Radiological evaluation of interstitial lung disease

Current Opinion in Pulmonary Medicine

Volumn 17, Issue 5, 2011, Pages 337-345

  Rohatgi, Prashant K ^a  

^a GEORGE WASHINGTON UNIVERSITY SCHOOL OF MEDICINE AND HEALTH SCIENCES   (United States)

Author keywords

Computed tomography; computed tomography image processing; computed tomography thin section; computer aided diagnosis; interstitial lung disease; lung segmentation; quantitative computed tomography

Indexed keywords

ALGORITHM; AUTOMATION; COMPUTER ASSISTED DIAGNOSIS; COMPUTER ASSISTED TOMOGRAPHY; DISEASE COURSE; EVALUATION; HIGH RESOLUTION COMPUTER TOMOGRAPHY; HUMAN; INTERSTITIAL LUNG DISEASE; MULTIDETECTOR COMPUTED TOMOGRAPHY; QUANTITATIVE DIAGNOSIS; RADIOLOGIST; REVIEW; SUPPORT VECTOR MACHINE; THORAX RADIOGRAPHY; THREE DIMENSIONAL IMAGING;

ALGORITHMS; DISEASE PROGRESSION; HUMANS; LUNG DISEASES, INTERSTITIAL; MULTIDETECTOR COMPUTED TOMOGRAPHY; RADIOGRAPHY, THORACIC; SENSITIVITY AND SPECIFICITY; TOMOGRAPHY, X-RAY COMPUTED;

EID: 80051793942     PISSN: 10705287     EISSN: 15316971     Source Type: Journal    
DOI: 10.1097/MCP.0b013e328347c16a     Document Type: Review

References (29)

1. Padley SPG, Adler B, Muller NL. High-resolution computed tomography of the chest: current indications. J Thorac Imaging 1993;8:189-199. (Pubitemid 23197378)
2. Gould DM, Dalrymple GV. A radiologic analysis of disseminated lung disease. Am J Med Sci 1959;238:622-637.
3. Groskin SA. Pattern recognition in pulmonary radiology. In: Groskin SA, editor. Heitzman's the lung. Radiologic-pathologic correlations, Third Edition St. Louis: Mosby; 1993. pp. 70-105.
4. Bachofen H, Voegeli E. Disseminated nodular and miliary lesions of the lung. Pneumonologie 1976;153:249-260.
5. Miller WT Jr. Chest radiographic evaluation of diffuse infiltrative lung disease: review of a dying art. Eur J Radiology 2002;44:182-197. (Pubitemid 35430203)
6. Matheison Jr, Mayo JR, Staples CA, Muller NL. Chronic diffuse infiltrative lung disease: comparison of diagnostic accuracy of CT and chest radiography. Radiology 1989;171:111-116. (Pubitemid 19093054)
7. Smithuis R, Delden OV, Schaefer-Prokop. HRCT part I: basic interpretation. http://www.radiologyassistant.nl [accessed 5 May, 2011].
8. Johkoh T, Itoh H, Muller NL, et al. Crazy-paving appearance at thin-section CT: spectrum of disease and pathologic findings. Radiology 1999;211:155-160. (Pubitemid 29161745)
9. Leung AN, Miller RR, Miller NL. Parenchymal opacification in chronic infiltrative lung disease: CT-pathologic correlation. Radiology 1993;188:209-214. (Pubitemid 23183126)
10. Wells A, Hirani N. Interstitial lung disease guideline. Thorax 2008;63(S):v1 - v58. This is a comprehensive document covering diagnostic approach and assessment of severity of DILDs. It also provides guidelines for management of specific ILD.
11. Galvin JR, Frazier AA, Franks TJ. Collaborative radiologic and histopathologic assessment of fibrotic lung disease. Radiology 2011;255:692-706. Using collaborative review of clinical data and high-spatial resolution chest CT in concert with the results of electron microscopy and quantitative assessment of histologic lung biopsies, the authors conclude that the lower lobe cystic spaces in idiopathic pulmonary fibrosis are related to collapse of alveoli around the alveolar ducts rather than the deposition of fibrous connective tissue.
12. Akira M, Kozuka T, Yamamoto S, Sakatani M. Computed tomography in acute exacerbations of idiopathic pulmonary fibrosis. Am J Respir Crit Care Med 2008;178:372-378.
13. Kazerooni EA, Martinez FA, Flint A, et al. Thin-section CT obtained at 10-mm increments versus limited three-level thin-section CT for idiopathic pulmonary fibrosis: correlation with pathologic scoring. Am J Roentgenol 1997;169:977-983. (Pubitemid 27406888)
14. Perez A, Rogers RM, Dauber JH. The prognosis of idiopathic pulmonary fibrosis. Am J Respir Cell Mol Biol 2003;29:S19-S26. (Pubitemid 37070303)
15. Goh NSL, Desai SR, Veeraraghavan S, et al. Interstitial lung disease in systemic sclerosis. A simple staging system. Am J Respir Crit Care Med 2008;177:1248-1254. (Pubitemid 351860934)
16. Best AC, Lynch AM, Bozic CM. Quantitative CT indexes in idiopathic pulmonary fibrosis: relationship with physiologic impairment. Radiology 2003;228:407-414. (Pubitemid 36910079)
17. Coxson HO, Hogg JC, Mayo JR, et al. Quantification of idiopathic pulmonary fibrosis using computed tomography and histology. Am J Respir Crit Care Med 1997;155:1649-1656. (Pubitemid 27216672)
18. Hsia CCW, Hyde DM, Ochs M, et al. An official research policy statement of the American Thoracic Society/European Respiratory Society: standards for quantitative assessment of lung structure. Am J Respir Crit Care Med 2010;181:394-418.
19. Wang J, Li F, Li Q. Automated segmentation of lungs with severe interstitial lung disease in CT. Med Phys 2009;36:4592-4599.
20. Prasad MN, Brown MS, Ahmed S, et al. Automatic segmentation of lung parenchyma in the presence of disease based on curvature of ribs. Acta Radiol 2008;15:1173-1180.
21. Nunzio GD, Tommasi E, Agrusti A, et al. Automatic lung segmentation in CT images with accurate handling of hilar region. J Digit Imaging 2011;24:11-27. Hilum with crowded airways and vessels has an irregular shape with no specific texture features. This causes problems with accurate segmentation of lungs when using thresholding and texture feature-based techniques. This paper describes a method by which extrapulmonary airways were removed with a wavefront simulation model with appropriate stop conditions.
22. Shikata H, McLennan G, Hoffman EA, Sonka M. Segmentation of pulmonary vascular trees from thoracic 3D CT images. Int J of Biomed Imaging 2009;2009:636240; Published online.
23. Gorbunova V, Durrleman S, Lo P, et al. Lung CT registration combining intensity, curves and surfaces. In: 2010 IEEE International Conference on Biomedical Imaging: from nano to macro; 2010. pp. 340-343. For automated comparison of sequential CTs it is important that accurate registration of images be obtained. Previously intensity-based approach or featurebased methods were used for registration. This paper provides preliminary results of lung CT registration combining intensity and feature - curves and surfacesbased methods.
24. Uppaluri R, Hoffman EA, Sonka M, et al. Computer recognition of regional lung disease patterns. Am J Respir Crit Care Med 1999;160:648-654. (Pubitemid 29380686)
25. Xu Y, van Beck EJ, Hwanjo Y, et al. Computer-aided classification of interstitial lung diseases via MDCT:3D adaptive multiple feature method (3D AMFM). Acta Radiol 2006;13:969-978. (Pubitemid 44056026)
26. Park SO, Seo JB, Kim N, et al. Feasibility of automated quantification of regional disease patterns depicted on high-resolution computed tomography in patients with various diffuse lung diseases. Korean J Radiol 2009;10:455-463.
27. Lim J, Kim N, Seo JB, et al. Regional context-sensitive support vector machine classifier to improve automated identification of regional patterns of diffuse interstitial lung disease. J Digit Imaging 2011 [Epub ahead of print]. This uses a context-sensitive support vector machine that incorporates information from neighboring regions of interest to improve pattern recognition.
28. Kim HJ, Li G, Gjertson D, et al. Classification of parenchymal abnormality in scleroderma lung using a novel approach to denoise images collected via a multicenter study. Acta Radiol 2008;15:1004-1016. (Pubitemid 351938744)
29. Arzhaeva Y, Prokop M, Murphy K. Automated estimation of progression of interstitial lung disease in CT images. Med Phys 2010;37:63-73. In this study the authors compared baseline two-dimensional axial HRCT sections obtained at predefined levels with follow-up sections after intrapatient threedimensional volumetric image registration, autosegmentation utilizing exclusion of trachea and main stem bronchi and if that failed then registration by utilizing multiatlas segmentation. A difference image was obtained by subtracting the baseline CT section from the follow-up CT section. Changes in ILD were assessed by analyzing intensity-based histogram from difference image; and by looking for dissimilarities computed between the baseline and follow-up images using only local texture features that were previously used to characterize different patterns associated with ILD. With this method, the accuracy of predicting progression of ILD approached the accuracy observed by visual methods employed by experienced radiologists.