Feasibility of Automated Quantification of Regional Disease Patterns Depicted on High-Resolution Computed Tomography in Patients with Various Diffuse Lung Diseases

Abstract

ObjectiveThis study was designed to develop an automated system for quantification of various regional disease patterns of diffuse lung diseases as depicted on high-resolution computed tomography (HRCT) and to compare the performance of the automated system with human readers.Materials and MethodsA total of 600 circular regions-of-interest (ROIs), 10 pixels in diameter, were utilized. The 600 ROIs comprised 100 ROIs that represented six typical regional patterns (normal, ground-glass opacity, reticular opacity, honeycombing, emphysema, and consolidation). The ROIs were used to train the automated classification system based on the use of a Support Vector Machine classifier and 37 features of texture and shape. The performance of the classification system was tested with a 5-fold cross-validation method. An automated quantification system was developed with a moving ROI in the lung area, which helped classify each pixel into six categories. A total of 92 HRCT images obtained from patients with different diseases were used to validate the quantification system. Two radiologists independently classified lung areas of the same CT images into six patterns using the manual drawing function of dedicated software. Agreement between the automated system and the readers and between the two individual readers was assessed.ResultsThe overall accuracy of the system to classify each disease pattern based on the typical ROIs was 89%. When the quantification results were examined, the average agreement between the system and each radiologist was 52% and 49%, respectively. The agreement between the two radiologists was 67%.ConclusionAn automated quantification system for various regional patterns of diffuse interstitial lung diseases can be used for objective and reproducible assessment of disease severity.

A Bag-of-Features Approach to Classify Six Types of Pulmonary Textures on High-Resolution Computed Tomography

“…For the identification of general DLD patterns, the number of textural types is relatively more. For example, five types are considered in [6], [16], six types are considered in [4], [7], [12] and seven types are considered in [5]. The definitions of the pulmonary textures are similar and differences Copyright c 2013 The Institute of Electronics, Information and Communication Engineers rely on the data or the purpose of clinical application.…”

“…Features can be designed by using one or several of the following measures on gray values [9], [15], such as statistical measures on histogram distributions, measures on gray-level co-occurrence matrices (GLCM) and measures on gray-level run-length matrices (GLRLM). More powerful features can be designed if these measures are combined with some other cues on geometrical information, such as fractal features [4], [13], [14] or shapes [7], [8]. There are also works [6], [12], [16], where the filter-bank based features are calculated from several scales and orientations and then sequential forward search is used to select the most discriminate features.…”

Classification of Diffuse Lung Disease Patterns on High-Resolution Computed Tomography by a Bag of Words Approach

“…From the viewpoints of computer vision, it can be generalized as the problem of texture analysis on a certain 2D or 3D region of interest (ROI). Some classical textural feature analysis methods calculated on 2D ROIs can be used, including the direct analysis on gray value intensities [2], features calculated on histogram statistics, and features extraction based on filter-banks, co-occurrence matrices or run-length parameters [1][5] [13]. Features may also be designed for the specific task on hands [4].…”

Regional Context-Sensitive Support Vector Machine Classifier to Improve Automated Identification of Regional Patterns of Diffuse Interstitial Lung Disease

“…Support vector machines (SVMs) are often used for image classification and have been shown to outperform other classifiers, such as Bayesian classifiers, artificial neural networks (ANNs), and generalized linear models [7][8][9]. SVM classifiers have been used to identify emphysema [10][11][12] and classify five regional disease patterns and normal tissues in DILD patients [13,14].…”