Back to resultsClinical Research on a Novel Deep-learning Based System in Mediastinal Endoscopic Ultrasound Scanning
Primary Purpose
Mediastinum Disease
Status
Recruiting
Phase
Not Applicable
Locations
China
Study Type
Interventional
Intervention
AI system
Sponsored by
About this trial
This is an interventional other trial for Mediastinum Disease focused on measuring EUS, AI, Quality Control, training
Eligibility Criteria
Inclusion Criteria: 1. Age ≥18 years old, <80 years old 2.Patients who need endoscopic ultrasonography of mediastinum; 3. Agree to participate in this study and sign the informed consent form. Exclusion Criteria: Subjects who meet any of the following criteria cannot be selected for this trial: First. The patient's physical condition does not meet the requirements of conventional endoscopic ultrasonography: Poor physical condition, including hemoglobin ≤8.0g/dl, severe cardiopulmonary insufficiency, etc. Anesthesia assessment failed Pregnancy or breastfeeding In the acute stage of chemical and corrosive injury, it is very easy to cause perforation Recent acute coronary syndrome or clinically unstable ischemic heart attack Heart disease patients with right-to-left shunt, patients with severe pulmonary hypertension (pulmonary artery pressure> 90mmHg),patients with uncontrolled systemic hypertension and patients with adult respiratory distress syndrome. Second. Disagree to participate in this study. Third. There are other problems that do not meet the requirements of this research or that affect the results of the research: Mediastinal lesions have previously undergone surgery or radiotherapy and chemotherapy; Mental illness, drug addiction, inability to express themselves or other diseases that may affect follow-up.
Sites / Locations
- The Third Xiangya Hospital of Central South UniversityRecruiting
Arms of the Study
Arm 1
Arm 2
Arm Type
Experimental
No Intervention
Arm Label
AI-assisted group
non-assisted group
Arm Description
Subjects will undergo EUS examination with the assistance of AI system.
Subjects will undergo EUS examination without the assistance of AI system
Outcomes
Primary Outcome Measures
Accuracy
The number of correctly classified images divided by the total number of images.
intersection over union (IoU)
It was defined as the relative area of overlap between the predicted bounding box(A) and the ground-truth(B) bounding box.
Precision
When the IoU was greater than the threshold, the prediction was true positive(TP); when the IoU was less than the threshold, the prediction was false positive(FP).When the model segmentation area was equal to 0, it was false negative(FN).Precision=TP/(TP+FP)
Recall
Recall=TP/(TP+FN)
Dice
Dice=2TP/(2TP+FP+FN)
Secondary Outcome Measures
Cohen's kappa coefficient
This data is to evaluate the agreement between the model and the endoscopists.
Full Information
NCT ID
NCT05792280
First Posted
March 17, 2023
Last Updated
March 29, 2023
Sponsor
The Third Xiangya Hospital of Central South University
1. Study Identification
Unique Protocol Identification Number
NCT05792280
Brief Title
Clinical Research on a Novel Deep-learning Based System in Mediastinal Endoscopic Ultrasound Scanning
Official Title
Clinical Research on Navigation and Quality Control System of Mediastinal Ultrasound Endoscopy Based on Deep Learning
Study Type
Interventional
2. Study Status
Record Verification Date
March 2023
Overall Recruitment Status
Recruiting
Study Start Date
December 1, 2022 (Actual)
Primary Completion Date
December 31, 2023 (Anticipated)
Study Completion Date
January 31, 2024 (Anticipated)
3. Sponsor/Collaborators
Responsible Party, by Official Title
Sponsor
Name of the Sponsor
The Third Xiangya Hospital of Central South University
4. Oversight
Studies a U.S. FDA-regulated Drug Product
No
Studies a U.S. FDA-regulated Device Product
No
5. Study Description
Brief Summary
The goal of this clinical trial is to develop and verify the auxiliary role of the artificial intelligence system in mediastinal ultrasound endoscopic scanning. The main questions it aims to answer are as follows: 1.The comparison of the image recognition accuracy between the artificial intelligence system and the ultrasound endoscopist; 2. Whether the artificial intelligence system can improve the efficiency of the mediastinum scanning for the ultrasound endoscopist. Participants will undergo mediastinal EUS with or without the assistance of the artificial intelligence system.
Detailed Description
In this study, a total of 200 cases of mediastinal endoscopic ultrasound scanning videos will be collected. First of all, an artificial intelligence system based on deep learning for the navigation and quality control of mediastinal endoscopic ultrasonography will be established. Secondly, the artificial intelligence system will be used to identify the site and anatomical structure of the mediastinal ultrasound endoscope, and the results of the artificial intelligence system's station recognition will be compared with the results of the endoscopist's station recognition. Finally, compare the image recognition speed, image recognition accuracy and precision of endoscopists with and without the assistance of artificial intelligence system.
6. Conditions and Keywords
Primary Disease or Condition Being Studied in the Trial, or the Focus of the Study
Mediastinum Disease
Keywords
EUS, AI, Quality Control, training
7. Study Design
Primary Purpose
Other
Study Phase
Not Applicable
Interventional Study Model
Parallel Assignment
Masking
ParticipantInvestigator
Allocation
Randomized
Enrollment
200 (Anticipated)
8. Arms, Groups, and Interventions
Arm Title
AI-assisted group
Arm Type
Experimental
Arm Description
Subjects will undergo EUS examination with the assistance of AI system.
Arm Title
non-assisted group
Arm Type
No Intervention
Arm Description
Subjects will undergo EUS examination without the assistance of AI system
Intervention Type
Device
Intervention Name(s)
AI system
Intervention Description
Patients will undergo EUS examination with the assistance of AI system.
Primary Outcome Measure Information:
Title
Accuracy
Description
The number of correctly classified images divided by the total number of images.
Time Frame
1 year
Title
intersection over union (IoU)
Description
It was defined as the relative area of overlap between the predicted bounding box(A) and the ground-truth(B) bounding box.
Time Frame
1 year
Title
Precision
Description
When the IoU was greater than the threshold, the prediction was true positive(TP); when the IoU was less than the threshold, the prediction was false positive(FP).When the model segmentation area was equal to 0, it was false negative(FN).Precision=TP/(TP+FP)
Time Frame
1 year
Title
Recall
Description
Recall=TP/(TP+FN)
Time Frame
1 year
Title
Dice
Description
Dice=2TP/(2TP+FP+FN)
Time Frame
1 year
Secondary Outcome Measure Information:
Title
Cohen's kappa coefficient
Description
This data is to evaluate the agreement between the model and the endoscopists.
Time Frame
1 year
10. Eligibility
Sex
All
Minimum Age & Unit of Time
18 Years
Maximum Age & Unit of Time
80 Years
Accepts Healthy Volunteers
Accepts Healthy Volunteers
Eligibility Criteria
Inclusion Criteria:
1. Age ≥18 years old, <80 years old 2.Patients who need endoscopic ultrasonography of mediastinum; 3. Agree to participate in this study and sign the informed consent form.
Exclusion Criteria:
Subjects who meet any of the following criteria cannot be selected for this trial:
First. The patient's physical condition does not meet the requirements of conventional endoscopic ultrasonography:
Poor physical condition, including hemoglobin ≤8.0g/dl, severe cardiopulmonary insufficiency, etc.
Anesthesia assessment failed
Pregnancy or breastfeeding
In the acute stage of chemical and corrosive injury, it is very easy to cause perforation
Recent acute coronary syndrome or clinically unstable ischemic heart attack
Heart disease patients with right-to-left shunt, patients with severe pulmonary hypertension (pulmonary artery pressure> 90mmHg),patients with uncontrolled systemic hypertension and patients with adult respiratory distress syndrome.
Second. Disagree to participate in this study.
Third. There are other problems that do not meet the requirements of this research or that affect the results of the research:
Mediastinal lesions have previously undergone surgery or radiotherapy and chemotherapy;
Mental illness, drug addiction, inability to express themselves or other diseases that may affect follow-up.
Central Contact Person:
First Name & Middle Initial & Last Name or Official Title & Degree
Xiaoyan Wang, Doctor
Phone
+8613974889301
Email
wxy20011@163.com
First Name & Middle Initial & Last Name or Official Title & Degree
Shiqin Huang, MD
Phone
+8618308312098
Email
sqhuang0213@163.com
Overall Study Officials:
First Name & Middle Initial & Last Name & Degree
Xiaoyan Wang, Doctor
Organizational Affiliation
The Third Xiangya Hospital of Central South University
Official's Role
Principal Investigator
Facility Information:
Facility Name
The Third Xiangya Hospital of Central South University
City
Changsha
State/Province
Hunan
ZIP/Postal Code
410013
Country
China
Individual Site Status
Recruiting
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Xiaoyan Wang, Doctor
Phone
+8613974889301
Email
wxy20011@163.com
First Name & Middle Initial & Last Name & Degree
Shiqin Huang, Doctor
Phone
+8618308312098
Email
sqhuang0213@163.com
12. IPD Sharing Statement
Plan to Share IPD
No
IPD Sharing Plan Description
Some data underlying this trial cannot be shared publicly due to protection of participant's privacy.
Learn more about this trial
Clinical Research on a Novel Deep-learning Based System in Mediastinal Endoscopic Ultrasound Scanning
We'll reach out to this number within 24 hrs