Developing Echocardiography Image Quality Management System Based on Deep Learning

NCT05633732 | Unknown

• 1 other identifier: 2022-337-01
• Study Type: observational
• Target: 2,000
• Locations: 1 country
• Sites: 1

Brief Summary

To develop an echocardiography image quality management system based on deep learning to achieve objective and accurate automatic echocardiography image quality control. A total of 2000 patients performing transthoracic echocardiography were prospectively enrolled in the Department of Ultrasound Medicine of the Affiliated Drum Tower Hospital with Medical School of Nanjing University. The data of 8 TTE view segmentations were collected, including the views of the parasternal long axis of the left ventricle (PLAX\_LV), parasternal short axis of the large vessel level (PSAX\_GV), parasternal short axis of the mitral valve level (PSAX\_MV), parasternal short axis of the papillary muscle level (PSAX\_PM), parasternal short axis of the apical level (PSAX\_AP), apical four cavity (A4C), apical three cavity (A3C), apical two cavity (A2C). The data of 1500 patients were used as the training set, and the rest were used as the validation set. These video data were classified into corresponding view segmentations and analyzed by the Video Swin Transformed Model. Then, the scoring module of different view segmentations combined key frame extraction, image segmentation, video target recognition and video classification model were established. At the same time, the scores achieved by the automatic echocardiography image assessment system were compared with the artificial score. By constantly correcting and learning and eventually building an primary automated grading system. At last, the automatic echocardiography image assessment system was constructed and performed on the rest 500 patients.

Conditions

Echocardiography

Keywords

Echocardiography; Quality Management System; Deep learning; Artificial Intelligence

Outcome Measures

Primary Outcomes (2)

• the score of PSAX view

  the score of PSAX view by the echocardiography image quality management system

  12 months

• the score of apical view

  the score of apical view by the echocardiography image quality management system

  12 months

Study Arms (1)

Standardized View Group

The echocardiography view images of patients in this group are standardized.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

patients with standardized TTE views

You may qualify if:

• aged ≥18years, gender unlimited;
• Patients with standardized TTE views;
• Subjects participated in the study voluntarily and signed informed consent;

You may not qualify if:

• patients wirh incomplete standard TTE views;
• patients with poor sound transmission conditions.

Sponsors & Collaborators

• The Affiliated Nanjing Drum Tower Hospital of Nanjing University Medical School: lead
• Southeast University, China: collaborator

Study Sites (1)

Affiliated Drum Tower Hospital of Nanjing University Medical School

Nanjing, Jiangsu, 210008, China

RECRUITING

Related Publications (4)

• Thiebaut R, Thiessard F; Section Editors for the IMIA Yearbook Section on Public Health and Epidemiology Informatics. Artificial Intelligence in Public Health and Epidemiology. Yearb Med Inform. 2018 Aug;27(1):207-210. doi: 10.1055/s-0038-1667082. Epub 2018 Aug 29.

  PMID: 30157525 BACKGROUND

• Sengupta PP, Shrestha S. Machine Learning for Data-Driven Discovery: The Rise and Relevance. JACC Cardiovasc Imaging. 2019 Apr;12(4):690-692. doi: 10.1016/j.jcmg.2018.06.030. Epub 2018 Dec 12. No abstract available.

  PMID: 30553684 BACKGROUND

• Ueda D, Shimazaki A, Miki Y. Technical and clinical overview of deep learning in radiology. Jpn J Radiol. 2019 Jan;37(1):15-33. doi: 10.1007/s11604-018-0795-3. Epub 2018 Dec 1.

  PMID: 30506448 BACKGROUND

• Madani A, Arnaout R, Mofrad M, Arnaout R. Fast and accurate view classification of echocardiograms using deep learning. NPJ Digit Med. 2018;1:6. doi: 10.1038/s41746-017-0013-1. Epub 2018 Mar 21.

  PMID: 30828647 BACKGROUND

Central Study Contacts

Jing Yao, Phd

CONTACT

+8618905188727; w1835199709@163.com

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: November 21, 2022
• First Posted: December 1, 2022
• Study Start: December 30, 2022
• Primary Completion: December 31, 2024
• Study Completion: December 31, 2025
• Last Updated: February 23, 2023

Record last verified: 2022-09

Locations

CN (1)