In the field of biomedicine, cell segmentation has always been one of the key and difficult points in cell imaging research, which is an important prerequisite for cell image recognition and counting. But so far, there is no universal, convenient and efficient segmentation method that can be universally applied to cell research. Therefore, the exploration of a universally applicable, convenient and efficient segmentation method has always been an important topic in the field of biomedical research.
—
The concept of cell segmentation?
Cell segmentation relies on a simple but basic concept: the segmented cells must have a different signal than the background. Cell segmentation refers to dividing the cell image into several disjoint regions according to the characteristics of grayscale, color, geometry, etc., so that these characteristics show consistency or similarity in the same region, and show obvious differences between different regions. Simply put, it is to combine the components of the cell itself and use various means and methods to distinguish the cell from the background.
—
What are the traditional cell segmentation techniques?
1. Threshold segmentation
Threshold segmentation is a traditional image segmentation method, which is simple, small in calculation, and stable in performance, especially suitable for images where the target and background occupy different gray levels. However, due to the complexity of the cell image and the uneven illumination of the microscopic image, the segmentation situation shown in the figure below will occur, and the color deviation of the background will have a large sensitivity and cause abnormal segmentation effect.
2. Segmentation based on edge detection
The purpose of edge detection is to identify points in a digital image where the brightness shift is significant. It is able to quickly and accurately find the edge, so that the grayscale or color information in the area is determined by the edge, so as to achieve fast segmentation of the image. However, due to the transparency of the cell, the edge information gradient will be small, resulting in the loss of gradient information and incomplete segmentation.
3. Watershed segmentation
This segmentation method does not require cells to be similar in size, shape and color, nor does it require the contact points to be very different, which is an advanced segmentation method. But in practical applications, due to the making of sections and the dispersion of the cells themselves, there may be two or more cells adhering in one way under the microscope, that is, cell adhesions. Watershed segmentation does not allow for the detailed separation of adhesion cells, which can lead to misidentification, etc.
—
Cellaview's cell segmentation effect?
In order to solve the problems of traditional cell segmentation methods and comprehensively develop a more universal, convenient and efficient cell segmentation method, Cellaview based on a new generation of image signal separation technology, relying on the technical support of Fudan University, Hong Kong University of Science and Technology and other universities, has carried out in-depth research and development of cell segmentation algorithms, and finally developed a cell segmentation method that can solve the problems of over-dependent parameters, uneven background, cell bonding and other problems in traditional methods, and has a good segmentation effect, the effect is as follows.
Cellaview's cell image segmentation method takes automatic, accurate, fast and adaptive as the research goal, and pays attention to clinical application, reducing the dependence on image morphological operation in the traditional method, the algorithm is efficient and accurate, the results are ideal, and the segmentation results have good robustness to texture details, which is generally consistent with the judgment of the human visual system。
Based on such a convenient and efficient cell segmentation method, Cellaview is perfectly suitable for most cell growth studies such as cell scratching, confluency recognition, organoid culture monitoring, tumor spheroid proliferation monitoring, embryonic stem cell growth monitoring, etc., which provides great help for cell quality control and monitoring.