Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Feb 18, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Automated Segmentation of Stellate Ganglion Block Region in Ultrasound Images Using Deep Learning Model.

Weixiong Chen^1,2, Lili Feng², Wenna Zhang²

¹From the School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China.

Anesthesia and Analgesia

|February 16, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Ultrafast damage dynamics and ablation mechanism of a BaGa<sub>4</sub>Se<sub>7</sub> crystal induced by femtosecond laser irradiation.

Optics express·2026

Same author

Efficient nutrient removal from low C/N municipal wastewater using a phototrophic biofilm system integrating simultaneous nitrification-denitrification and phosphorus removal (SND).

Environmental research·2026

Same author

Cyclodextrin-Derived Porous Liquids Enabled by In Situ Solvation Shell Formation.

Journal of the American Chemical Society·2026

Same author

Microsurgical Clip Reconstruction of Multiple Contiguous Aneurysms of the Anterior Communicating Artery Complex: Subfrontal Exposure and Endoscopic Verification-A Case Illustration.

Neurosurgery practice·2026

Same author

Musculoskeletal disorders: does cuproptosis hold the key?

Frontiers in cell and developmental biology·2026

Same author

Endothelialization of bioprosthetic valves: unanswered questions and a roadmap for translational research.

Angiogenesis·2026

Same journal

Ketamine Infusion and Risk of Postoperative Nausea and Vomiting and Adverse Outcomes in Surgical Patients: A Secondary Analysis of the IMPAKT Randomized Trial.

Anesthesia and analgesia·2026

Same journal

A Novel Algorithm for Continuous Real-Time Cerebral Autoregulation Assessment Based on Mean Arterial Pressure and Cerebral Oxygen Saturation.

Anesthesia and analgesia·2026

Same journal

Anesthesia Care, Complications, and Airway Management for Patients With Spinal Muscular Atrophy: A Retrospective Chart Review From a Quaternary Children's Hospital.

Anesthesia and analgesia·2026

Same journal

The Impact of the "2023 American Society of Anesthesiologists Practice Guidelines for Monitoring and Antagonism of Neuromuscular Blockade" on Quantitative Neuromuscular Monitoring Two Years Later.

Anesthesia and analgesia·2026

Same journal

Computer Simulation Approach to Assessing Anesthetic Gas Leak Exposure to Theater Staff.

Anesthesia and analgesia·2026

Same journal

Emergency Jet Oxygenation Via a Narrow-Bore Cannula: A Computational Modelling Investigation.

Anesthesia and analgesia·2026

See all related articles

A new deep learning model, MLF-UNet, accurately segments the stellate ganglion (SG) region on ultrasound, aiding beginners in performing stellate ganglion blocks (SGBs) safely and effectively.

Area of Science:

Medical Imaging
Artificial Intelligence in Medicine
Ultrasound Guided Procedures

Background:

The stellate ganglion (SG) is a critical anatomical region for nerve blocks.
Ultrasound-guided stellate ganglion block (SGB) is technically demanding due to dense vascularization and innervation.
Automated segmentation of the SG region using deep learning has not been extensively studied.

Purpose of the Study:

To develop and validate a deep learning model for automated ultrasound segmentation of the SG region.
To improve the accuracy and safety of ultrasound-guided SGB procedures.
To support clinicians, especially beginners, in identifying the SG anatomy.

Main Methods:

A retrospective study included 370 patients undergoing ultrasound-guided SGB.

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Feb 18, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

A multilevel feature fusion UNet (MLF-UNet) was developed and trained on 2190 annotated ultrasound images.

Performance was evaluated using Dice similarity coefficient (DSC), Intersection over Union (IoU), Hausdorff distance (95HD), and symmetric surface distance (ASSD), comparing MLF-UNet against benchmark models, experts, and nonexperts.

Main Results:

MLF-UNet achieved superior performance with DSC of 0.856 and IoU of 0.754.
Expert ratings indicated MLF-UNet outperformed benchmark models in topological integrity, boundary precision, and background accuracy.
MLF-UNet demonstrated expert-level region overlap, with slightly larger boundary imprecision compared to expert delineations.

Conclusions:

MLF-UNet provides accurate automated ultrasound segmentation of the SG region.
The model achieves expert-level performance in region overlap, aiding procedural safety.
This deep learning approach shows promise for supporting SGB procedures and enhancing clinical training.