A Method for Structural Extraction of Image Report

An extraction method and structured technology, applied in the field of image report structured extraction, can solve the problems of low recognition accuracy and slow model convergence speed, so as to reduce the impact of input errors, ensure information accuracy, and reduce easy classification. The effect of wrong loss

Active Publication Date: 2022-06-24
浙江卡易智慧医疗科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention mainly solves the problems of slow convergence speed and low recognition accuracy of the image report entity text extraction in the existing technology; provides a structured image report extraction method, speeds up the convergence speed of the model and improves the accuracy of model prediction, Obtain an accurate structured relationship roadmap for imaging reports

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
  • A Method for Structural Extraction of Image Report
  • A Method for Structural Extraction of Image Report
  • A Method for Structural Extraction of Image Report

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0030] Example: a structured extraction method for image reports, such as figure 1 shown, including the following steps:

[0031] S1: Obtain unstructured radiological image texts and preprocess them; obtain unstructured radiological image report descriptions through the in-hospital RIS system or other data sources, and perform data preprocessing on the long texts obtained:

[0032] 1. Remove spaces in the text;

[0033] 2. Remove the brackets and the content in the brackets, most of the content in the brackets is some content that does not require structured extraction;

[0034] 3. Unify Chinese and English punctuation marks and full-width half-width numbers and letters, and delete repeated punctuation marks;

[0035] 4. Remove escape characters (such as newlines, indents, etc.);

[0036] 5. Vectorize the text and map it into the vector space.

[0037] S2: The preprocessed text is segmented and then normalized; the preprocessed text is segmented, the open source jieba word...

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 method for structured extraction of image reports, which comprises the following steps: acquiring unstructured radiographic image texts and performing preprocessing; performing word segmentation on the preprocessed texts and performing normalization processing; using attention focal loss as The optimization function optimizes the bert model, and performs entity recognition on the normalized text based on the optimized bert model; extracts the entity structured relationship based on the entity-extent bert model, and forms a structured report; the present invention extracts attention-focal loss The loss function increases the penalty for the wrong prediction of individual word labels that appear in the same entity, and can increase the loss of misclassified labels and reduce the loss of easy classification errors, so as to accelerate the convergence of the model and improve the accuracy rate the goal of.

Description

technical field [0001] The invention relates to the technical field of text recognition and extraction, in particular to a method for extracting a structured image report. Background technique [0002] Today, medical imaging has entered a data-driven era. Imaging data accounts for more than 90% of medical informatization data, and China's data volume accounts for almost 20% of the world's data. An ordinary tertiary hospital has about 3,000 imaging examinations a day, and 1.1 million imaging reports will be generated every year. This examination volume will increase when the scale of the hospital becomes larger. Can the world's largest data be effectively mined? Treasures of resources are of great value to the development of imaging disciplines, intelligent medical care and even the health industry. In 2007-2008, the ACR and RSNA published a series of guidelines on reporting quality, encouraging the construction of structured reports, improving the quality of imaging reports...

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): G06F16/35G06F16/36G06F40/295G16H15/00
Inventor 金倍建叶金德陈集房麻元兴
Owner 浙江卡易智慧医疗科技有限公司
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