Automatic cell counting for phase‐contrast microscopic images based on a combination of Otsu and watershed segmentation method

Abstract

Cell counting plays a vital role in biomedical researches. However, manual cell counting is time-consuming, laborious, and low efficiency and has a high counting error rate problem. An automatic counting approach for Hela cells of phase-contrast microscopic images is proposed based on the combination of Otsu and watershed segmentation methods to solve the mentioned issues. Firstly, image preprocessing is performed. Secondly, the Otsu method was used to obtain an automatic global optimal threshold for segmentation to achieve batch counting of images. Thirdly, the marker watershed was performed to separate adherent cells and to avoid oversegmentation simultaneously. Finally, cells in phase-contrast microscopic images were counted by detecting the numbers of connected domains in the binary image.

Cerebral Angiography under Artificial Intelligence Algorithm in the Design of Nursing Cooperation Plan for Intracranial Aneurysm Patients in Craniotomy Clipping

“…The intraclass variance, the between-class variance, and the total variance of the overall image when the gray level was t were represented, respectively. In such a situation, the optimal threshold selection could be simplified to finding the value of threshold t. Thus, it satisfied any one of the criteria to obtain the maximum value in equation (12), and these three criteria were equivalent to each other. As the evaluation standards were set, the threshold could be satisfied that it maximized the degree of separation between the target and the background.…”

“…When some parts of the target and the background are misclassified mutually, the difference between the two parts will be reduced. Thus, the maximum between-class variance means the smallest probability of being misclassified [12][13][14]. ICAC is one of the common methods for the treatment of intracranial aneurysms, but the surgery is traumatic to a certain extent.…”

An Improved Adaptive Median Filtering Algorithm for Radar Image Co-Channel Interference Suppression

“…Suppose that the tangential interference ratio obtained in the previous step is represented in levels . Let denote the number of interference points at ratio level i , and D denote the total number of interference points [ 37 ]. The probability of occurrence of level i is given by .…”

Deep Learning and Computer Vision: Machine Learning Analysis and Image Processing of Puromycin Treated Microscopy

“…Image histograms are in large part used to gain insight into specific image statistics (or features) needed for image processing. (Lin et al, 2022) proposed an automated counting technique for Hela cells of phase-comparison microscopic picture primarily based totally at the mixture of Otsu and watershed segmentation techniques to remedy the cited issues. The Otsu approach become used to gain an automated international choicest threshold for segmentation to attain batch counting of picture relation analysis of microscopic images.…”

“…A specific image may be taken as a feature of two variables say f(a,b) represented in a matrix structure where each location or position of embedded object within a specific frame can be referenced by a single matrix. Image processing itself in part involves enhancement, recovery, evaluation and compression through finite precision numerical analysis (Lin et al, 2022). This, in turn gives ability for concise image segmentation, aspect ratios, and texture and feature engineering.…”