Lung disease recognition model training method, lung disease recognition method and device
A lung disease and recognition model technology, applied in the computer field, can solve problems such as long training time, large number of model parameters, poor residual channel to explore new features, etc., to achieve the effect of improving training speed, reducing parameter amount and model size
Pending Publication Date: 2022-03-15
CHINA MOBILE CHENGDU INFORMATION & TELECOMM TECH CO LTD +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In related technologies, the method of three-dimensional (3-dimension, 3D) target detection usually uses 3D residual network (ResNet) as the backbone network to extract features for lung nodule area to locate, but the residual channel is not good at exploring new features, At the same time, the number of model parameters of the network structure is too large, and the training time is long, which leads to low training efficiency of the lung disease recognition model.
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
[0073] The characteristics and exemplary embodiments of various aspects of the application will be described in detail below. In order to make the purpose, technical solution and advantages of the application clearer, the application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only configured to explain the application, not to limit the application. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by showing examples of the present application.
[0074] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily ...
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 training method of a lung disease recognition model and a lung disease recognition method and device. The method specifically comprises the steps that an electronic computed tomography (CT) image sample is obtained, and the CT image sample comprises a sample CT image and a sample label of the sample CT image; according to a preset first interception condition, carrying out interception operation on the CT image sample to obtain first volume data containing a disease region; inputting the first volume data into a first dual-path network of a lung disease recognition model to be trained, and determining position information of a disease region; according to a preset second interception condition and the position information, carrying out interception operation on the first volume data to obtain second volume data; and inputting the second volume data into a target classification network of a to-be-trained lung disease recognition model, and carrying out iterative training to obtain a target lung disease recognition model. According to the embodiment of the invention, the training speed of the lung disease recognition model can be improved.
Description
technical field [0001] The present application belongs to the field of computer technology, and in particular relates to a training method for a lung disease recognition model, a lung disease recognition method and device, equipment, and a computer storage medium. Background technique [0002] Usually, chest computed tomography (Computed Tomography, CT) images, as the most effective non-invasive detection technique for lung diseases, are widely used in lung disease screening and auxiliary diagnosis. For CT image classification and diagnosis, the localization detection of lung diseases with the help of deep learning model can not only improve the diagnostic efficiency, but also provide doctors with more objective and accurate diagnostic results, so it has important clinical application value. [0003] In related technologies, the method of three-dimensional (3-dimension, 3D) target detection usually uses 3D residual network (ResNet) as the backbone network to extract features...
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): G06T7/00
CPCG06T7/0012G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30061
Inventor 左东奇胡冉杰杨了唐明轩黄承基
Owner CHINA MOBILE CHENGDU INFORMATION & TELECOMM TECH CO LTD