Cell instance segmentation model construction method, cell instance segmentation method and device
A technology for segmentation models and construction methods, which is applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as poor cell segmentation results, and achieve the effect of improving segmentation performance and accuracy
Active Publication Date: 2022-07-12
ZHUHAI LIVZON CYNVENIO DIAGNOSTICS +1
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention provides a cell instance segmentation model construction method, cell instance segmentation method and device to solve the defect of poor cell segmentation effect in the dense cell scene in the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0056] In order to make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention. , not all examples. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0057] figure 1 A schematic flowchart of a method for constructing a cell instance segmentation model provided in an embodiment of the present invention, such as figure 1 As shown, the method includes:
[0058] Step 110: Perform mask labeling on each cell in the sample cell image to obtain the mask labeling value of each cell.
[0059] Specifically, after acquiring the sample cell image, mask labeling is perform...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention provides a cell instance segmentation model construction method, cell instance segmentation method and device, wherein the model construction method comprises: performing expansion and erosion operations on the mask labeling value of any cell, respectively, to obtain the mask expansion result and Mask the corrosion result, and determine the edge area of the cell based on the difference between the mask expansion result of the cell and the mask corrosion result; determine the weight value of each edge pixel in the edge area of any cell and the center of the cell The weight value of the pixel; the weight value of the edge pixel of any cell is greater than the weight value of the center pixel of the cell; based on the weight value of the edge pixel and the center pixel of each cell, the corresponding segmentation loss of each cell is determined separately, and based on For the segmentation loss corresponding to each cell, the model parameters of the cell instance segmentation model are updated. The present invention improves the segmentation performance of the cell instance segmentation model in the dense cell scene.
Description
technical field [0001] The present invention relates to the technical field of cell image processing, in particular to a method for constructing a cell instance segmentation model, a method and device for cell instance segmentation. Background technique [0002] In recent years, the detection of Circulating genetically abnormal cells (CACs) can predict the existence of tumors earlier, which has broad application prospects. At present, the method for detecting CACs is to accurately segment the CACs cells in the DF image by collecting dark field (DF, Dark Field) microscope images of peripheral blood, which is the basis for further automated analysis of individual cells. However, CACs cell segmentation has the following difficulties: 1. CACs cells are densely packed, so it is difficult to accurately segment dense cells; It is usually an irregular shape. How to accurately predict the irregular boundaries of each cell without overlapping the predicted boundaries of each cell is ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06V20/69G06V10/26G06V10/44G06V10/764G06V10/774G06K9/62
CPCG06F18/24G06F18/214
Inventor 王华嘉吕行邝英兰范献军黄仁斌叶莘
Owner ZHUHAI LIVZON CYNVENIO DIAGNOSTICS