Texture classification‐based segmentation of lung affected by interstitial pneumonia in high‐resolution CT

Abstract

Accurate and automated lung field (LF) segmentation in high-resolution computed tomography (HRCT) is highly challenged by the presence of pathologies affecting lung borders, also affecting the performance of computer-aided diagnosis (CAD) schemes. In this work, a two-dimensional LF segmentation algorithm adapted to interstitial pneumonia (IP) patterns is presented. The algorithm employs k-means clustering followed by a filling operation to obtain an initial LF order estimate. The final LF border is obtained by an iterative support vector machine neighborhood labeling of border pixels based on gray level and wavelet coefficient statistics features. A second feature set based on gray level averaging and gradient features was also investigated to evaluate its effect on segmentation performance of the proposed method. The proposed method is evaluated on a dataset of 22 HRCT cases spanning a range of IP patterns such as ground glass, reticular, and honeycombing. The accuracy of the method is assessed using area overlap and shape differentiation metrics (d(mean), d(rms), and d(max)), by comparing automatically derived lung borders to manually traced ones, and further compared to a gray level thresholding-based (GLT-based) method. Accuracy of the methods evaluated is also compared to interobserver variability. The proposed method incorporating gray level and wavelet coefficient statistics demonstrated the highest segmentation accuracy, averaged over left and right LFs (overlap=0.954, d(mean)=1.080 mm, d(rms)=1.407 mm, and d(max)=4.944 mm), which is statistically significant (two-tailed student's t test for paired data, p<0.0083) with respect to all metrics considered as compared to the proposed method incorporating gray level averaging and gradient features (overlap=0.918, d(mean)=2.354 mm, d(rms)=3.711 mm, and d(max)=14.412 mm) and the GLT-based method (overlap=0.897, d(mean)=3.618 mm, d(rms)=5.007 mm, and d(max)=16.893 mm). The performance of the three segmentation methods, although decreased as IP pattern severity level (mild, moderate, and severe) was increased, did not demonstrate statistically significant difference (two-tailed student's t test for unpaired data, p>0.0167 for all metrics considered). Finally, the accuracy of the proposed method, based on gray level and wavelet coefficient statistics ranges within interobserver variability. The proposed segmentation method could be used as an initial stage of a CAD scheme for IP patterns.

Robust Segmentation of Challenging Lungs in CT Using Multi-stage Learning and Level Set Optimization

“…Diseased parenchyma has a different texture pattern which can often be extracted through the use of texture features [20,39,37]. Texture, the local structural pattern of intensities, is commonly characterized by measurements obtained from a co-occurance matrix [9], which records the joint frequency of intensity values between two pixels separated by a fixed offset computed over small volumes of interest around each image voxel.…”

Computer-Aided Diagnosis for Phase-Contrast X-ray Computed Tomography: Quantitative Characterization of Human Patellar Cartilage with High-Dimensional Geometric Features

“…However, results of its application to analysis of point distributions in atomic microscopy [19] and in astrophysical data [22] motivates its use here in characterizing chondrocyte organization. For comparison, we also investigate the use of second-order statistical features derived from gray-level co-occurrence matrices (GLCM) [23], which have also been previously investigated in medical image analytic tasks such as distinguishing pathological patterns on chest CT [24,25], classifying benign and malignant lesions on dynamic breast MRI [26][27][28], etc.…”

Lung Segmentation from CT with Severe Pathologies Using Anatomical Constraints

“…In order to account for specific pathologies, such as ILD, some existing methods focus on utilizing texture cues [4,11], or for tumors, robust statistical shape models can be used [9]. In order to robustly segment diseased lung parenchyma, other researchers have identified the need to use other nearby anatomical context.…”