Real-Time Identification System of Magnetically Controlled Capsule Endoscopy Using Artificial Intelligence

• Conditions: Capsule Endoscopy

• Registration Number: NCT04203264
• Lead Sponsor: Changhai Hospital

Brief Summary

The aim of this study is to evaluate the performance of real-time auxiliary system based on artificial intelligence algorithm in lesion detection and quality control in magnetically controlled capsule endoscopy.

Detailed Description

Magnetically controlled capsule endoscopy (MCE) has been used in clinical practice for gastric examination, with high sensitivity and specificity of 90.4% and 94.7%, respectively.

Therefore, a real-time auxiliary system based on convolutional neural network deep learning framework was developed to assist clinicians to improve the quality in MCE examinations.

Patients referred for magnetically controlled capsule endoscopy (MCE) in the participating center were prospectively enrolled. After passage through the esophagus, physician will finish the gastric examination under magnetic steering with the real-time auxiliary system. Professional operators guarantee the integrity of the examination and the diagnostic results of professional endoscopist was used as the gold standard. The system diagnosis results was recorded at the same time. The sensitivity, delay time, specificity of lesions and anatomical landmarks will be analyzed.

Study Timeline

• Status Verified: 2019-12
• Study Start: 2019-12-16
• Study First Submitted: 2019-12-16
• Study First Submitted QC: 2019-12-16
• Last Update Submitted: 2019-12-16
• Study First Posted: 2019-12-18
• Last Update Posted: 2019-12-18
• Primary Completion: 2020-01-01
• Study Completion: 2020-01-01

Recruitment & Eligibility

• Status: UNKNOWN
• Sex: All
• Target Recruitment: 50

Inclusion Criteria

• With or without gastrointestinal complaints
• Scheduled to undergo a capsule endoscopy for both stomach and small bowel
• Signed the informed consents before joining this study

Exclusion Criteria

• Dysphagia or symptoms of gastric outlet obstruction, suspected or known intestinal stenosis, overt gastrointestinal bleeding, history of upper gastrointestinal surgery or abdominal surgery altering gastrointestinal anatomy
• Refused abdominal surgery to take out the capsule in case of capsule retention
• Implanted pacemaker, except the pacemaker is compatible with MRI
• Other implanted electromedical devices or magnetic metal foreign bodies
• Pregnancy or suspected pregnancy

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Sensitivity	up to 2 weeks	The sensitivity of lesions detected by system

Secondary Outcome Measures

Name	Time	Method
Delay time	up to 2 weeks	Average preprocessing and displaying times before and after the execution of system
Specificity	up to 2 weeks	The specificity of detected by system
Accuracy of anatomic landmarks identification	up to 2 weeks	Accuracy of anatomic landmarks ( cardia, fundus, body, lesser curvature, greater curvature, angle, antrum and pylorus) identified by real-time identification system
Completeness of real-time observation with assistance	up to 2 weeks	Whether the clinician observed all anatomic landmarks of stomach (cardia, fundus, body, angulus, antrum and pylorus).
Accuracy of heat map	up to 2 weeks	The rate of the highlighted area indicated in the lesion
Lesion detection yield	up to 2 weeks	The ratio of lesions detected by system to all lesions

Trial Locations

Locations (1)

Changhai Hospital; 🇨🇳 Shanghai, China