Analytical methods and systems that integrate annotation, data, project management, and non-programmatic modeling

A data processing and data technology, applied in medical simulation, medical automated diagnosis, computer-aided medical procedures, etc., can solve the problems of reducing research efficiency, data management difficulties, and occupying researchers' time, so as to reduce labeling errors and improve experimental efficiency , the effect of improving the labeling efficiency

Active Publication Date: 2021-06-25
浙江医准智能科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Intelligent medical image analysis includes a series of complex processes such as data collection, data labeling, feature extraction, and data analysis. However, it is difficult for current mainstream scientific research platforms to provide a series of complete and flexible tools to help researchers complete the entire process of medical image analysis.
Researchers need to switch between different software to complete each step in the research project, resulting in difficulties in data management and complicated operation steps
Especially for the data analysis step, the modeling process through traditional statistical and machine learning tools is complicated. For example, writing codes through tools such as Python, R language, and SAS not only requires high engineering literacy of researchers, but also takes up a lot of complicated coding work. It consumes a lot of time for researchers and reduces research efficiency
Some graphical tools can only provide a limited set of preset experimental procedures. Although they meet some of the needs of medical researchers, they are not flexible enough, and it is difficult for researchers to adjust experiments.

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
  • Analytical methods and systems that integrate annotation, data, project management, and non-programmatic modeling
  • Analytical methods and systems that integrate annotation, data, project management, and non-programmatic modeling
  • Analytical methods and systems that integrate annotation, data, project management, and non-programmatic modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] Such asfigure 1 As shown, a scientific research platform system of the present invention is shown, including: a data labeling system, a radiomics feature extraction system, a data analysis system, a project management system, and a user authority management system.

[0080] The user rights management system organizes users according to project groups. Users have different roles in the system, and users with the right to edit roles can assign different rights to different roles. Users can view datasets and research projects created by other members of the same project group. The user authority management system saves the user's account number, password, project group, role and other information, and sends the user's corresponding data set and scientific research project information according to the user account number and password. The system presets an administrator account, which has full authority of the account system. The permissions of the account system include: ...

Embodiment 2

[0082] Depend on figure 2 The flow chart of the data labeling system of the present invention is shown. The data labeling system organizes and manages user data sets, including: data import module, label label configuration module, data label module, semi-automatic label module and data information display module.

[0083] figure 2 It can be seen that the data import module can be connected to different data sources, transform the data from different data sources into structured data archives and write its specific information into the annotation database; For image data, after the user selects data import, the module records the image information imported by the user. This module also supports the user to upload local images and archives the images uploaded by the user.

[0084] When users create a new dataset, they first need to configure the label information that needs to be labeled. Annotation tags can be divided into two types: (1) data composed of "key-value" pairs...

Embodiment 3

[0089] image 3 The flow of the medical radiomics feature extraction system of the present invention is shown. The radiomics feature extraction system is separated from the data analysis system. When configuring the labeling label in the labeling system, the user can configure whether to perform radiomics feature extraction and the corresponding radiomics feature extraction parameters for data of a certain modality.

[0090] When the user completes the annotation submission of a sample, the data annotation module requests the radiomics feature extraction system to send relevant image information and annotation information while saving the new annotation. After receiving the request, the radiomics feature extraction system runs the radiomics feature extraction program in the background to perform heavy feature extraction calculations. After the calculation is completed, the radiomics feature extraction system requests the data labeling module and sends the feature extraction r...

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 present invention proposes a medical imaging scientific research platform system integrating data collection-data labeling-feature extraction-data analysis and model building-model evaluation and prediction. The system has the advantages of flexible configuration, reducing labeling errors, and improving labeling efficiency. At the same time, it is suitable for those who lack engineering experience to use clinical data to realize experimental analysis.

Description

technical field [0001] The present invention relates to an information processing device and method, in particular to an analysis method and system for integrating labeling, data, project management and non-programming modeling. Background technique [0002] The way of medical research is changing. On the one hand, the rapid growth of medical data provides a lot of material for research; on the other hand, doctors devote a lot of time and energy to work and research. As a result, artificial intelligence entered medical research, and doctors discovered clinical needs. By cooperating with artificial intelligence companies, they jointly carried out data processing and analysis to establish models, and quickly produced scientific research results. However, this cooperation method has certain limitations due to factors such as explosive growth in demand, high communication costs, and low efficiency. If doctors can independently apply artificial intelligence to conduct clinical r...

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 Patents(China)
IPC IPC(8): G16H50/50G16H50/20G16H30/00
CPCG16H30/00G16H50/20G16H50/50
Inventor 刘浩吴日城庄雯璟冯赛张佳琦王子腾吕晨翀丁佳胡阳
Owner 浙江医准智能科技有限公司
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