A dynamic lesion model for differentiation of malignant and benign pathologies

Abstract

Malignant lesions have a high tendency to invade their surrounding environment compared to benign ones. This paper proposes a dynamic lesion model and explores the 2nd order derivatives at each image voxel, which reflect the rate of change of image intensity, as a quantitative measure of the tendency. The 2nd order derivatives at each image voxel are usually represented by the Hessian matrix, but it is difficult to quantify a matrix field (or image) through the lesion space as a measure of the tendency. We conjecture that the three eigenvalues contain important information of the Hessian matrix and are chosen as the surrogate representation of the Hessian matrix. By treating the three eigenvalues as a vector, called Hessian vector, which is defined in a local coordinate formed by three orthogonal Hessian eigenvectors and further adapting the gray level occurrence computing method to extract the vector texture descriptors (or measures) from the Hessian vector, a quantitative presentation for the dynamic lesion model is completed. The vector texture descriptors were applied to differentiate malignant from benign lesions from two pathologically proven datasets: colon polyps and lung nodules. The classification results not only outperform four state-of-the-art methods but also three radiologist experts.

Vector textures derived from higher order derivative domains for classification of colorectal polyps

“…In this study, we look forward to expand upon the vector model introduced in ref. [ 26 ] to more deeply evaluate the image textures generated from the first- and second-order derivative information. Two differential operators, i.e., the gradient and Hessian operators, are employed to extract six local geometric measures, three of which are from the gradient operator and the other three are from the Hessian operator.…”