Calcified false positive recognition method and device, calcified false positive recognition model training method and device, terminal and medium
A technology for identifying models and training methods, which is applied in the field of image recognition, can solve the problems of unfavorable calcification area morphology and separate identification, reduce the efficiency of doctor's film reading, etc., and achieve the effect of improving film reading efficiency and reducing false positive rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] Figure 1a It is a schematic flowchart of a calcification false positive recognition model training method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of training a breast calcification false positive recognition model. The method can be executed by the calcification false positive recognition model training device provided in the embodiment of the present invention, and the calcification false positive recognition model training device can be configured in the terminal provided in the embodiment of the present invention.
[0037] see Figure 1a , the calcification false positive identification model training method specifically comprises the following steps:
[0038] S110. Acquire a sample breast image and first candidate calcification points in the sample breast image, and mark false positive calcification points in the first candidate calcification points.
[0039] Wherein, the calcification false positive identif...
Embodiment 2
[0059] Figure 2a It is a schematic flow chart of a calcification false positive identification method provided by Embodiment 2 of the present invention. This embodiment is applicable to the situation of identifying false positive calcification points, especially when the false positive rate of the breast calcification detection model is high. False-positive calcifications identified by a pre-trained calcification false-positive recognition model. The method can be executed by the calcification false positive identification device provided in the embodiment of the present invention, and the calcification false positive identification device can be configured in the terminal provided in the embodiment of the present invention. The calcification false positive recognition method provided by the embodiment of the present invention belongs to the same inventive concept as the calcification false positive recognition model training method provided by the above embodiment, and the t...
Embodiment 3
[0072] image 3 It is a schematic structural diagram of a calcification false positive recognition model training device provided in Embodiment 3 of the present invention. The calcification false positive recognition device can be used to realize the calcification false positive recognition model training method provided by any embodiment of the present invention.
[0073] see image 3 , a calcification false positive recognition model training device, comprising:
[0074] The first acquisition module 310 is configured to acquire a sample mammary gland image and first candidate calcification points in the sample mammary gland image, and mark false positive calcification points in the first candidate calcification points;
[0075] The first processing module 320 is configured to crop the sample mammary gland image according to the first candidate calcification point, obtain a region image of the first candidate calcification point, and perform convolution processing on the re...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


