Image processing method and system, and image processing model training method and system

An image processing and model technology, applied in the field of image processing, can solve problems such as time-consuming and complicated operations, and achieve the effects of shortening time-consuming, reducing the probability of missed diagnosis, and speeding up the reading time

Active Publication Date: 2019-06-07
SHANGHAI UNITED IMAGING INTELLIGENT MEDICAL TECH CO LTD
View PDF5 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of complex operation and long time consumption caused by the separate processing of bone segmentation and bone fracture detection in the prior art, the present invention provides a training method and system for image processing and image processing models

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
  • Image processing method and system, and image processing model training method and system
  • Image processing method and system, and image processing model training method and system
  • Image processing method and system, and image processing model training method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] Such as figure 1 As shown, the embodiment of the present invention provides an image processing method, the method comprising:

[0073] S110. Acquire an image to be detected.

[0074] In this embodiment, after the image to be detected is acquired, a step of preprocessing the image to be detected is further included, and the preprocessing includes;

[0075] Perform resampling processing on the image to be detected, and sample the image to be detected into an image with a specified resolution;

[0076] Randomly take an image block from the resampled image;

[0077] The image block is normalized so that the gray distribution of the image is controlled within a specified range, such as between 0-1.

[0078] S120. Input the image to be detected into a neural network model for processing to obtain bone segmentation results, bone centerline segmentation results, and bone fracture detection results;

[0079] Wherein, the neural network model is determined based on machine t...

Embodiment 2

[0099] Such as Figure 4 As shown, the embodiment of the present invention provides another image processing method, the method comprising:

[0100] S210. Acquire the image to be detected.

[0101] This step is the same as S110 and will not be repeated here.

[0102] S220. Input the image to be detected into the neural network model for processing to obtain bone segmentation results, bone centerline segmentation results, and bone fracture detection results; wherein, the neural network model is determined based on machine training and learning based on training images, and Including coarse network model and fine network model.

[0103] The neural network model in this embodiment is specifically determined by machine training and learning based on training images and corresponding bone labels, bone midline labels, and bone fracture labels. The coarse network model in this embodiment is mainly used to perform positioning processing on the image to be detected, so as to improve...

Embodiment 3

[0132] Such as Figure 8 As shown, this embodiment discloses a training method of an image processing model, which is used to train the neural network model in Embodiment 1, and the method includes:

[0133] S310. Obtain training images;

[0134] Perform down-sampling processing on the training image, and sample the training image into a specified resolution image;

[0135] Randomly take an image block from the downsampled image;

[0136] The image block is normalized so that the gray distribution of the image is controlled within a specified range, such as between 0-1.

[0137] In this embodiment, the image block operation is performed on the image, and the image block training is used instead of the entire training image for training, mainly considering the limitation of the graphics processor (GPU) memory, and the image block training can be regarded as a kind of regularization means to improve the performance of the model.

[0138] S320. Train a neural network model ba...

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 invention discloses an image processing method and system, and image processing model training method and system. The image processing method comprises: obtaining a to-be-detected image; inputtingthe to-be-detected image into a neural network model for processing to obtain a bone segmentation result, a bone center line segmentation result and a bone fracture detection result; wherein the neural network model is determined by machine training learning based on a training image. The bone segmentation, bone center line segmentation and bone fracture detection functions are achieved at the same time through the trained deep learning network, the total consumed time can be shortened by 50%, the memory space of the model can be saved by 40%, and meanwhile a doctor can be helped to reduce the film reading burden, accelerate the film reading time, reduce the missed diagnosis probability and reduce the contradiction between the doctor and the patient.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image processing and a training method and system for an image processing model. Background technique [0002] With the development of the times, various chest traumas caused by accidents such as car accidents and falls often occur, and bone fractures (such as rib fractures) are common phenomena. X-ray plain films are less sensitive to bone fractures and are difficult to clearly show Chest and chest wall other lesions, so CT is the preferred imaging method for chest diseases, and often used as an important means of responsibility identification for chest trauma interviewees, especially after bone trauma. Although most skeletal fractures are not harmful, due to the different sentencing for the number of rib fractures in judicial appraisal, and the appearance of some skeletal fractures is hidden, tiny skeletal fractures are easy to miss diagnosis, and disputes a...

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 Applications(China)
IPC IPC(8): G06T7/187G06T7/136
Inventor 唐章源王誉吴迪嘉詹翊强
Owner SHANGHAI UNITED IMAGING INTELLIGENT MEDICAL TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap