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

Classification of Signals01:30

Classification of Signals

1.1K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.1K
Classification of Illness01:17

Classification of Illness

8.2K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
8.2K
Classification of Leukocytes01:30

Classification of Leukocytes

4.2K
Leukocytes are classified into two groups based on the presence or absence of cytoplasmic granules. Granular leukocytes, which contain granules, belong to the myeloid lineage and are divided into three subtypes: neutrophils, eosinophils, and basophils. These cells are roughly spherical and characterized by the granules in their cytoplasm.
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
4.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Multi-dimensional evaluation of user-operated audible contrast sensitivity tests towards efficient hearing healthcare services.

PLOS digital health·2026
Same author

Noise Management Preferences During Long-Term Hearing Aid Usage and Their Relation to Audiologic Factors.

Trends in hearing·2026
Same author

Population-based characterization of left atrial and appendage variations: Prevalence, risk factor associations, and sex-specific morphology.

Journal of cardiovascular computed tomography·2026
Same author

[EOSINOPHIL-ASSOCIATED DISEASES: A PATHOBIOLOGY-BASED, CROSS-ORGAN PERSPECTIVE].

Arerugi = [Allergy]·2026
Same author

Recent systemic corticosteroid exposure and mild cognitive impairment in elderly asthma: A prospectively collected cross-sectional study.

Allergology international : official journal of the Japanese Society of Allergology·2026
Same author

Nationwide surveillance of antibacterial susceptibility patterns of bacterial pathogens isolated from otorhinolaryngological infectious diseases in Japan.

Journal of infection and chemotherapy : official journal of the Japan Society of Chemotherapy·2026

Related Experiment Video

Updated: Nov 9, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

158

Deep metric learning for otitis media classification.

Josefine Vilsbøll Sundgaard1, James Harte2, Peter Bray3

  • 1Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark.

Medical Image Analysis
|April 13, 2021
PubMed
Summary

This study introduces an automatic algorithm for diagnosing otitis media using deep metric learning on tympanic membrane images. Triplet loss demonstrated high precision, offering an operator-independent diagnostic tool comparable to clinical experts.

Keywords:
Convolutional neural networkDeep metric learningImage classificationOtitis media

More Related Videos

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

2.8K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

629

Related Experiment Videos

Last Updated: Nov 9, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

158
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

2.8K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

629

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Otolaryngology

Background:

  • Accurate diagnosis of otitis media is crucial for appropriate treatment and antibiotic stewardship.
  • Distinguishing between acute otitis media and otitis media with effusion is clinically significant.
  • Current diagnostic methods can be operator-dependent and require specialized expertise.

Purpose of the Study:

  • To develop and evaluate an automatic diagnostic algorithm for otitis media detection using deep metric learning.
  • To compare the performance of various distance-based metric loss functions against standard classification methods.
  • To assess the feasibility of deep metric learning for classifying tympanic membrane abnormalities.

Main Methods:

  • Utilized a dataset of 1336 otoscopy images of the tympanic membrane.
  • Employed deep metric learning techniques, including contrastive loss, triplet loss, and multi-class N-pair loss.
  • Compared deep metric learning models with standard cross-entropy and class-weighted cross-entropy networks.

Main Results:

  • Triplet loss achieved high precision, particularly on an imbalanced dataset.
  • Deep metric learning methods provided valuable insights into neural network decision-making processes.
  • The developed algorithm demonstrated diagnostic performance comparable to that of expert clinicians.

Conclusions:

  • Deep metric learning offers a promising approach for the automated diagnosis of otitis media.
  • The proposed algorithm enables accurate and operator-independent detection of tympanic membrane abnormalities.
  • This technology has the potential to improve patient care and optimize antibiotic usage.