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 integrity and efficiency of the mediastinum scanning for the ultrasound endoscopist. Participants will undergo mediastinal EUS with or without the assistance of the artificial intelligence system.
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, the completeness of standard sites and scanning time of endoscopic-assisted and non-assisted AI systems were compared.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
OTHER
Masking
DOUBLE
Enrollment
180
Patients will undergo EUS examination with the assistance of AI system.
The Third Xiangya Hospital of Central South University
Changsha, Hunan, China
RECRUITINGAccuracy
The number of correctly classified images divided by the total number of images.
Time frame: 1 year
The completeness for standard station scanning
This was calculated as the number of stations successfully scanned divided by the total number of stations that should have been scanned.
Time frame: Until the end of the study
Cohen's kappa coefficient
This data is to evaluate the agreement between the model and the endoscopists.
Time frame: 1 year
The completeness for standard stations and anatomical landmarks per individual
The completeness of stations and anatomic landmarks of endoscopic ultrasonography by different endoscopists in the AI system assisted group and the control group were compared.
Time frame: Until the end of the study
The completeness of anatomical landmarks
It calculated as the number of anatomical structures successfully scanned divided by the total number of structures that should have been scanned
Time frame: Until the end of the study
Operation time
In addition to puncture, elastography, and ultrasound enhancement to observe the lesion or treatment, it can also be used to observe the time of the mediastinum.
Time frame: Until the end of the study
The incidence of adverse events
The incidence of adverse events in both groups during the entire research process.
Time frame: Until the end of the study
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.