Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Topic Model-Based Approach to Abnormality Detection in Chest X-ray Diagnosis Reports

A diagnostic report and topic model technology, applied in medical reports, healthcare informatics, instruments, etc., can solve problems such as deviations in abnormal point detection, inability to be classified as abnormal, and poor results

Active Publication Date: 2022-06-24
KUNMING UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The text description of the diagnosis report is free, and some images describe symptoms or diseases that appear less frequently, but they cannot be classified as abnormal, so the detection of abnormal points will be biased
The diagnostic report data is high-dimensional and sparse, and the traditional mapping function is used to perform contextual feature matching, which is not effective

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 Topic Model-Based Approach to Abnormality Detection in Chest X-ray Diagnosis Reports
  • A Topic Model-Based Approach to Abnormality Detection in Chest X-ray Diagnosis Reports
  • A Topic Model-Based Approach to Abnormality Detection in Chest X-ray Diagnosis Reports

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Example 1: as figure 1 As shown, a method for detecting anomalies in chest X-ray diagnostic reports based on a subject model, the specific steps of the method are as follows:

[0037] Step1. Entity extraction of diagnosis report: The core content of diagnosis report is image description and diagnosis conclusion. According to the characteristics of diagnosis report, entity extraction of diagnosis report based on LSTM-CRF model is proposed;

[0038] Step 2. Entity feature expansion and supplementation: The entity extracted in Step 1 is extended and supplemented by features, and the nature of the diagnosis is added to the conclusion part, and matched with the symptom entity in the image description;

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 relates to a method for detecting abnormality in a chest X-ray diagnosis report based on a subject model, and belongs to the technical field of computer natural language processing. The present invention first proposes the entity extraction of the diagnosis report based on the LSTM-CRF model according to the characteristics of the diagnosis report itself; then, according to the domain knowledge and the template, the diagnosis report is effectively extended to alleviate the problem of data sparseness; the image description is obtained by using the improved LDA model The example subject distribution of the two diagnostic reports and the diagnosis conclusion; whether the example subject distribution obtained by calculating and comparing the image description entity and the diagnosis conclusion entity matches can be used to detect abnormal diagnosis reports; the detection accuracy of the present invention is high.

Description

technical field [0001] The invention relates to a method for detecting abnormality in a chest X-ray diagnostic report based on a subject model, and belongs to the technical field of computer natural language processing. Background technique [0002] Chest X-rays are the preferred choice for patients' chest examination, and play an important role in the diagnosis and treatment of patients. Doctors write chest X-ray diagnostic reports based on their own experience and habits. The core content of the diagnostic report is image description and diagnostic conclusion. These two parts are important references to assist doctors in diagnosis and patient treatment, and are also the key to abnormal detection of diagnostic reports. information. There is considerable subjectivity in the writing of diagnostic reports by doctors, which may lead to misinterpretation of the contents of the image description due to lack of experience or fatigue, resulting in missed diagnosis and misdiagnosis...

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): G16H15/00G06F40/295G06F40/30
CPCG16H15/00
Inventor 黄青松殷宁波尤诚诚刘利军冯旭鹏
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com