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 Experiment Videos

StyleGAN-based synthetic image augmentation for multi-class otoscopy image classification.

Seda Camalan1, Carl D Langefeld2,3,4, Amy Zinnia3

  • 1Center for Artificial Intelligence Research, Wake Forest University School of Medicine, Winston-Salem, NC, USA. asc.seda@gmail.com.

Scientific Reports
|June 10, 2026
PubMed
Summary

Related Concept Videos

Force Classification01:22

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Imaging Biological Samples with Optical Microscopy01:18

Imaging Biological Samples with Optical Microscopy

Optical microscopy uses optic principles to provide detailed images of samples. Antonie van Leeuwenhoek designed the first compound optical microscope in the 17th century to visualize blood cells, bacteria, and yeast cells. In 1830, Joseph Jackson Lister created an essentially modern light microscope. The 20th century saw the development of microscopes with enhanced magnification and resolution.
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...

You might also read

Related Articles

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

Sort by
Same author

Baseline Function Predicts Gains in Both Speech Recognition and Quality of Life After Cochlear Implantation.

Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology·2026
Same author

Role of Communication Partners in Pre-Cochlear Implant Decision-Making: A Scoping Review.

Ear and hearing·2026
Same author

Cochlear Implant Complications and Outcomes: National Trends of the MAUDE Database From 2016 to 2024.

Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery·2026
Same author

Audiovisual Speech Recognition in Adult Cochlear Implant Candidates: Relations with Cognitive-Linguistic Abilities.

Otology & neurotology open·2026
Same author

Perspectives on Aural Rehabilitation From Adult Cochlear Implant Recipients.

American journal of audiology·2026
Same author

Machine Learning to Characterize Speech Recognition and Quality of Life Outcomes in Adult Cochlear Implant Users.

Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology·2026

This study shows that using artificial intelligence (AI) image augmentation with StyleGAN3 significantly improves the accuracy of classifying eardrum images, aiding in diagnosing ear conditions. The AI-generated images boosted classification performance, offering a promising tool for objective eardrum evaluation.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Otolaryngology

Background:

  • Accurate diagnosis of eardrum abnormalities is crucial for managing ear conditions.
  • Otoscopy provides visual inspection but faces challenges like lighting variations and limited datasets.
  • Objective evaluation methods, such as machine learning for image classification, are needed.

Purpose of the Study:

  • To investigate the efficacy of StyleGAN3 artificial image augmentation for enhancing otoscopy image classification.
  • To improve the accuracy and objectivity of diagnosing eardrum pathologies.

Main Methods:

  • Utilized StyleGAN3 to generate artificial and composite otoscopy images.
  • Trained and validated a ResNet-101 model on augmented datasets, including synthetic and classic augmented images.
Keywords:
Deep learningGANImage augmentationOtoscopy image

Related Experiment Videos

  • Compared classification performance against models trained without augmentation and with traditional augmentation.

    • Main Results:

    • StyleGAN3 augmentation significantly improved classification accuracy to 0.95 ± 0.03 and F1-score to 0.96 ± 0.02.
    • Models without augmentation achieved 0.82 ± 0.03 accuracy and 0.78 ± 0.02 F1-score.
    • Traditional augmentation yielded 0.87 ± 0.02 accuracy and 0.85 ± 0.02 F1-score.

    Conclusions:

    • Generative Adversarial Network (GAN)-based augmentation, specifically StyleGAN3, substantially enhances eardrum image classification.
    • This approach offers a potential solution to diagnostic challenges posed by limited data and image variability.
    • The findings highlight the value of synthetic data in improving automated diagnostic systems for ear conditions.