Abstract
We devised an automated classification scheme by using the rule-based method plus artificial neural networks (ANN) for distinction between normal and abnormal lungs with interstitial disease in digital chest radiographs. Four measures used in the classification scheme are determined from the texture and geometric-pattern feature analyses. The rms variation and the first moment of the power spectrum of lung patterns aredetermined as measures for the texture analysis. In addition, the total area of nodular opacities and the total length of linear opacities are determined as measures for the geometric-pattern feature analysis. In our classification scheme with these measures, we identify obviously normal and abnormal cases first by the rule-based method and then ANN is applied for the remaining difficult cases. The rulebased plus ANN method provided a sensitivity of 0.926 at the specificity of 0.900, which was considerably improved compared to performance of either the rule-based method alone or ANNs alone.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Fraser RG, Pare JA: Diagnosis of Diseases of the Chest. Philadelphia, PA, Saunders, 1970
Tully RJ, Conners RW, Harlow CA, et al: Toward computer analysis of pulmonary infiltration. Invest Radio 13:298–305, 1978
Doi K, Giger ML, MacMahon H, et al: Computer-aided Diagnosis (CAD): Development of automated schemes for quantitative analysis of radiographic images. Semin Ultrasound CT MR 13:140–152, 1992
Giger ML, Doi K, MacMahon H, et al: An intelligent workstation for computer-aided diagnosis. RadioGraphics 13: 647–656, 1993
MacMahon H, Doi K, Chan HP, et al: Computer-aided diagnosis in chest radiology. J Thorac Imag 5:67–76, 1990
Jagoe JR, Paton KA: Reading chest radiographs by computer. Br J Ind Med 32:267–272, 1975
Revesz G, Kundel HL: Feasibility of classifying disseminated pulmonary diseases based on their Fourier spectra. Invest Radiol 8:345–349, 1973
Turner AF, Kruger RP, Thompson WB: Automated computer screening of chest radiographs for pneumoconiosis. Invest Radiol 11:258–266, 1976
Kruger RP, Thompson WB, Turner AF: Computer diagnosis of pneumoconiosis. IEEE Trans Syst Man Cybern 4:40–49, 1974
Kido S, Ikezoe J, Naito H, et al: An image analyzing system for interstitial lung abnormalities in chest radiography: Detection and classification by Laplacian-Gaussian filtering and linear opacity judgment. Invest Radiol 29:172–177, 1994
Katsuragawa S, Doi K, MacMahon H: Image feature analysis and computer-aided diagnosis in digital radiography: Detection and characterization of interstitial lung disease in digital chest radiographys. Med Phys 15:311–319, 1988
Powell GF, Doi K, Katsuragawa S: Localization of inter-rib spaces for lung texture analysis and computer-aided diagnosis in digital chest images. Med Phys 15:581–587, 1988
Katsuragawa S, Doi K, Nakamori N, et al: Image feature analysis and computer-aided diagnosis in digital radiography: Effect of digital parameters on the accuracy of computerized analysis of interstitial disease in digital chest radiographs. Med Phys 17:72–78, 1990
Katsuragawa S, Doi K, MacMahon H, et al: Quantitative computer-aided analysis of lung texture in chest radiographs. RadioGraphics 10:257–269, 1990
Chen X, Doi K, Katsuragawa S, et al: Automated selection of regions of interest for quantitative analysis of lung textures in digital chest radiographs. Med Phys 20:975–982, 1993
Morishita J, Doi K, Katsuragawa S, et al: Computer-aided diagnosis for interstitial infiltrates in chest radiographs: Analysis of optical-density dependence on texture measures. Med Phys 22:1515–1522, 1995
Katsuragawa S, Doi K, MacMahon H, et al: Quantitative analysis of geometric-pattern features of interstitial infiltrates in digital chest radiographs. J Digit Imaging 9:137–144, 1996
Asada N, Doi K, MacMahon H, et al: Potential usefulness of an artificial neural network for differential diagnosis of interstitial lung diseases: Pilot study. Radiology 177:857–860, 1990
Boone JM, Gross GW, Greco-Hunt V: Neural networks in radiologic diagnosis: I. Introduction and illustration. Invest Radiol 25:1012–1016, 1990
Wu Y, Doi K, Giger ML, et al: Computerized detection of clustered microcultifications in digital mammograms: Application of artificial neural networks. Med Phys 19:555–560, 1992
Wu Y, Giger ML, Doi K, et al: Artificial neural networks in mammography: Application to decision making in the diagnosis of breast cancer. Radiology 187:81–87, 1993
Chan HP, Metz CE, Doi K: Digital image processing: Optimal spatial filter for maximization of the perceived SNR based on a statistical decision theory model for the human observer. Proc SPIE 535:2–11, 1985
Rogers SK, Kabrisky M: An introduction to biological and artificial neural networks for pattern recognition. Bellingham, WA, SPIE Press, 1991
Metz CE: ROC methodology in radiologic imaging. Invest Radiol 21:720–733, 1986
Author information
Authors and Affiliations
Additional information
This study was supported by USPHS Grant CA 24806 and 62625.
Rights and permissions
About this article
Cite this article
Katsuragawa, S., Doi, K., MacMahon, H. et al. Classification of normal and abnormal lungs with interstitial diseases by rule-based method and artificial neural networks. J Digit Imaging 10, 108–114 (1997). https://doi.org/10.1007/BF03168597
Issue Date:
DOI: https://doi.org/10.1007/BF03168597