Comparison detector and building method thereof as well as cervical cancer cell detection method
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A detector and prediction result technology, applied in the field of medical image processing, can solve problems such as research and attempts in the field of automatic screening of cervical cancer
Active Publication Date: 2019-07-16
湖南品信生物工程有限公司
View PDF7 Cites 16 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, there is no research and attempt in the field of automatic screening of cervical cancer
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
[0157] Such as Figure 2-9 As shown, the present embodiment provides a comparison detector, including a sequentially connected basic convolutional network, a feature pyramid network, a reference sample processing module, a region recommendation module, a head module and a prediction result screening module;
[0158] The basic convolutional network is constructed by a multi-layer convolutional module, which is specifically composed of several stages. As the stage increases, the resolution of the feature map decreases and the number of channels increases. Each stage consists of a certain number of convolutional layers. ;
[0159] The feature pyramid network is also constructed by a multi-layer convolution module, including the use of the basic convolutional network from the second stage to the last stage, and the last layer of features in each stage and the features above it. The corresponding feature m...
Embodiment 3
[0198] Example 3 The application example of the comparative detector described in Example 1 constructed by the method of Example 2 in the detection of cervical cancer cells
[0199] Such as Figure 2-9 As shown, the present embodiment provides a method for detecting cervical cancer cells based on the above-mentioned comparative detector, comprising the following steps:
[0200] Step 1. Construct the training set and test set of cervical microscopic images:
[0201] Collect microscopic images of the cervix and label the key components in the microscopic images of the cervix, and randomly select the microscopic images of the cervix after the labeling operation to construct a training set and a test set;
[0202] The operation of marking the key components in cervical microscopic images refers to marking the area where the key components in cervical microscopic images are located by systematically trained professionals (such as Figure 9 (a)), and record the center coordinate p...
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 provides a comparison detector and a building method as well as a cervical cancer cell detection method. The method applying the comparison detector to detect cervical cancer cell comprises the following steps that firstly, a class reference sample is selected by applying a t-SNE (t-distributedstochastic neighbor embedding) visualization method, and then the features of the class reference sample and a target detection image are extracted by applying a feature extraction network which is composed of a basic convolution network and a pyramid convolution network in the comparison detector; the extracted feature of the reference sample is processed by applying a reference sample processing module so as to obtain prototype expression of each class; a recommended region is obtained by applying a region recommending module, and features are obtained from a corresponding feature pyramid; and finally, the class of the recommended region is obtained by comparing the pyramid feature of the recommended region and the prototype expression of class, and fine tuning is conducted on the rectangular frame by utilizing the features of a candidate region. The method builds a target detection network which detects targets on small data sets, and can relieve the overfitting problem of the target detection network on the small data sets.
Description
technical field [0001] The invention belongs to the technical field of medical image processing, in particular to a comparison detector and its construction method and its application in cervical cancer cell detection, in particular to a comparison detector suitable for cervical cell microscopic image processing and its construction method and cervical cancer detection methods. [0002] technical background [0003] Cervical smear testing of microscopic images is one of the most common screening diagnostic tests performed in medical laboratories. It can assist physicians in diagnosing whether or not the cervix is cancerous or the degree of cancerous disease, and it is also an important indicator for monitoring physical health. The traditional method adopts manual reading, and experienced pathologists find several diseased cells from hundreds of thousands of cells on each liquid-based smear. Subjective factors and other influences are not suitable for large-scale promotion...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more