Intelligent cervical cancer cell detection method based on liquid-based thin-layer cell detection technology TCT
A technology for cervical cancer cells and thin-layer cells, which is applied in neural learning methods, image enhancement, instruments, etc., can solve the problems of high labor intensity, time-consuming and labor-intensive, and high requirements for the professional and technical level of inspectors, and achieves the effect of reducing requirements.
Active Publication Date: 2021-06-11
ARMY MEDICAL UNIV
View PDF10 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] In order to solve the problems existing in the microscopic detection method of TCT inspection in the prior art, such as high requirements for the professional technical level of the detection personnel, high labor intensity, time-consuming and labor-intensive, etc., the present invention proposes a cervical Intelligent detection method of cancer 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
[0047] attached figure 2 It is a schematic flow chart of the intelligent detection method of cervical cancer cells of the present invention. It can be seen from the figure that the intelligent detection method of cervical cancer cells based on the liquid-based thin-layer cell detection technology TCT of the present invention includes the following steps:
[0048] Step S1, performing microphotography on the cell smears examined by the liquid-based thin-layer cytometry technique TCT, obtaining digital images with stained cells, and cutting them into RGB pathological images with a resolution of 2048*2048;
[0049] Step S2, using the fully convolutional network layer to perform cell detection on the 2048*2048 RGB pathological image to obtain the position information of a single pathological cell; including:
[0050] S201. An image processing module is set at the front end of the full convolution network layer to perform downsampling processing on the high-definition image obtaine...
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 an intelligent cervical cancer cell detection method based on liquid-based thin-layer cell detection technology TCT, and aims to solve the problems of high requirement on professional skill level of detection personnel, high labor intensity, time and labor consumption and the like in a microscopic detection method of TCT examination in the prior art. Comprising the following steps: carrying out photomicrography on a cell smear examined by a liquid-based thin-layer cell detection technology TCT to obtain a digital image with stained cells; performing cell detection on the pathological image by adopting a full convolutional network layer to obtain position information of a single pathological cell; dividing a single pathological cell image into four types of SCC, ASC-H, ASC-US and (HISL + LISL) by adopting a universal network; using the expert network to carry out binary classification judgment on single pathological cell images of HISL and LISL, so that five classifications of cervical cancer cells are realized. The invention has the beneficial technical effects that a strategy of firstly detecting the cell nucleus and then detecting the whole cell is adopted, so that the requirement on a data set is greatly reduced, and meanwhile, five classifications of the cervical cancer cells are realized.
Description
technical field [0001] The invention relates to a method for detecting cervical cancer cells in the field of biomedical image processing, in particular to an intelligent detection method for cervical cancer cells based on liquid-based thin-layer cell detection technology TCT. Background technique [0002] Liquid-based thin-layer cytology detection technology TCT is currently the most advanced cervical cancer detection technology in the world. out rate. In the TCT examination, the clinician uses a special sampler for TCT examination to collect cervical cell samples, then puts the collector into a vial containing cell preservation solution for rinsing, and then uses special equipment to disperse and filter the samples to reduce blood , mucus, and remnants of inflammatory tissue, thus, a thin well-preserved cell layer is obtained on the cell smear for further microscopic examination and diagnosis. [0003] At present, the microscopic detection of TCT examination is mostly car...
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 IPC IPC(8): G06T7/00G06T7/11G06T7/136G06K9/32G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06T7/136G06N3/08G06T2207/10061G06T2207/20104G06T2207/20081G06T2207/20084G06V10/25G06N3/045G06F18/241
Inventor 汪沛刘丽蒋冽肖晶晶吴毅李雯雯
Owner ARMY MEDICAL UNIV