Contour estimation method of dense fibroblasts

Abstract

The invention discloses a contour estimation method for dense fibroblasts. The contour estimation method comprises the following steps: S1, acquiring an image of the dense fibroblasts; s2, performingFrangi filtering on the dense fibroblast image, and obtaining a cell part boundary line and a cytoplasm part region through threshold segmentation to obtain an image with a part of contour; s3, obtaining contour control points in the image with the partial contour through a shortest distance search method; s4, for the contour control points on the boundary line of the same cell, reserving end points, presetting the step length m of the contour control points, and selecting one contour control point every m contour control points to obtain a fitting point set; and S5, performing curve fitting by adopting a B-spline approximation curve algorithm based on the fitting point set, and taking a fitted closed curve as a cell contour to complete contour estimation of the dense fibroblasts. The method solves the problem that dense fibrocyte contours are difficult to obtain by an existing algorithm.

Description

technical field [0001] The invention relates to the field of cell image segmentation, in particular to a method for estimating the outline of dense fiber cells. Background technique [0002] Cells are the basic unit of the structure and function of organisms. Researchers use microscopes to obtain cell images, and then use computer image analysis technology to obtain cell outlines, so as to perform cell counting, type identification and parameter measurement, which is helpful for medical clinical diagnosis and medical development. Cell image segmentation has always been one of the hot research directions, and academia has produced many segmentation algorithms. T. Bhagya et al. combined dilation erosion and histogram stretching, average filtering, and median filtering with four different segmentation algorithms: Otsu threshold segmentation, watershed segmentation, Canny edge detection, and K-means clustering. Combination, apply each combination to the segmentation of the acut...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned deficiencies in the prior art, a method for estimating the contour of dense fibroblasts provided by the present invention solves the problem that existing algorithms are difficult to perform good contour estimation on dense fibroblasts

Images