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: Dec 9, 2025

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

Two step convolutional neural network for automatic glottis localization and segmentation in stroboscopic videos.

Varun Belagali¹, Achuth Rao M V², Pebbili Gopikishore³

¹Computer Science and Engineering, RV College of Engineering, Bangalore 560059, India.

Biomedical Optics Express

|September 14, 2020

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

Expiratory Musculature Targeted Resistance Training Modulates Neural Connections During Swallowing Tasks: Preliminary fMRI Evidence.

Neural plasticity·2025

Same author

Exploring Wav2vec 2.0 Model for Heart Sound Analysis.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

Same author

Multimodal Adaptations to Expiratory Musculature-Targeted Resistance Training: A Preliminary Study in Healthy Young Adults.

Journal of speech, language, and hearing research : JSLHR·2025

Same author

Inter-speaker acoustic differences of sustained vowels at varied dysarthria severities for amyotrophic lateral sclerosis.

JASA express letters·2024

Same author

Response to the Letter to the Editor Regarding "Instrumental Assessment of Aero-Resistive Expiratory Muscle Strength Rehabilitation Devices".

Journal of speech, language, and hearing research : JSLHR·2024

Same author

Test of mastication and swallowing solids in healthy individuals aged 6 to 20 years: A normative study in an Indian context.

Journal of oral rehabilitation·2024

This study introduces a two-step convolutional neural network (CNN) for automatic glottis segmentation in stroboscopic videos, improving voice disorder analysis. The method achieved 90.08% localization accuracy for vocal fold vibratory patterns.

Area of Science:

Medical imaging and signal processing
Computational phoniatrics
Artificial intelligence in healthcare

Background:

Accurate vocal fold vibratory pattern analysis is crucial for diagnosing voice disorders.
Automatic glottis segmentation is a key preliminary step in stroboscopic video analysis.
Existing methods may lack precision in complex vocal fold dynamics.

Purpose of the Study:

To develop and evaluate a novel two-step convolutional neural network (CNN) for automatic glottis localization and segmentation.
To enhance the precision of glottis segmentation in stroboscopic laryngeal videos.
To improve the foundational analysis for voice disorder evaluation.

Main Methods:

A two-step CNN approach was implemented for glottis segmentation.

Related Experiment Videos

Last Updated: Dec 9, 2025

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

Data augmentation techniques, including blind rotation (WB) and rotation with glottis orientation (WO), were utilized.

The dataset comprised stroboscopic videos from 18 subjects with Sulcus vocalis, annotated by speech language pathologists (SLPs).

Main Results:

The proposed two-step CNN achieved an average glottis localization accuracy of 90.08%.
A mean Dice score of 0.65 was obtained for glottis segmentation.
The data augmentation strategies contributed to robust model performance.

Conclusions:

The developed two-step CNN effectively automates glottis segmentation in stroboscopic videos.
This approach shows significant potential for improving the objective analysis of voice disorders.
Further research can explore integration into clinical diagnostic workflows.