Combined segmentation method for cell nucleuses and cytoplasm
A joint segmentation and cell nucleus technology, applied in neural learning methods, image analysis, image data processing, etc., can solve the problems of fine cell segmentation and other problems, and achieve the effects of helping grading and diagnosis, accurate segmentation results, and good cell contours and positions
Active Publication Date: 2021-06-22
HARBIN UNIV OF SCI & TECH
View PDF7 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In cell image processing, due to the influence of dyeing differences, uneven illumination and garbage impurities, cells adhere to each other and overlap, which brings difficulties to the fine segmentation of cells
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
[0039] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0040] Such as figure 1 The joint segmentation method of nucleus and cytoplasm provided in this paper mainly includes the following steps:
[0041] S1. Collect cell images for labeling and data enhancement;
[0042] S2. Build an improved UNet model for image segmentation;
[0043] S3. Initialize model parameters with self-supervised learni...
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 invention discloses a combined segmentation method for cell nucleuses and cytoplasm, and relates to the problem that the cell nucleuses and the cytoplasm are difficult to segment in a cell pathology picture analysis and diagnosis technology. The method for extracting the morphology, texture and appearance characteristics of the cell nucleus and the cytoplasm provides a basis for classification and detection of abnormal cells, and is one of key works of cell pathology image analysis and diagnosis. Accurate segmentation of the cell nucleus is the key point of extracting cell characteristics. However, due to overlapping among cells, large cellular morphology difference, poor cytoplasm boundary contrast and the like, no good segmentation method exists at present. In order to solve the problem, a model and a loss function are designed in combination with the characteristics of tasks, and model parameters are initialized by utilizing self-supervised learning so as to introduce priori knowledge. Experiments show that the method can effectively realize accurate segmentation of the cell nucleus and the cytoplasm in the cell pathology analysis process. The method is mainly applied to a cell nucleus and cytoplasm segmentation task in a cell analysis task.
Description
technical field [0001] The invention is applied to the cell nucleus and cytoplasm segmentation problem in the cytopathological image analysis technology. Background technique [0002] In recent years, with the development of economy and society, due to factors such as eating habits, social pressure, environmental pollution, and irregular work and rest, cancer has exploded on a global scale and has become a serious problem that endangers people's lives. Cytopathological diagnosis is made by collecting exfoliated cells for inspection. It is simple to obtain materials, widely used, and can make qualitative diagnosis. It is especially suitable for early diagnosis and screening, and it is worthy of large-scale promotion. Traditional pathological diagnosis relies entirely on the manual reading of images by pathologists "manually operated and observed with the naked eye". There are two major pain points: (1) The diagnostic accuracy of pathologists for cancer is generally low, and t...
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 Applications(China)
IPC IPC(8): G06T7/11G06N3/08
CPCG06T7/11G06N3/08G06T2207/30024G06T2207/30204G06T2207/20132G06T2207/20081G06T2207/20084
Inventor 何勇军秦健盖晋平
Owner HARBIN UNIV OF SCI & TECH