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 Video

Updated: Dec 5, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.2K

Biomedical image classification made easier thanks to transfer and semi-supervised learning.

A Inés1, C Domínguez1, J Heras1

  • 1Department of Mathematics and Computer Science of University of La Rioja, Centro Científico Tecnológico Logroño E-26006, La Rioja, Spain.

Computer Methods and Programs in Biomedicine
|October 16, 2020
PubMed
Summary

Related Concept Videos

Classification of Systems-I01:26

Classification of Systems-I

468
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
468

You might also read

Related Articles

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

Sort by
Same author

Higher rate of pathologic complete response in patients with early-onset locally advanced rectal cancer.

ESMO gastrointestinal oncology·2026
Same author

JustRAIGS: Justified Referral in AI Glaucoma Screening Challenge.

IEEE transactions on medical imaging·2025
Same author

Correction: the TEOGIC study project: a comprehensive characterization of early onset gastrointestinal cancer in the Northern area of Spain.

BMC cancer·2024
Same author

The TEOGIC study project: a comprehensive characterization of early onset gastrointestinal cancer in the Northern area of Spain.

BMC cancer·2024
Same author

Natural language processing tools for non-clinical healthcare management.

Journal of healthcare quality research·2023
Same author

Angiogenic imbalance in maternal and cord blood is associated with neonatal birth weight and head circumference in pregnancies with major fetal congenital heart defect.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2023

This study introduces an Automated Machine Learning (AutoML) method for biomedical image classification, enabling deep learning with limited annotated data. The new approach surpasses existing tools in speed and accuracy, especially for small datasets.

Area of Science:

  • Biomedical image analysis
  • Machine learning in healthcare
  • Computer vision applications

Background:

  • Deep learning excels at biomedical image classification but requires extensive annotated data.
  • Complex deep learning libraries and hyperparameter tuning hinder adoption by non-experts.
  • Existing methods face challenges with limited or partially annotated biomedical image datasets.

Purpose of the Study:

  • To present an Automated Machine Learning (AutoML) method addressing the data and usability limitations of deep learning in biomedicine.
  • To develop a tool that democratizes the use of advanced deep learning techniques for medical image classification.
  • To enable effective model training even with scarce annotated image resources.

Main Methods:

  • Developed an AutoML method combining transfer learning and a novel semi-supervised learning procedure.
Keywords:
AutoMLBenchmarkImage classificationSemi-Supervised learningTransfer-learning

Related Experiment Videos

Last Updated: Dec 5, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.2K
  • Implemented the method as an open-source tool named ATLASS for accessibility and dissemination.
  • Evaluated the method's performance using two benchmark biomedical image classification datasets.

    • Main Results:

    • The AutoML method demonstrates superior performance in both speed and accuracy compared to existing tools on small datasets.
    • Achieved up to a 10% improvement in model accuracy when working with partially annotated datasets.
    • Successfully trained deep learning models using small and partially annotated biomedical image datasets.

    Conclusions:

    • The presented AutoML method effectively enables the application of deep learning for image classification with limited resources.
    • It facilitates the training of deep models using small and partially annotated image datasets, overcoming previous limitations.
    • The method outperforms existing AutoML tools in accuracy and speed for small dataset scenarios, promoting wider adoption.