method for lung nodules based on hybrid features from computed tomography (CT) images. The method fused 3D deep dual path network (DPN) features, local binary pattern (LBP)-based texture features and histogram of oriented gradients (HOG)-based shape features to characterize lung nodules. DPN is a convolutional neural network which integrates the advantages of aggregated residual transformations (ResNeXt) for feature reuse and a densely convolutional network (DenseNet) for exploring new features. LBP is a prominent feature descriptor for texture classification, when combining with the HOG descriptor, it can improve the classification performance considerably. To differentiate malignant nodules from benign ones, a gradient boosting machine (GBM) algorithm is employed. We evaluated the proposed method on the publicly available LUng Nodule Analysis 2016 (LUNA16) dataset with 1004 nodules, achieving an area under the receiver operating characteristic curve (AUC) of 0.9687 and accuracy of 93.78%. The promising results demonstrate that our method has strong robustness on the classification of nodule patterns by virtue of the joint use of texture features, shape features and 3D deep DPN features. The method has the potential to help radiologists to interpret diagnostic data and make decisions in clinical practice.

PET/CT Radiomics in Lung Cancer: An Overview

“…Other texture features different from the above have also been investigated for characterizing PET/CT images in lung cancer-as, for instance, Gabor filters [36], Laws' masks [37], Local Binary Patterns [38], and wavelets [32].…”

“…Deep Learning has recently shown great potential for computer-assisted diagnosis [38,40] and for prediction of response to therapy [41] in patients with lung cancer. A potential drawback of Deep Learning, however, is that the resulting features are not as easy to interpret as the hand-designed ones, nor readily linkable to clinically relevant image findings [42].…”

Predicting benign, preinvasive, and invasive lung nodules on computed tomography scans using machine learning

“…It has been used extensively for classifying lung nodules because of its accuracy with a limited training dataset. [6][7][8][9] However, it can be a laborious process because every nodule requires segmentation and analysis by personnel with expertise in the method. Alternatively, deep learning classification takes the images that fully enclose the nodule and sends them into a convolutional neural network (CNN).…”

Integrated System for Classification of Pulmonary Nodules on CT Images

“…types of nodules file also contains boundary coordinates. Nodules annotation was provided in XML sheet by up to four radiologist separately [14,15,16]. In Table II is description of nine characteristics of nodules considered with respect to LIDC images along with rating.…”