A pattern classification approach to characterizing solitary pulmonary nodules imaged on high resolution CT: preliminary results.

The purpose of this research is to characterize solitary pulmonary nodules as benign or malignant based on quantitative measures extracted from high resolution CT (HRCT) images. High resolution CT images of 31 patients with solitary pulmonary nodules and definitive diagnoses were obtained. The diagnoses of these 31 cases (14 benign and 17 malignant) were determined from either radiologic follow-up or pathological specimens. Software tools were developed to perform the classification task. On the HRCT images, solitary nodules were identified using semiautomated contouring techniques. From the resulting contours, several quantitative measures were extracted related to each nodule's size, shape, attenuation, distribution of attenuation, and texture. A stepwise discriminant analysis was performed to determine which combination of measures were best able to discriminate between the benign and malignant nodules. A linear discriminant analysis was then performed using selected features to evaluate the ability of these features to predict the classification for each nodule. A jackknifed procedure was performed to provide a less biased estimate of the linear discriminator's performance. The preliminary discriminant analysis identified two different texture measures--correlation and difference entropy--as the top features in discriminating between benign and malignant nodules. The linear discriminant analysis using these features correctly classified 28/31 cases (90.3%) of the training set. A less biased estimate, using jackknifed training and testing, yielded the same results (90.3% correct). The preliminary results of this approach are very promising in characterizing solitary nodules using quantitative measures extracted from HRCT images. Future work involves including contrast enhancement and three-dimensional measures extracted from volumetric CT scans, as well as the use of several pattern classifiers.

[1]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[2]  Ian T. Young,et al.  An Analysis Technique for Biological Shape. I , 1974, Inf. Control..

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

[4]  E A Zerhouni,et al.  CT of the solitary pulmonary nodule. , 1980, AJR. American journal of roentgenology.

[5]  Theodosios Pavlidis,et al.  Algorithms for Shape Analysis of Contours and Waveforms , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  E A Zerhouni,et al.  A standard phantom for quantitative CT analysis of pulmonary nodules. , 1983, Radiology.

[7]  Alex Pentland,et al.  Fractal-Based Description of Natural Scenes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  A. Proto,et al.  Pulmonary nodules studied by computed tomography. , 1985, Radiology.

[9]  S S Sagel,et al.  CT of the pulmonary nodule: a cooperative study. , 1986, Radiology.

[10]  E. Fishman,et al.  Solitary pulmonary nodules: CT assessment. , 1986, Radiology.

[11]  James M. Keller,et al.  Texture description and segmentation through fractal geometry , 1989, Comput. Vis. Graph. Image Process..

[12]  S J Swensen,et al.  CT evaluation of solitary pulmonary nodules: value of 185-H reference phantom. , 1991, AJR. American journal of roentgenology.

[13]  D. Cavouras,et al.  Image analysis methods for solitary pulmonary nodule characterization by computed tomography. , 1992, European journal of radiology.

[14]  H. K. Huang,et al.  Feature selection in the pattern classification problem of digital chest radiograph segmentation , 1995, IEEE Trans. Medical Imaging.

[15]  S. Swensen,et al.  Pulmonary nodules: CT evaluation of enhancement with iodinated contrast material. , 1995, Radiology.

[16]  J Konishi,et al.  Solitary pulmonary nodule: preliminary study of evaluation with incremental dynamic CT. , 1995, Radiology.

[17]  H P Chan,et al.  Image feature selection by a genetic algorithm: application to classification of mass and normal breast tissue. , 1996, Medical physics.

[18]  J. Vetter,et al.  Entrance skin exposure and mean glandular dose: effect of scatter and field gradient at mammography. , 1997, Radiology.

[19]  J G Goldin,et al.  Development and testing of image-processing methods for the quantitative assessment of airway hyperresponsiveness from high-resolution CT images. , 1997, Journal of computer assisted tomography.