Title:
DEEP LEARNING-BASED ELECTROCARDIOGRAM DATA NOISE REMOVAL SYSTEM
Document Type and Number:
WIPO Patent Application WO/2023/022493
Kind Code:
A8
Abstract:
The present invention provides a deep learning-based electrocardiogram data noise removal system comprising: an electrocardiogram measurement unit (110) for measuring electrocardiogram data for each lead from the body of an examinee; and a style-based electrocardiogram generation unit (120) for extracting a unique style from the electrocardiogram data measured by the electrocardiogram measurement unit (110) by reflecting the characteristics of the examinee and a measurement method through an electrocardiogram generation deep learning algorithm (121), which is constructed by pre-learning low-noise electrocardiogram data for each lead and a learning dataset of a unique style of electrocardiogram data for each lead on the basis of multiple pieces of electrocardiogram data, and on the basis of the extracted unique style, converting the measured electrocardiogram data into electrocardiogram data of a specific lead style in which noise is not included and generating the converted electrocardiogram data of a specific lead style. Therefore, by the configuration described above, the present invention can generate electrocardiogram data from which noise has been removed and increase the accuracy of disease diagnosis prediction.
Inventors:
KWON JOON MYOUNG (KR)
Application Number:
PCT/KR2022/012244
Publication Date:
November 23, 2023
Filing Date:
August 17, 2022
Export Citation:
Assignee:
MEDICALAI CO LTD (KR)
International Classes:
A61B5/346; A61B5/00; A61B5/308; A61B5/327; G16H50/20; G16H50/70
Attorney, Agent or Firm:
AHN, Jihwan (KR)
Download PDF: