Classification of texture patterns in CT lung imaging

Abstract

Since several lung diseases can be potentially diagnosed based on the patterns of lung tissue observed in medical images, automated texture classification can be useful in assisting the diagnosis. In this paper, we propose a methodology for discriminating between various types of normal and diseased lung tissue in computed tomography (CT) images that utilizes Vector Quantization (VQ), an image compression technique, to extract discriminative texture features. Rather than focusing on images of the entire lung, we direct our attention to the extraction of local descriptors from individual regions of interest (ROIs) as determined by domain experts. After determining the ROIs, we generate "locally optimal" codebooks representing texture features of each region using the Generalized Lloyd Algorithm. We then utilize the codeword usage frequency of each codebook as a discriminative feature vector for the region it represents. We compare k-nearest neighbor, support vector machine and neural network classification approaches using the normalized histogram intersection as a similarity measure. The classification accuracy reached up to 98% for certain experimental settings, indicating that our approach may potentially assist clinicians in the interpretation of lung images and facilitate the investigation of relationships among structure, texture and function or pathology related to several lung diseases.

The Emerging Role of Quantification of Imaging for Assessing the Severity and Disease Activity of Emphysema, Airway Disease, and Interstitial Lung Disease

“…Beyond density measures, texture analysis takes into account the pattern, the spatial relationships between voxels, and the magnitude of attenuation values to enable further characterization and quantitation of parenchymal pathology (Fig. 1) [21][22][23]. Methods such as run-length matrices, fractal measures, and gray-level co-occurrence matrices can be used to determine uniformity, shape, and other morphologically distinct features.…”

Recognition of Lung Cancer Using Machine Learning Mechanisms with Fuzzy Neural Networks

“…It is more sensible and more exact for estimating the significance level of a component than the hard estimation of 0 or 1. After the weight development is finished, the component whose weight surpasses an edge is picked as an individual from the ideal element subset [17]. The limit is resolved adaptively as indicated by preparing information [18], as clarified in the last passage of the principal sub-area beneath.…”

Using HOG-LBP features and MMP learning to recognize imaging signs of lung lesions

“…In the last decades, many works have been done worldwide in the lung disease pattern classification. They want to distinguish abnormal tissues from normal ones [1][2] or to classify different visual patterns of a specific lung disease such as Diffuse Parenchyma Lung Disease (DPLD) [3], Chronic Obstructive Pulmonary Disease (COPD) [4][5][6] and Interstitial Lung Diseases (ILD) [7]. However, the problem of recognizing Common Imaging Signs of Lesions (CISLs) in lung CT images has not attracted the attention of the researchers.…”