Ultrasound Therapy; Complications
Conditions
Keywords
peripheral nerve block, ultrasound image, deep neural network, brachial plexus
Brief 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.
Detailed 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.
Interventions
PROCEDUREultrasound 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.
Sponsors
Huashan Hospital
Study design
Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
DIAGNOSTIC
Masking
NONE
Intervention model description
Patients who have been scheduled to surgery will be recruited for collecting ultrasound images.
Eligibility
Sex/Gender
ALL
Age
18 Years to 80 Years
Healthy volunteers
No
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
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| The distance of the lateral midpoints of the nerve sheath contours | immediately after the procedure | between model predictions and the ground truth; between nonexpert anesthesiologist predictions and the ground truth |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| The percentage of the intersection over union | immediately after the procedure | between model predictions and the ground truth; between nonexpert anesthesiologist predictions and the ground truth |
| Accuracy, Sensitivity and specificity | immediately after the procedure | Accuracy, Sensitivity and specificity of the network and nonexpert anesthesiologists |
Countries
China
Outcome results
None listed