Supercharge Your Innovation With Domain-Expert AI Agents!

Pulmonary embolism detection model training method and device, equipment and storage medium

A detection model and training method technology, applied in image data processing, instrumentation, computing, etc., can solve the problems of high labeling cost, high requirements for labelers, and difficulty in labeling lung CT images at the lesion level, so as to improve detection accuracy and reduce The effect of labeling costs

Pending Publication Date: 2022-07-08
GUANGZHOU SHIYUAN ELECTRONICS CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the lesion-level labeling of lung CT images is extremely difficult, and the requirements for the labeler are high, that is, the labeling cost is very high

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
  • Pulmonary embolism detection model training method and device, equipment and storage medium
  • Pulmonary embolism detection model training method and device, equipment and storage medium
  • Pulmonary embolism detection model training method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] figure 1 This is a flowchart of a method for training a pulmonary embolism detection model provided in Embodiment 1 of the present invention. This embodiment can be applied to the process of training a pulmonary embolism detection model. It is difficult to label lung CT images, and labeling takes a long time and requires labelers. In high cases, the method can be performed by the pulmonary embolism detection model training device provided in the embodiment of the present invention, and the device can be implemented by software and / or hardware, and is usually configured in computer equipment, such as figure 1 As shown, the method specifically includes the following steps:

[0044] S101. Obtain a lung CT image sequence sample.

[0045]Specifically, a CT (Computed Tomography) image, that is, an electronic computed tomography image, uses a precisely collimated X-ray beam, γ-ray, ultrasound, etc., together with a highly sensitive detector to make a connection around a certa...

Embodiment 2

[0063] Figure 2A , Figure 2B This is a flowchart of a pulmonary embolism detection model training method provided in Embodiment 2 of the present invention. This embodiment is refined on the basis of the above-mentioned Embodiment 1, and describes the network structure and processing process of the pulmonary embolism detection model in detail. And the specific process of multi-example learning, such as Figure 2A and Figure 2B As shown, the method includes:

[0064] S201. Obtain a lung CT image sequence sample.

[0065] In the embodiment of the present invention, the lung CT image sequence samples include multiple (usually several hundreds) lung CT image samples obtained by one CT examination, and multiple consecutive scans need to be performed for different regions to obtain multiple lung CT images. Part of the CT image samples can be reconstructed for a plurality of lung CT image samples subsequently to obtain a three-dimensional CT image.

[0066] The lung CT image s...

Embodiment 3

[0135] Figure 3A The third embodiment of the present invention provides a pulmonary embolism detection method, which can be used for pulmonary embolism detection. The method may be performed by the pulmonary embolism detection device provided in the embodiment of the present invention, and the device may be implemented in software and / or hardware, and integrated into the computer device provided in the embodiment of the present invention, such as Figure 3A As shown, the method specifically includes the following steps:

[0136] S301. Obtain a lung CT image sequence.

[0137] In the embodiment of the present invention, the lung CT image sequence includes multiple (usually several hundreds) lung CT images obtained by one CT examination, and multiple consecutive scans need to be performed for different regions to obtain multiple lung CT images. Afterwards, multiple lung CT images can be reconstructed to obtain a three-dimensional three-dimensional CT image.

[0138] S302. In...

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 a pulmonary embolism detection model training method and device, equipment and a storage medium. The pulmonary embolism detection model is trained by the weak supervision training method based on multi-example learning, the pulmonary embolism detection model is trained only by adopting an inspection-level annotation sample and an image-level annotation sample, and a focus-level annotation sample is not needed, so that the annotation cost is reduced. Besides, based on the characteristic that a doctor writes an image report, an examination-level label of whole lung examination (lung CT image sequence samples) and an image-level label of a single lung CT image sample are utilized at the same time, and the pulmonary embolism detection model is trained by adopting multi-level labels, so that the detection precision of the pulmonary embolism detection model can be improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of machine learning, and in particular, to a method, apparatus, device, and storage medium for training a pulmonary embolism detection model. Background technique [0002] Pulmonary embolism (PE) is a fatal disease caused by the shedding of emboli in the systemic circulation (most commonly thrombus) blocking the pulmonary blood vessels. Currently, CT pulmonary angiography is the main method for evaluating patients with suspected pulmonary embolism, but a CT scan usually contains hundreds of images, and doctors need to look carefully to find the emboli that are blocking the blood vessels, so as to further evaluate the condition. [0003] With the development of computer artificial intelligence, more and more computer-aided diagnosis systems are applied to clinical diagnosis, which can reduce the workload of doctors and improve the efficiency and accuracy of diagnosis. [0004] However, ...

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): G06T7/00
CPCG06T7/0012G06T2207/10081G06T2207/20076G06T2207/20081G06T2207/20084G06T2207/30061
Inventor 王静雯
Owner GUANGZHOU SHIYUAN ELECTRONICS CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com