Interstitial lung disease (ILD), representing a collection of disorders, is considered to be the deadliest one, which increases the mortality rate of humans. In this paper, an automated scheme for detection and classification of ILD patterns is presented, which eliminates low inter-class feature variation and high intra-class feature variation in patterns, caused by translation and illumination effects. A novel and efficient feature extraction method named Template-Matching Combined Sparse Coding (TMCSC) is proposed, which extracts features invariant to translation and illumination effects, from defined regions of interest (ROI) within lung parenchyma. The translated image patch is compared with all possible templates of the image using template matching process. The corresponding sparse matrix for the set of translated image patches and their nearest template is obtained by minimizing the objective function of the similarity matrix of translated image patch and the template. A novel Blended-Multi Class Support Vector Machine (B-MCSVM) is designed for tackling high-intra class feature variation problems, which provides improved classification accuracy. Region of interests (ROIs) of five lung tissue patterns (healthy, emphysema, ground glass, micronodule, and fibrosis) selected from an internal multimedia database that contains high-resolution computed tomography (HRCT) image series are identified and utilized in this work. Performance of the proposed scheme outperforms most of the state-of-art multi-class classification algorithms.
KatabamiMDosaka-AkitaHHonmaK, et al. Pneumoconiosis-related lung cancers: preferential occurrence from diffuse interstitial fibrosis-type pneumoconiosis. Am J Respir Crit Care Med2000; 162: 295–300.
2.
RosasIORenPAvilaNA, et al. Early interstitial lung disease in familial pulmonary fibrosis. Am J Respir Crit Care Med2007; 176: 698–705.
3.
BiedererJSchnabelAMuhleC, et al. Correlation between HRCT findings, pulmonary function tests and bronchoalveolar lavage cytology in interstitial lung disease associated with rheumatoid arthritis. Eur Radiol2004; 14: 272–280.
4.
WebbWRMüllerNLNaidichDP. High-resolution computed tomography of the lungs. New York: Raven Press, 1992.
5.
MüllerNL. Clinical value of high-resolution CT in chronic diffuse lung disease. Am J Roentgenol1991; 157: 1163–1170.
6.
ShinHCRothHRGaoM, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging2016; 35: 1285–1298.
7.
AnthimopoulosMChristodoulidisSEbnerL, et al. Semantic segmentation of pathological lung tissue with dilated fully convolutional networks. IEEE J Biomed Health Inform2019; 23: 714–722.
8.
RaghuGFlahertyKRLedererDJ, et al. Use of a molecular classifier to identify usual interstitial pneumonia in conventional transbronchial lung biopsy samples: a prospective validation study. Lancet Respir Med2019; 7: 487–496.
9.
WangJLiFLiQ. Automated segmentation of lungs with severe interstitial lung disease in CT. Med Phys2009; 36: 4592–4599.
10.
CoxsonHORogersRMWhittallKP, et al. A quantification of the lung surface area in emphysema using computed tomography. Am J Respir Crit Care Med1999; 159: 851–856.
11.
HsuT-ICalwayADWilsonR. Texture analysis using the multi-resolution Fourier transform. In: 8th Scandinavian conference on image analysis, Tromsø, 25–28 May 1993, pp.823–830. Berlin: Springer.
12.
ZrimecTBusayaratS. A system for computer aided detection of disease patterns in high resolution CT images of the lungs. In: Proceeding of twentieth IEEE international symposium on computer-based medical systems, Maribor, 20–22 June 2007, pp.41–46. New York: IEEE.
13.
KorfiatisPDKarahaliouANKazantziAD, et al. Texture-based identification and characterization of interstitial pneumonia patterns in lung multi-detector CT. IEEE Trans Inf Technol Biomed2010; 14: 675–680.
14.
XuYSonkaMMcLennanG, et al. MDCT-based 3-D texture classification of emphysema and early smoking related lung pathologies. IEEE Trans Med Imag2006; 25: 464–475.
15.
XuRHiranoYTachibanaR, et al. Classification of diffuse lung disease patterns on high-resolution computed tomography by a bag of words approach, medical image computing and computer- assisted intervention: MICCAI. New York: Springer, 2011.
16.
YaoJDwyerASummersRM, et al. Computer-aided diagnosis of pulmonary infections using texture analysis and support vector machine classification. Acad Radiol2011; 18: 306–314.
17.
OjalaTPietikainenMHarwoodD. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition2000; 29: 51–59.
18.
OjalaTPietikainenMMaenpaaT. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell2002; 24: 971–987.
19.
SemlerLDettoriLFurstJ. Wavelet-based texture classification of tissues in computed tomography. In: Proceedings of the 18th IEEE international symposium on computer-based medical systems, Dublin, 23–24 July 2005, pp.265–270. New York: IEEE.
20.
DepeursingeASageDHidkiA, et al. Lung tissue classification using wavelet frames. In: Proceedings of the 29th annual international conference of the IEEE EMBS, Lyon, 22–26 August 2007, pp.23–26. New York: IEEE.
21.
DepeursingeAVandeVilleDPlatonA, et al. Near-affine-invariant texture learning for lung tissue analysis using isotropic wavelet frames. IEEE Trans Inf Technol Biomed2012; 16: 665–675.
22.
ToloueeAAbrishami MoghaddamHForouzanfarM, et al. Image based diagnostic aid system for interstitial lung diseases. Expert Syst Appl2011; 38: 7755–7765.
23.
MacKayDJS. Bayesian methods for adaptive models. PhD Dissertation, California Institute of Technology, Pasadena, CA, 1992.
24.
NealRM. Bayesian learning for neural networks. In: BickelP.DiggleP.FienbergS. (eds) Lecture notes in statistics. New York: Springer, 1996; 118: 99–136.
25.
ChenYNasrabadiNMTranTD. Hyperspectral image classification via kernel sparse representation. IEEE Trans Geosci Remote Sens2013; 51: 217–231.
26.
BaxE. Validation of k-Nearest neighbor classifiers. IEEE Trans Inf Theory2012; 58: 3225–3234.
27.
ShuHYuRJiangW, et al. Efficient implementation of $k$-nearest neighbor classifier using vote count circuit. IEEE Trans Circ Syst: II: Exp Briefs2014; 61: 448–452.
28.
KnerrSL, et al. Single-layer learning revisited: a stepwise procedure for building and training a neural network. In: SoulieFFHeraultJ (eds) Neurocomputing: algorithms, architectures and applications, vol. 68. New York: Springer, 1990, pp.41–50.
29.
KrebelU, et al. Pairwise classification and support vector machines. In: Advances in Kernel methods: support vector learning. Cambridge, MA: MIT Press, 1999, 255–268.
30.
TsujinishiDYoshiakiKShigeoA. Why pairwise is better than one-against-all or all-at-once. Proc IEEE Int Joint Conf Neural Netw2004; 1: 693-698.
31.
FriedmanJ. Another approach to polychotomous classification. Technical report, Department of Statistics, Stanford University, Stanford, CA, 1996.
32.
ManikandanJVenkataramaniB. Design of a real time automatic speech recognition system using modified one against all SVM classifier. Microprocess Microsyst2011; 35: 568–578.
33.
FeiBLiuJ. Binary tree of SVM: a new fast multiclass training and classification algorithm. IEEE Trans Neural Netw2006; 17: 696–704.
34.
MelganiFBruzzoneL. Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans Geosci Remote Sens2004; 42: 1778–1790.
35.
PlattJCristianiniNShawe-TaylorJ. Large margin Dagsvm’s for multiclass classification. Adv Neural Inform Process Syst2000; 12: 547–553.
36.
HsuCWLinCJ. A comparison of methods for multiclass support vector machines. IEEE Trans Neural Netw2002; 13: 415–425.
37.
DepeursingeAMüllerHHidkiA. Image–based diagnostic aid for interstitial lung disease with secondary data integration. Med Imag2007: 6514.
38.
DepeursingeAVargasAPlatonA, et al. Building a reference multimedia database for interstitial lung diseases. Comput Med Imaging Graph2012; 36: 227–238.
