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 r esolution CT (HRCT) images. High resolution CT images of 31 patients with s olitary pulmonary nodules and definitive diagnoses were obtained. The diagn oses of these 31 cases (14 benign and 17 malignant) were determined from ei ther radiologic follow-up or pathological specimens. Software tools were de veloped to perform the classification task. On the HRCT images, solitary no dules were identified using semiautomated contouring techniques. From the r esulting contours, several quantitative measures were extracted related to each nodule's size, shape, attenuation, distribution of attenuation, and te xture. A stepwise discriminant analysis was performed to determine which co mbination 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 pr ovide a less biased estimate of the linear discriminator's performance. The preliminary discriminant analysis identified two different texture measure s-correlation and difference entropy-as the top features in discriminating between benign and malignant nodules. The linear discriminant analysis usin g these features correctly classified 28/31 cases (90.3%) of the training s et. 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 m easures extracted from HRCT images. Future work involves including contrast enhancement and three-dimensional measures extracted from volumetric CT sc ans, as well as the use of several pattern classifiers. (C) 1999 American A ssociation of Physicists in Medicine.