Detection method based on medical image, and model training method and device
A technology of medical images and detection methods, applied in the field of intelligent medical care, can solve the problems of uniform setting of difficult mammography images and generalization of experience thresholds that cannot be reached.
Active Publication Date: 2019-11-19
TENCENT TECH (SHENZHEN) CO LTD
View PDF3 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Considering the impact of the hardware environment on mammography images, it is difficult to set a unified empirical threshold for diverse mammography images, resulting in different hospitals needing to learn empirical thresholds separately, which cannot achieve the effect of generalization of experience thresholds
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
[0106] The embodiment of the present application provides a medical image-based detection method, model training method and device, which can use the neural network model to detect calcification on any medical image, and further detect benign and malignant areas with calcification without considering The influence of the hardware environment on medical images, and there is no need to set an empirical threshold to judge the lesion, thereby improving the accuracy and convenience of detection.
[0107]The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein, for example, can be practiced in sequences other than those illustrated ...
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 medical image-based detection method, which is applied to the field of artificial intelligence, can be specifically applied to the field of intelligent medical treatment, andcomprises the steps of obtaining a calcification probability label of a to-be-detected medical image through a first neural network model, the to-be-detected medical image being a molybdenum target image; if the calcification probability label meets the calcification condition, extracting a calcification region from the to-be-detected medical image; obtaining a malignant calcification probabilitylabel of the calcified area through a second neural network model, the malignant calcification probability label being used for representing the probability that a malignant calcification situation exists in the calcified area, and both the second neural network model and the first neural network model belonging to a medical image detection model; and generating a malignant calcification positioning result according to the malignant calcification probability label. The invention further discloses a related device. According to the invention, calcification detection can be carried out on the molybdenum target image by using the neural network model, and benign and malignant detection is further carried out on the calcified area, so that the detection accuracy and convenience are improved.
Description
[0001] This application is a divisional application of a Chinese patent application submitted to the China Patent Office on February 14, 2019, with the application number 201910116648.8, and the title of the invention is "A medical image-based detection method, model training method and device". technical field [0002] The present application relates to the field of intelligent medical care, in particular to a medical image-based detection method, a model training method and a device. Background technique [0003] Mammography is the first choice for the diagnosis of breast diseases at present, and it is also the easiest and most reliable non-invasive detection method. It is relatively painless, easy to implement, and has high resolution and good repeatability. The images obtained can be compared before and after. It is not restricted by age and body shape, and it is currently used as a routine inspection. [0004] Calcification is one of the most important clues in the diag...
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): G06T7/00G06T7/11G06N3/04G06N3/08G16H50/20
CPCG06T7/0012G06T7/11G06N3/08G16H50/20G06T2207/30068G06T2207/30096G06T2207/10081G06T2207/20081G06T2207/20084G06N3/045
Inventor 田宽江铖
Owner TENCENT TECH (SHENZHEN) CO LTD