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: Jul 25, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Evaluating robotic-assisted partial nephrectomy surgeons with fully convolutional segmentation and multi-task

Yihao Wang¹, Zhongjie Wu¹, Jessica Dai²

¹Department of Computer Science, Southern Methodist University, Dallas, USA.

Journal of Robotic Surgery

|June 27, 2023

Summary

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

Dual-Channel Inhibition With Rivaroxaban and Aspirin for Thromboprophylaxis in Patients With Long-Term Inferior Vena Cava Filter Implantation: A Two-Center Cohort Study.

Clinical and applied thrombosis/hemostasis : official journal of the International Academy of Clinical and Applied Thrombosis/Hemostasis·2026

Same author

Design of Flexible Conformal Beam-Scanning Leaky-Wave Antenna.

Micromachines·2026

Same author

Remote Sensing of Soil Water Retention Signatures Using Sentinel-2 Time-Series and Exponential Decay Fitting Model.

Sensors (Basel, Switzerland)·2026

Same author

A Programmable Multi‑Modal Information Encryption System Based on the Dynamic Wetting Behavior of Liquid Metal.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Self-adaptive hetero-phase superlattices in TaS<sub>2</sub> via layer-resolved 1T-to-1H transformations.

National science review·2026

Same author

Bone health in asthma: a twofold effect of disease and pharmacotherapy.

Frontiers in endocrinology·2026

Same journal

Posterior tibial slope accuracy in robotic-assisted TKA: a risk factor analysis focusing on CPAK phenotypes.

Journal of robotic surgery·2026

Same journal

Comparative outcomes and adoption trends of robotic versus non-robotic ureteral reconstruction: a national matched cohort study.

Journal of robotic surgery·2026

Same journal

Research trends and collaboration patterns in robotic retroperitoneal lymph node dissection for testicular cancer.

Journal of robotic surgery·2026

Same journal

Bridging access, training, and robotic surgery technology: lessons from the 2025 SRS LATAM session.

Journal of robotic surgery·2026

Same journal

Mako robot-assisted unicompartmental knee arthroplasty mitigates the impact of surgeon handedness.

Journal of robotic surgery·2026

Same journal

Global Research Trends and Thematic Evolution in Robotic Surgery for Obstructive Sleep Apnoea: A Bibliometric and Visualisation Study.

Journal of robotic surgery·2026

See all related articles

This summary is machine-generated.

Machine learning models assess surgical skill in robotic assisted partial nephrectomy (RAPN) using video analysis. The system accurately predicts proficiency scores but requires more diverse data for improved accuracy.

Area of Science:

Robotics in Surgery
Machine Learning Applications
Surgical Education Technology

Background:

Robotic assisted partial nephrectomy (RAPN) is a complex procedure requiring high surgical skill.
Objective evaluation of surgical skill is crucial for training and quality improvement.
Previous studies often utilized synthetic environments, limiting real-world applicability.

Purpose of the Study:

To develop and evaluate machine learning models for assessing surgical skill from actual RAPN procedure videos.
To predict surgical proficiency scores, specifically OSATS (Objective Structured Assessment of Technical Skills) and GEARS (Global Evaluative Assessment of Robotic Skills).
To investigate the use of cascaded neural networks for instrument tracking and skill scoring.

Main Methods:

Keywords:

Convolutional network Multi-task learning Self-attention Surgical assessment

More Related Videos

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

Robot-Assisted Kidney Transplantation

Robot-Assisted Kidney Transplantation

Published on: July 19, 2021

Related Experiment Videos

Last Updated: Jul 25, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

Robot-Assisted Kidney Transplantation

Robot-Assisted Kidney Transplantation

Published on: July 19, 2021

Utilized videos from DaVinci robotic systems during tumor resection and renography steps of RAPN.
Employed cascaded neural networks, including a semantic segmentation network for instrument tracking.
A scoring network processed instrument movements to predict OSATS and GEARS scores for various subcategories.

Main Results:

The model demonstrated good performance in predicting subcategory scores for metrics like force sensitivity and instrument knowledge.
The system successfully tracked surgical instruments within the operative field.
Identified limitations including false positives/negatives, attributed to limited training data variability and sparsity.

Conclusions:

Machine learning can effectively evaluate surgical skill from real-world RAPN videos.
The developed cascaded neural network approach shows promise for automated surgical skill assessment.
Further research with larger and more diverse datasets is needed to enhance model robustness and accuracy.