Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Comparison of Outcomes of Leadless Versus Transvenous Pacemakers Following Tricuspid Valve Surgery.

Journal of the American Heart Association·2026
Same author

Association of municipal rurality and area deprivation with cause-specific mortality in Japan: a nationwide ecological study.

BMJ public health·2026
Same author

Outcomes of Percutaneous and Surgical Interventions of Right-Sided Heart Masses in Older Patients: A Nationwide Comparative Study.

Journal of the American Heart Association·2026
Same author

Nationwide Implementation of Non-Mandatory Preventive Medicine Programmes in Japanese Municipalities: A Descriptive Cross-Sectional Survey and Evidence-Practice Gap Analysis.

Research square·2026
Same author

Racial and Sex Differences in Postoperative Mortality Between Patients With Versus Without Dementia.

Annals of surgery open : perspectives of surgical history, education, and clinical approaches·2026
Same author

Estimating the Effect of Hospital Admission on Health Care Outcomes and Spending Among Persons With Dementia : A Quasi-experimental Study.

Annals of internal medicine·2026

Related Experiment Video

Updated: Jun 18, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

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

Published on: April 14, 2023

2.4K

Identifying sex from pharyngeal images using deep learning algorithm.

Hiroshi Yoshihara1, Memori Fukuda2, Takaya Hanawa2

  • 1Aillis, Inc., Yaesu Central Tower 7F, 2-2-1 Yaesu, Chuo-ku, Tokyo, 104-0028, Japan. hiroshi.yoshihara@aillis.jp.

Scientific Reports
|August 2, 2024
PubMed
Summary
This summary is machine-generated.

Artificial intelligence can now identify sex from pharyngeal images, similar to retinal scans. This deep learning model shows potential for non-invasive sex identification using images of the throat.

More Related Videos

Visualization and Analysis of Pharyngeal Arch Arteries using Whole-mount Immunohistochemistry and 3D Reconstruction
10:02

Visualization and Analysis of Pharyngeal Arch Arteries using Whole-mount Immunohistochemistry and 3D Reconstruction

Published on: March 31, 2020

9.5K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

Related Experiment Videos

Last Updated: Jun 18, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

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

Published on: April 14, 2023

2.4K
Visualization and Analysis of Pharyngeal Arch Arteries using Whole-mount Immunohistochemistry and 3D Reconstruction
10:02

Visualization and Analysis of Pharyngeal Arch Arteries using Whole-mount Immunohistochemistry and 3D Reconstruction

Published on: March 31, 2020

9.5K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Otolaryngology

Background:

  • The pharynx offers a unique, non-invasive window for observing internal body structures like blood vessels and immune tissues.
  • Previous research successfully used artificial intelligence (AI) to determine sex from retinal images, but its application to pharyngeal images was unexplored.

Purpose of the Study:

  • To investigate the feasibility of identifying individuals' sex using deep learning analysis of pharyngeal images.
  • To develop and validate an AI model for sex classification based on non-invasively acquired pharyngeal imagery.

Main Methods:

  • A deep learning classification model, utilizing a multiple instance convolutional neural network, was trained on 20,319 pharyngeal images from 51 primary care clinics in Japan.
  • Model validation was conducted on 4,869 images from 13 separate clinics.
  • Model interpretation involved a framework combining saliency and organ segmentation maps to identify key image regions.

Main Results:

  • The AI model achieved an area under the receiver operating characteristic curve (AUC) of 0.883 (95% CI 0.866-0.900), indicating accurate sex classification.
  • Performance significantly improved for individuals aged 20 and older, suggesting age-related sex-specific patterns in the pharynx.
  • Saliency analysis revealed the model primarily focused on the posterior pharyngeal wall and uvula for classification.

Conclusions:

  • Pharyngeal images, analyzed with a deep learning algorithm, demonstrate significant potential for accurate and non-invasive sex identification.
  • The findings suggest that AI-driven analysis of pharyngeal imagery could be a novel diagnostic or demographic tool.
  • Further research may explore the clinical applications of sex identification from pharyngeal images, particularly in older age groups.