Automatic image segmentation with linear clustering for quantification of neointimal formation after surgical vein grafting.

OBJECTIVE

To identify extracellular matrix deposition on combined Masson elastin stains from cross-sectional, fixed vein grafts.

STUDY DESIGN

Source vectors from RGB components of color images are transformed into new vectors with most of the energy concentrated in fewer coefficients based on the eigenvalues and eigenvectors of their co-variance matrix so their dimension can be reduced for efficient computation and analysis. The vectors are distributed in a triangular shape in which most vectors are located in a long, narrow strip that can be approximated by a straight line while a separate group of vectors from collagen areas form a loose cluster away from the line. An iterative procedure has been developed for the representative vectors in the 2 centroids for linear and circular clusters. The linear centroid consists of all vectors in a straight line, and the centroid of the circular cluster is a single vector. Vector classification is based on the measure of its distance to each of the 2 centroids.

RESULTS

The automatic segmentation of the collagen content pixels in green-blue matches the image background color.

CONCLUSION

The procedure automatically quantifies and characterizes the neointimal deposition after surgical vein grafting in mice.