Method and device for detecting medical images
A medical image and image feature technology, applied in the field of image analysis, can solve the problems of missed detection of detection targets, detection ability to be improved, uncertainty, etc.
Active Publication Date: 2022-05-13
浙江医准智能科技有限公司
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the medical image detection based on this algorithm needs to manually set the anchor size of the detection target, so it can only detect the detection target close to the anchor size
[0004] In some cases, the actual size of the detection target has a strong uncertainty
The detection based on the anchor size may cause some detection targets with a large deviation from the anchor size to be missed
Therefore, the detection ability of such detection schemes still needs to be improved.
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
[0045] In order to make the purpose, features, and advantages of the application more obvious and understandable, the technical solutions in the embodiments of the application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the application. Obviously, the described The embodiments are only some of the embodiments of the present application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of this application.
[0046] Application overview
[0047] In the prior art, in the process of using image analysis technology to detect medical images to determine the detection target, it is necessary to set the anchor size of the detection target, that is, to estimate the size range of the detection target. In other words, this type of detection scheme can only detect objects clo...
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 application discloses a method and device for detecting a medical image, including: using a feature analysis structure in a detection network to determine a first image feature corresponding to an image to be detected; the feature analysis structure includes a first encoding structure and a first decoding structure structure; the first decoding structure includes a channel attention module and a spatial attention module; the feature detection structure in the detection network is used to determine the first detection target in the to-be-detected image according to the first image feature; Based on the above structure, the detection process in the present application no longer needs to set the anchor size, and can detect detection targets of different sizes, which solves the problem that detection targets with a large deviation from the anchor size in the prior art are likely to be missed. Inspection of technical problems.
Description
technical field [0001] The present application relates to the technical field of image analysis, in particular to a method and device for detecting medical images. Background technique [0002] In the medical field, malignant tumors have a very high lethality rate, which poses a great threat to the health and life of patients. Clinically, tumors can be detected and screened through medical images. The observation and recognition of traditional medical images are done manually by doctors, which requires human resources. [0003] With the advancement of artificial intelligence technology, image analysis technology based on artificial intelligence can be used at this stage to realize the detection of medical images. For example, the Faster RCNN two-stage detection algorithm can be used to detect medical images. However, the medical image detection based on this algorithm needs to manually set the anchor size of the detection target, so it can only detect the detection target...
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): G06T7/00G06N3/02G06N3/08
CPCG06T7/0012G06N3/08G06N3/02G06T2207/10081G06T2207/10132G06T2207/10088G06T2207/20081G06T2207/20084G06T2207/30096G06T2207/30064
Inventor 孙凯张佳琦安南胡阳王立威丁佳吕晨翀
Owner 浙江医准智能科技有限公司