Search research articles

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

EdgeVolution: democratizing multi-objective neural architecture search and end-to-end deployment on microcontrollers.

Communications engineering·2026

Same author

T1-weighting in Steady-State FLASH MRI-Diffusion Is Not Only Supportive but Mandatory for the Contrast.

Magnetic resonance in medicine·2026

Same author

An mHealth App and System Architecture for Respiratory Disease Management: Design Principles, Tool Development, and Pilot Usability Study.

JMIR formative research·2025

Same author

A multimodal dataset for precision oncology in head and neck cancer.

Nature communications·2025

Same author

Unstructured Electronic Health Records of Dysphagic Patients Analyzed by Large Language Models.

IEEE journal of translational engineering in health and medicine·2025

Same author

3D anthropometry of the nasolabial region in children aged 3 to 9 months as reference database for clinical assessment.

Scientific reports·2025

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: Sep 17, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Predicting semantic segmentation quality in laryngeal endoscopy images.

Andreas M Kist¹, Sina Razi¹, René Groh¹

¹Department Artificial Intelligence in Biomedical Engineering (AIBE), Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Bavaria, Germany.

|July 3, 2025

Summary

This study introduces an AI system for evaluating laryngeal endoscopy image segmentation quality. The system matches human performance, identifying problematic frames for clinical adaptation of AI analysis.

More Related Videos

Point-of-Care Ultrasound: A Review of Ultrasound Parameters for Predicting Difficult Airways

Point-of-Care Ultrasound: A Review of Ultrasound Parameters for Predicting Difficult Airways

Published on: April 7, 2023

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

Related Experiment Videos

Last Updated: Sep 17, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Point-of-Care Ultrasound: A Review of Ultrasound Parameters for Predicting Difficult Airways

Point-of-Care Ultrasound: A Review of Ultrasound Parameters for Predicting Difficult Airways

Published on: April 7, 2023

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

Area of Science:

Medical Imaging
Artificial Intelligence
Otolaryngology

Background:

Endoscopy is crucial for assessing internal organ physiology.
Artificial intelligence (AI) enables semantic segmentation for medical image analysis, aiding in tasks like cancer detection and laryngeal physiology assessment.
Assessing the quality of AI-driven semantic segmentation is vital due to patient diversity.

Purpose of the Study:

To present a fully automatic system for evaluating segmentation performance in laryngeal endoscopy images.
To demonstrate the system's capability in assessing glottal area segmentation quality.
To facilitate human-in-the-loop improvements for clinical adaptation of AI analysis procedures.

Main Methods:

Development of a fully automatic system to evaluate segmentation performance.
Application of the system to glottal area segmentation in laryngeal endoscopy images.
Utilizing a traffic light system to identify problematic segmentation frames.

Main Results:

The system's predicted segmentation quality, measured by the intersection over union (IoU) metric, is comparable to human raters.
Problematic segmentation frames can be effectively identified using the traffic light system.
The developed system aids in quality control for AI-based laryngeal image analysis.

Conclusions:

The automatic system provides reliable segmentation quality evaluation for laryngeal endoscopy.
The findings support the clinical integration of AI in laryngeal physiology assessment.
Human-in-the-loop quality control is essential for robust AI application in medical procedures.