Research Article Enhanced Classification of Interstitial Lung Disease Patterns in HRCT Images Using Differential Lacunarity Verónica Vasconcelos, 1,2 João Barroso, 1,3 Luis Marques, 2 and José Silvestre Silva 4 1 INESC TEC, Campus da FEUP, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal 2 Coimbra Institute of Engineering, Polytechnic Institute of Coimbra, Rua Pedro Nunes, Quinta da Nora, 3030-199 Coimbra, Portugal 3 School of Science and Technology, University of Tr´ as-os-Montes e Alto Douro, Apartado 1013, 5001-801 Vila Real, Portugal 4 Military Academy Research Center, Avenida Conde Castro Guimar˜ aes, 2720-113 Amadora, Portugal Correspondence should be addressed to Ver´ onica Vasconcelos; veronica@isec.pt Received 11 September 2015; Accepted 18 November 2015 Academic Editor: Yukihisa Takayama Copyright © 2015 Ver´ onica Vasconcelos et al. Tis is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Te analysis and interpretation of high-resolution computed tomography (HRCT) images of the chest in the presence of interstitial lung disease (ILD) is a time-consuming task which requires experience. In this paper, a computer-aided diagnosis (CAD) scheme is proposed to assist radiologists in the diferentiation of lung patterns associated with ILD and healthy lung parenchyma. Regions of interest were described by a set of texture attributes extracted using diferential lacunarity (DLac) and classical methods of statistical texture analysis. Te proposed strategy to compute DLac allowed a multiscale texture analysis, while maintaining sensitivity to small details. Support Vector Machines were employed to distinguish between lung patterns. Training and model selection were performed over a stratifed 10-fold cross-validation (CV). Dimensional reduction was made based on stepwise regression (-test,  value < 0.01) during CV. An accuracy of 95.8 ± 2.2% in the diferentiation of normal lung pattern from ILD patterns and an overall accuracy of 94.5 ± 2.1% in a multiclass scenario revealed the potential of the proposed CAD in clinical practice. Experimental results showed that the performance of the CAD was improved by combining multiscale DLac with classical statistical texture analysis. 1. Introduction Interstitial lung disease (ILD) is a common name for a heterogeneous group of complex disorders afecting lung parenchyma. Te ILD afects similar lung regions and has identical clinical, radiological, and functional tests which hinder the diferential diagnosis. However, ILD subtypes have diferent prognoses and treatments, so a correct diagnosis is essential [1]. High-resolution computed tomography (HRCT) imaging of the chest can ofer such good image quality that it has become essential in the detection, diagnosis, and follow- up of ILD [2]. HRCT images of patients afected with ILD have specifc patterns whose distribution and visual content analysis is particularly relevant in elaborating an accurate diagnosis [3]. Multidetector row computed tomography (CT) scanners generate a huge volume of data that must be visually examined by radiologists. Tis task is very time-consuming and requires experience, especially in the presence of ILD. Computer-aided diagnosis (CAD) for ILD is seen as a necessary tool to reduce interobserver and intraobserver vari- ations, as well as to improve diagnostic accuracy by assisting radiologists in the detection, characterization, and quantif- cation of pathological regions [3–13]. In this paper, a CAD scheme is presented allowing for a classifcation of regions of interest (ROIs), from HRTC images, in four classes of lung patterns: normal (NOR), ground glass (GG), honeycombing (HC), and emphysema (EMP). A scenario of binary diferentiation, NOR class versus pathological class, is also considered. A generic fowchart of the proposed approach is shown in Figure 1. Classical statistical methods were used to extract and quantify texture information. Te frst-order (FO) analysis, the Spatial Gray Level Dependence Method (SGLDM), and the Gray Level Run-Length Method (GLRLM) allowed the estimate of statistical properties of individual pixel values and of the Hindawi Publishing Corporation BioMed Research International Volume 2015, Article ID 672520, 9 pages http://dx.doi.org/10.1155/2015/672520