In this issue of Academic Radiology , Dr. Robb and colleagues ( ) detail the steps required to develop a novel texture analysis approach that can be used to classify and quantify the various pathologies present in the lungs of patients with fibrotic lung disease. The article also demonstrates that this novel method is effective in the classification of normal versus abnormal tissue and performs as well as expert radiologists in distinguishing typical pathologies present within the lungs of patients with idiopathic pulmonary fibrosis.
Usual interstitial pneumonia (UIP) is the most common chronic interstitial pneumonia, accounting for 25%–30% of cases ( ). Usual interstitial pneumonia is characterized histologically by inflammation (fibroblastic foci) that progresses to dense fibrosis and honeycombing, and is distinguished from the other interstitial pneumonias by fibrosis and both temporal and spatial heterogeneity. Temporal heterogeneity refers to the presence of abnormalities representing different stages in the development of fibrosis within the lung, whereas spatial heterogeneity refers to nonuniform lung involvement, with abnormal areas of lung adjacent to normal areas ( ). Usual interstitial pneumonia may be primary or secondary. When primary (60%–70% of cases), idiopathic pulmonary fibrosis (IPF) is used to describe the clinical syndrome. IPF occurs most often in older patients, 50–70 years of age, is difficult to treat, has a poor life expectancy, and has a median survival from onset of 3 years and a 5-year survival of about 50% ( ). The early detection of these disease entities is of growing interest both for phenotyping as well as for the evaluation of interventions over short periods and preferably at early stages of the pathologic processes. On high-resolution computed tomography, UIP is typically patchy, with a peripheral, subpleural, posterior, and lower lobe predominance. The features are irregular reticular opacities with traction bronchiectasis, honeycombing in 80% of patients, and inconspicuous isolated areas of ground-glass opacity ( ).
Computer-aided diagnosis (CAD) has become one of the major research subjects in medical imaging and diagnostic radiology. It provides a computerized diagnostic result as a “second opinion” to assist radiologists in the diagnosis of various diseases by use of medical images ( ). The radiologists use the computer output as a “second opinion” and make the final decisions. Therefore, CAD takes into account equally the roles of physicians and computers ( ). With CAD, the performance by computers does not have to be comparable to or better than that by physicians, but needs to be complementary to that by physicians ( ).
Several CAD systems have been employed for assisting physicians, predominantly in the early detection of breast cancers on mammograms ( ). With regard to CAD and lung disease, a large research effort has been devoted to the detection and classification of various lung diseases on both chest radiograph and thoracic computed tomography (CT) images. Current CAD schemes for chest radiographs include nodule detection and distinction between benign and malignant pulmonary nodules ( ), detection and classification of lung cancers ( ), and interstitial disease detection and the characterization and differentiation of interstitial lung disease ( ). Current CAD schemes for chest CT include nodule detection and distinction between benign and malignant pulmonary nodules ( ), and interstitial lung disease detection and differentiation ( ).
The development of multidetector CT scanners (MDCT) has allowed the volumetric imaging of the lung with near isotropic voxels and a single breath hold in less than 10 seconds. Therefore, great interest has developed in the use of MDCT and its exquisite three-dimensional (3D) anatomic detail that can be rendered with these studies to quantitate lung disease by assessment of lung tissue using texture features extended from two-dimensional (2D) to 3D formulations.
Although CAD of lung disease has been an active area of research for some time, 3D CAD is very new. In one study, Xu et al assessed MDCT-based 3D texture classification of emphysema and early smoking related lung pathologies ( ). In that article, the authors demonstrate the ability to differentiate normal lung from subtle pathologies using MDCT and extending a 2D texture-based tissue classification adaptive multiple feature method using 3D texture features. The authors showed that the 3D analysis is significantly better than the 2D analysis. More recently, the same author has published an article that further developed a computer-aided detection tool, the adaptive multiple feature method, for the detection of interstitial lung diseases based on MDCT-generated volumetric data ( ). The author showed that 3D features can be successfully used in differentiation of lung parenchymal pathology associated with both emphysema and interstitial lung diseases. Until now, this was the only substantive article describing an extension of their 2D algorithm to 3D for detection of various radiologic patterns of lung fibrosis from MDCT data.
Get Radiology Tree app to read full this article<
Get Radiology Tree app to read full this article<
Get Radiology Tree app to read full this article<
Get Radiology Tree app to read full this article<
Get Radiology Tree app to read full this article<
Get Radiology Tree app to read full this article<
References
1. Zavaletta V.A., Bartholmai B.J., Robb R.A.: High resolution multi-detector CT aided tissue analysis and quantification of lung fibrosis. Acad Radiol 2007; 14: pp. 772-787.
2. American Thoracic Society/European Respiratory Society International Multidisciplinary Consensus Classification of the Idiopathic Interstitial pneumonias: This joint statement of the American Thoracic Society (ATS), and the European Respiratory Society (ERS) was adopted by the ATS board of directors, June 2001 and by the ERS Executive Committee, June 2001. Am J Respir Crit Care Med 2002; 165: pp. 277-304.
3. Doi K.: Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 2007; 31: pp. 198-211.
4. Doi K., MacMahon H., Katsuragawa S., et. al.: Computer-aided diagnosis in radiology: potential and pitfalls. Eur J Radiol 1999; 31: pp. 97-109.
5. Abe H., MacMahon H., Engelmann R., et. al.: Computer-aided diagnosis in chest radiography: results of large-scale observer tests at the 1996–2001 RSNA scientific assemblies. Radiographics 2003; 23: pp. 255-265.
6. Abe H., Macmahon H., Shiraishi J., et. al.: Computer-aided diagnosis in chest radiology. Semin Ultrasound CT MR 2004; 25: pp. 432-437.
7. Li Q., Li F., Suzuki K., et. al.: Computer-aided diagnosis in thoracic CT. Semin Ultrasound CT MR 2005; 26: pp. 357-363.
8. Katsuragawa S., Doi K.: Computer-aided diagnosis in chest radiography. Comput Med Imaging Graph 2007; 31: pp. 212-223.
9. Kobayashi T., Xu X.W., MacMahon H., et. al.: Effect of a computer-aided diagnosis scheme on radiologists’ performance in detection of lung nodules on radiographs. Radiology 1996; 199: pp. 843-848.
10. Penedo M.G., Carreira M.J., Mosquera A., et. al.: Computer-aided diagnosis: a neural-network-based approach to lung nodule detection. IEEE Trans Med Imaging 1998; 17: pp. 872-880.
11. MacMahon H., Engelmann R., Behlen F.M., et. al.: Computer-aided diagnosis of pulmonary nodules: results of a large-scale observer test. Radiology 1999; 213: pp. 723-726.
12. Li Q., Katsuragawa S., Doi K.: Computer-aided diagnostic scheme for lung nodule detection in digital chest radiographs by use of a multiple-template matching technique. Med Phys 2001; 28: pp. 2070-2076.
13. Suzuki K., Shiraishi J., Abe H., et. al.: False-positive reduction in computer-aided diagnostic scheme for detecting nodules in chest radiographs by means of massive training artificial neural network. Acad Radiol 2005; 12: pp. 191-201.
14. Schilham A.M., van Ginneken B., Loog M.: A computer-aided diagnosis system for detection of lung nodules in chest radiographs with an evaluation on a public database. Med Image Anal 2006; 10: pp. 247-258.
15. Shiraishi J., Li Q., Suzuki K., et. al.: Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification. Med Phys 2006; 33: pp. 2642-2653.
16. Shiraishi J., Abe H., Li F., et. al.: Computer-aided diagnosis for the detection and classification of lung cancers on chest radiographs ROC analysis of radiologists’ performance. Acad Radiol 2006; 13: pp. 995-1003.
17. Morishita J., Doi K., Katsuragawa S., et. al.: Computer-aided diagnosis for interstitial infiltrates in chest radiographs: optical-density dependence of texture measures. Med Phys 1995; 22: pp. 1515-1522.
18. Monnier-Cholley L., MacMahon H., Katsuragawa S., et. al.: Computer-aided diagnosis for detection of interstitial opacities on chest radiographs. AJR Am J Roentgenol 1998; 171: pp. 1651-1656.
19. Reeves A.P., Kostis W.J.: Computer-aided diagnosis of small pulmonary nodules. Semin Ultrasound CT MR 2000; 21: pp. 116-128.
20. Awai K., Murao K., Ozawa A., et. al.: Y. Pulmonary nodules at chest CT: effect of computer-aided diagnosis on radiologists’ detection performance. Radiology 2004; 230: pp. 347-352.
21. Wormanns D., Beyer F., Diederich S., et. al.: Diagnostic performance of a commercially available computer-aided diagnosis system for automatic detection of pulmonary nodules: comparison with single and double reading. Rofo 2004; 176: pp. 953-958.
22. Abe Y., Hanai K., Nakano M., et. al.: A computer-aided diagnosis (CAD) system in lung cancer screening with computed tomography. Anticancer Res 2005; 25: pp. 483-488.
23. Ko J.P.: Lung nodule detection and characterization with multi-slice CT. J Thorac Imaging 2005; 20: pp. 196-209.
24. Li F., Arimura H., Suzuki K., et. al.: Computer-aided detection of peripheral lung cancers missed at CT: ROC analyses without and with localization. Radiology 2005; 237: pp. 684-690.
25. Xu Y., van Beek E.J., Hwanjo Y., et. al.: Computer-aided classification of interstitial lung diseases via MDCT: 3D adaptive multiple feature method (3D AMFM). Acad Radiol 2006; 13: pp. 969-978.
26. Xu Y., Sonka M., McLennan G., et. al.: MDCT-based 3-D texture classification of emphysema and early smoking related lung pathologies. IEEE Trans Med Imaging 2006; 25: pp. 464-475.
27. Hu S., Hoffman E., Reinhardt J.: Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images. IEEE Trans Med Imaging 2001; 20: pp. 490-498.
28. Levina P., Bickel E.: 2001. Proceedings of the IEEE International Conference on Computer Vision (ICCV 2001) Vancouver, Canada July 9–12