Computerized detection of diffuse lung disease in MDCT: the usefulness of statistical texture features

Accurate detection of diffuse lung disease is an important step for computerized diagnosis and quantification of this disease. It is also a difficult clinical task for radiologists. We developed a computerized scheme to assist radiologists in the detection of diffuse lung disease in multi-detector computed tomography (CT). Two radiologists selected 31 normal and 37 abnormal CT scans with ground glass opacity, reticular, honeycombing and nodular disease patterns based on clinical reports. The abnormal cases in our database must contain at least an abnormal area with a severity of moderate or severe level that was subjectively rated by the radiologists. Because statistical texture features may lack the power to distinguish a nodular pattern from a normal pattern, the abnormal cases that contain only a nodular pattern were excluded. The areas that included specific abnormal patterns in the selected CT images were then delineated as reference standards by an expert chest radiologist. The lungs were first segmented in each slice by use of a thresholding technique, and then divided into contiguous volumes of interest (VOIs) with a 64 x 64 x 64 matrix size. For each VOI, we determined and employed statistical texture features, such as run-length and co-occurrence matrix features, to distinguish abnormal from normal lung parenchyma. In particular, we developed new run-length texture features with clear physical meanings to considerably improve the accuracy of our detection scheme. A quadratic classifier was employed for distinguishing between normal and abnormal VOIs by the use of a leave-one-case-out validation scheme. A rule-based criterion was employed to further determine whether a case was normal or abnormal. We investigated the impact of new and conventional texture features, VOI size and the dimensionality for regions of interest on detecting diffuse lung disease. When we employed new texture features for 3D VOIs of 64 x 64 x 64 voxels, our system achieved the highest performance level: a sensitivity of 86% and a specificity of 90% for the detection of abnormal VOIs, and a sensitivity of 89% and a specificity of 90% for the detection of abnormal cases. Our computerized scheme would be useful for assisting radiologists in the diagnosis of diffuse lung disease.

[1]  Charles E Metz,et al.  ROC analysis in medical imaging: a tutorial review of the literature , 2008, Radiological physics and technology.

[2]  Ernest L. Hall,et al.  Texture Measures for Automatic Classification of Pulmonary Disease , 1972, IEEE Transactions on Computers.

[3]  S. Kido,et al.  Fractal Analysis for Quantitative Evaluation of Diffuse Lung Abnormalities on Chest Radiographs: Use of Sub-ROIs , 2003, Journal of thoracic imaging.

[4]  R P Kruger,et al.  Hybrid optical-digital radiography-based system for lung disease detection. , 1977, Applied optics.

[5]  E. Hoffman,et al.  Interstitial lung disease: A quantitative study using the adaptive multiple feature method. , 1999, American journal of respiratory and critical care medicine.

[6]  S Katsuragawa,et al.  Computerized analysis of interstitial infiltrates on chest radiographs: a new scheme based on geometric pattern features and Fourier analysis. , 1995, Academic radiology.

[7]  S Katsuragawa,et al.  Image feature analysis and computer-aided diagnosis in digital radiography: detection and characterization of interstitial lung disease in digital chest radiographs. , 1988, Medical physics.

[8]  Kunio Doi,et al.  Automatic detection of abnormalities in chest radiographs using local texture analysis , 2002, IEEE Transactions on Medical Imaging.

[9]  S Katsuragawa,et al.  Quantitative computer-aided analysis of lung texture in chest radiographs. , 1990, Radiographics : a review publication of the Radiological Society of North America, Inc.

[10]  E. V. van Beek,et al.  Computer-aided classification of interstitial lung diseases via MDCT: 3D adaptive multiple feature method (3D AMFM). , 2006, Academic radiology.

[11]  Ye Xu,et al.  MDCT-based 3-D texture classification of emphysema and early smoking related lung pathologies , 2006, IEEE Transactions on Medical Imaging.

[12]  Yulia Arzhaeva,et al.  Computer-aided detection of interstitial abnormalities in chest radiographs using a reference standard based on computed tomography. , 2007, Medical physics.

[13]  S Katsuragawa,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. , 1990, Medical physics.

[14]  Qiang Li,et al.  Reduction of bias and variance for evaluation of computer-aided diagnostic schemes. , 2006, Medical physics.

[15]  J Ikezoe,et al.  Fractal analysis of interstitial lung abnormalities in chest radiography. , 1995, Radiographics : a review publication of the Radiological Society of North America, Inc.

[16]  Bram van Ginneken,et al.  Improving computer-aided diagnosis of interstitial disease in chest radiographs by combining one-class and two-class classifiers , 2006, SPIE Medical Imaging.

[17]  Bram van Ginneken,et al.  Computer analysis of computed tomography scans of the lung: a survey , 2006, IEEE Transactions on Medical Imaging.

[18]  Qiang Li,et al.  Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans. , 2003, Medical physics.

[19]  H. Kauczor,et al.  Automatic detection of ground glass opacities on lung HRCT using multiple neural networks , 1997, European Radiology.

[20]  E. Hoffman,et al.  Quantification of pulmonary emphysema from lung computed tomography images. , 1997, American journal of respiratory and critical care medicine.

[21]  C. Metz.  ROC Methodology in Radiologic Imaging , 1986, Investigative radiology.

[22]  K. Harrington,et al.  Correlation between second trimester maternal serum inhibin-A and human chorionic gonadotrophin for the prediction of pre-eclampsia. , 2000, Placenta.

[23]  B. van Ginneken,et al.  Computer-aided diagnosis in high resolution CT of the lungs. , 2003, Medical physics.

[24]  Kunio Doi,et al.  Computer-aided diagnosis in chest radiography , 2007, Comput. Medical Imaging Graph..

[25]  Kunio Doi,et al.  A novel scheme for detection of diffuse lung disease in MDCT by use of statistical texture features , 2009, Medical Imaging.

[26]  G. van Kaick,et al.  Usual interstitial pneumonia. Quantitative assessment of high-resolution computed tomography findings by computer-assisted texture-based image analysis. , 1997, Investigative radiology.

[27]  Kunio Doi,et al.  Application of an artificial neural network to high-resolution CT: usefulness in differential diagnosis of diffuse lung disease. , 2004, AJR. American journal of roentgenology.

[28]  R.M. Haralick,et al.  Statistical and structural approaches to texture , 1979, Proceedings of the IEEE.

[29]  Carol E. Osborn,et al.  Statistical Applications for Health Information Management , 2000 .

[30]  T Kobayashi,et al.  Computerized analysis of interstitial disease in chest radiographs: improvement of geometric-pattern feature analysis. , 1997, Medical physics.

[31]  K Doi,et al.  The nature and subtlety of abnormal findings in chest radiographs. , 1991, Medical physics.

[32]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[33]  K. Doi,et al.  Quantitative computerized analysis of diffuse lung disease in high-resolution computed tomography. , 2003, Medical physics.

[34]  K. Doi,et al.  Computerized detection of lung nodules in thin-section CT images by use of selective enhancement filters and an automated rule-based classifier. , 2008, Academic Radiology.

[35]  E. Hoffman,et al.  Computer recognition of regional lung disease patterns. , 1999, American journal of respiratory and critical care medicine.