Unlock instant, AI-driven research and patent intelligence for your innovation.

Biopsy area prediction method, image recognition method, device and storage medium

An image recognition and area technology, applied in the field of communication, can solve the problems of missed detection, low accuracy and effectiveness of biopsy areas, etc., and achieve the effect of improving accuracy and effectiveness, and reducing the probability of missed detection

Active Publication Date: 2020-03-17
腾讯医疗健康(深圳)有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, during the research and practice of the prior art, the inventors of the present invention found that because only fixed areas of the picture are intercepted, and some lesion areas are relatively small, therefore, the existing schemes are used to detect images ( Classification), it is easy to miss detection, resulting in low accuracy and effectiveness of biopsy area prediction

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
  • Biopsy area prediction method, image recognition method, device and storage medium
  • Biopsy area prediction method, image recognition method, device and storage medium
  • Biopsy area prediction method, image recognition method, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] This embodiment will be described from the perspective of a biopsy area prediction device. The biopsy area prediction device may be integrated in a network device, which may be a terminal or a server, where the terminal may include a tablet computer, a notebook computer or Personal computer (PC, Personal Computer), etc.

[0066] An embodiment of the present invention provides a method for predicting a biopsy area, including: collecting an image of a living body tissue to be detected, using a preset lesion area detection model to detect a lesion area on the image of a living body tissue, and if a lesion area is detected, using a preset The algorithm is used to preprocess the lesion area to obtain the area to be identified, and the preset lesion classification model is used to classify the area to be identified, and the predicted probability of the lesion corresponding to the area to be identified is obtained as the classification result, and the predicted probability of t...

Embodiment 2

[0112] According to the methods described in the previous embodiments, the following will take an example in which the biopsy area prediction device is specifically integrated in a network device for further detailed description.

[0113] (1) First, it is necessary to train the lesion area detection model and lesion classification model, which can be as follows:

[0114] (1) Training of lesion region detection model.

[0115] The network device collects multiple sample images of living tissue samples marked with diseased areas, and then trains the preset target detection model according to the sample images of living body tissue. For example, it can specifically determine the current The sample image of living body tissue that needs to be trained, and then input the current sample image of living body tissue that needs to be trained into the preset target detection model for detection to obtain the predicted lesion area, and the predicted lesion area and the marked lesion area...

Embodiment 3

[0153] On the basis of the above embodiments, the embodiments of the present invention also provide an image recognition method and device.

[0154] Wherein, the image recognition device can specifically be integrated in a network device, and the network device can be a terminal or a server, for example, see Figure 3a , the network device can collect images of living body tissues to be detected, for example, it can specifically receive images of living body tissues sent by some image acquisition devices, such as colposcopes or endoscopes (such as colposcope images or endoscope images, etc.), Then, classify the vital tissue image to obtain an image classification result; when the image classification result is a lesion, use a preset lesion area detection model to detect a lesion area on the vital tissue image, and if a lesion area is detected, then Use the preset algorithm to preprocess the lesion area, such as merging and resetting, to obtain the area to be identified, and th...

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

No PUM Login to View More

Abstract

The embodiment of the present invention discloses a biopsy area prediction method, image recognition method, device and storage medium; the embodiment of the present invention can collect the image of the living body tissue to be detected, and then use the preset lesion area detection model for the living body tissue The lesion area is detected on the image. If a lesion area is detected, the lesion area is preprocessed using a preset algorithm, and the preprocessed lesion classification model is used to classify the preprocessed area to be identified, and the classification result is the lesion to be identified. The predicted probability of the lesion corresponding to the region determines the region to be identified with the predicted probability of the lesion higher than the preset threshold as the biopsy region; this scheme can reduce the probability of missed detection and improve the accuracy and effectiveness of the prediction of the biopsy region.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a method for predicting a biopsy region, an image recognition method, a device and a storage medium. Background technique [0002] The biopsy area refers to the area where biopsy is performed in medical activities. Biopsy, referred to as biopsy, means to cut diseased tissue from a patient for pathological examination to assist clinicians in determining diseases. For example, cervical biopsy refers to taking a small or several pieces of tissue from the cervix for pathological examination, etc. etc. It is a relatively routine examination method in modern medical activities, and biopsy can provide the basis for subsequent diagnosis. [0003] The traditional biopsy and the determination of the biopsy area are all manually operated, and with the development of artificial intelligence (AI, Artificial Intelligence), people have gradually proposed the technology of realiz...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/45
Inventor 伍健荣贾琼孙星郭晓威周旋常佳
Owner 腾讯医疗健康(深圳)有限公司