Identification of Interscalene Brachial Plexus on Ultrasonography Using a Deep Neural Network

Ultrasound Therapy; Complications Clinical Trial

— IBRUNNET  

Official title:

Identification of Interscalene Brachial Plexus Automatically on Ultrasonography Using a Deep Neural Network

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT04183972
• Other study ID #: KY2019-502
• Status: Completed
• Phase: N/A
• Start date: December 1, 2019
• Est. completion date: October 31, 2020

Study information

• Verified date: June 2021
• Source: Huashan Hospital
• Contact: n/a
• Is FDA regulated: No
• Study type: Interventional

Clinical Trial Summary

The purpose of the study is to develop and validate an algorithm based on deep neural networks (DNNs) to identify interscalene brachial plexus on ultrasonography automatically.

Description:

The investigators plan to develop a deep learning-based network to automatically identify interscalene brachial nerves on ultrasound images. The trained model will be validated on an independent dataset. The performance of the network will also be compared against practicing anesthesiologists.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 1126
• Est. completion date: October 31, 2020
• Est. primary completion date: September 30, 2020
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years to 80 Years

Eligibility

Inclusion Criteria:

• ASA physical status class I or II

• scheduled for elective surgery

Exclusion Criteria:

• skin lesion or infection of neck

• any known peripheral neuropathy

• brachial nerve plexus injury

• previous injury or operation on neck

• pregnancy

• allergic to ultrasound gel

Related Conditions & MeSH terms

• Ultrasound Therapy; Complications

Intervention

Procedure:
• ultrasound examination
the participants will be placed in the supine position, with head turned slightly away from the operating side and arms beside the body. The operator will identify right and left interscalene brachial plexuses by ultrasound equipment (Sonosite EDGE or GE LOGIQ e). Clear images and videos of brachial plexus will be captured and saved.

Locations

Country	Name	City	State
China	Huashan Hospital	Shanghai	Shanghai

Sponsors (1)

Lead Sponsor	Collaborator
Huashan Hospital

Country where clinical trial is conducted

China, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	The distance of the lateral midpoints of the nerve sheath contours	between model predictions and the ground truth; between nonexpert anesthesiologist predictions and the ground truth	immediately after the procedure
Secondary	Accuracy, Sensitivity and specificity	Accuracy, Sensitivity and specificity of the network and nonexpert anesthesiologists	immediately after the procedure
Secondary	The percentage of the intersection over union	between model predictions and the ground truth; between nonexpert anesthesiologist predictions and the ground truth	immediately after the procedure