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

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

Equine fecal microbiota response to short term antibiotic administration.

Journal of equine veterinary science·2024

Same author

Efficacy of incisional negative pressure therapy in preventing post-sternotomy wound complications.

American journal of surgery·2023

Same author

A novel tool to quantify in vivo lumbar spine kinematics and 3D intervertebral disc strains using clinical MRI.

Journal of the mechanical behavior of biomedical materials·2023

Same author

Neutron time-of-flight detectors (nTOF) used at Sandia's Z-Machine.

The Review of scientific instruments·2022

Same author

CDC field triage criteria accurately predicts outcomes in high impact trauma.

Journal of injury & violence research·2022

Same author

Patient perspective on remission in rheumatoid arthritis: Validation of patient reported outcome instruments to measure absence of disease activity.

Seminars in arthritis and rheumatism·2021

Search research articles

Related Experiment Video

Updated: May 21, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Endoscopic image analysis in semantic space.

R Kwitt¹, N Vasconcelos, N Rasiwasia

¹Kitware Inc., Chapel Hill, NC, USA. roland.kwitt@kitware.com

Medical Image Analysis

|June 22, 2012

Summary

This summary is machine-generated.

This study introduces a new semantic encoding for endoscopic images, making visual medical data interpretable for physicians. This approach aids in medical decision support and training by creating human-understandable image representations.

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

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Related Experiment Videos

Last Updated: May 21, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 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

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Area of Science:

Medical Imaging Analysis
Computer Vision
Geometric Deep Learning

Background:

Endoscopic imagery analysis often uses high-dimensional, less interpretable features for medical decision support.
Recent advances in scene recognition highlight the value of semantic modeling for image content.
Current methods lack human interpretability, hindering direct clinical application and physician training.

Purpose of the Study:

To propose a novel, low-dimensional, semantic encoding for endoscopic imagery.
To develop an interpretable representation of medical visual elements within endoscopic images.
To leverage advances in scene recognition and information geometry for medical image analysis.

Main Methods:

Developed a semantic encoding based on scene recognition principles, adapted for medical semantics.
Established a connection to Riemannian geometry and information geometry.
Applied information geometry to address semantic concept recognition, image browsing, and average-case encoding estimation.

Main Results:

Created a semantic space with human-interpretable coordinate axes for endoscopic images.
Demonstrated principled solutions for physician training and clinical practice challenges.
Enabled semantically-focused image browsing and recognition of medically relevant visual details.

Conclusions:

The proposed semantic encoding offers physicians an interpretable representation of endoscopic visual content.
This approach contrasts with current high-dimensional, less interpretable feature-based methods.
The method facilitates natural decision-making and operations based on visual content analysis.