Segmentation and Pore Structure Estimation in SEM Images of Tissue Engineering Scaffolds Using Genetic Algorithm.

Abstract

A python computer package is developed to segment and analyze scanning electron microscope (SEM) images of scaffolds for bone tissue engineering. The method requires only a portion of an SEM image to be labeled and used for training. The algorithm is then able to detect the pore characteristics for other SEM images acquired at different ambient conditions from different scaffolds with the same material as the labeled image. The quality of SEM images is first enhanced using histogram equalization. Then, a global thresholding method is used to perform the image analysis. The thresholding values for the SEM images are obtained using genetic algorithm (GA). The image analysis results include pore distributions of pore size, pore elongation and pore orientation. The results agree satisfactorily with the experimental data for the chitosan-alginate porous scaffolds considered. Applications of the method developed for image segmentation is not limited to scaffold pore structure analysis. The method can also be used for any SEM image containing multiple objects such as different types of cells and subcellular components.