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

Energy Losses in Transformers01:21

Energy Losses in Transformers

986
In an ideal transformer, it is assumed that there are no energy losses, and, hence, all the power at the primary winding is transferred to the secondary winding. However, in reality,  the transformers always have some energy losses, and, hence, the output power obtained at the secondary winding is less than the input power at the primary winding due to energy losses.
There are four main reasons for energy losses in transformers.
The first cause can be  the high resistance of the...
986

You might also read

Related Articles

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

Sort by
Same author

AI weather prediction toward multi-scale earth system prediction: status and pathways.

Science bulletin·2026
Same author

Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks, Challenges and Baselines.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Co-modification of corn flour by <i>Lactobacillus HR</i> and transglutaminase reduces glycemic index and enhances functional properties.

Frontiers in nutrition·2026
Same author

A multi-data fusion deep learning model for prognostic prediction in upper tract urothelial carcinoma.

Frontiers in oncology·2025
Same author

Benchmark dataset and deep learning method for global tropical cyclone forecasting.

Nature communications·2025
Same author

Lightweight Multi-Stage Aggregation Transformer for robust medical image segmentation.

Medical image analysis·2025

Related Experiment Video

Updated: Sep 18, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K

Refocal Loss in Transformer for Long-Tailed Multi-Granularity Cataract Classification.

Qiong Wang, Yan Wang, Hongdi Sun

    IEEE Journal of Biomedical and Health Informatics
    |June 25, 2025
    PubMed
    Summary

    This study introduces a new method for multi-granularity cataract classification, improving diagnostic accuracy. The proposed model effectively handles imbalanced data, aiding physicians in making better treatment decisions for cataracts.

    More Related Videos

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    43.0K
    Multifocal Electroretinograms
    16:49

    Multifocal Electroretinograms

    Published on: December 4, 2011

    18.4K

    Related Experiment Videos

    Last Updated: Sep 18, 2025

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    2.0K
    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    43.0K
    Multifocal Electroretinograms
    16:49

    Multifocal Electroretinograms

    Published on: December 4, 2011

    18.4K

    Area of Science:

    • Ophthalmology
    • Computer Vision
    • Artificial Intelligence

    Background:

    • Cataract diagnosis requires classifying different types and severities, with existing methods limited in handling multi-granularity levels.
    • Current approaches often group cataracts into common types or focus on fine-grained grading of specific types, lacking comprehensive classification.
    • The varying severity assessment across different cataract types necessitates improved diagnostic tools.

    Purpose of the Study:

    • To develop an improved system for multi-granularity cataract classification.
    • To address the limitations of existing methods in predicting various cataract types at different granularity levels.
    • To enhance diagnostic efficiency and provide reliable quantitative evaluations for clinical decision-making.

    Main Methods:

    • Collected a large-scale dataset named Multi-Granularity Long-Tailed Cataract.
    • Proposed an end-to-end training network utilizing Transformer for multi-granularity cataract feature extraction.
    • Introduced Refocal loss to address data imbalance and long-tailed distribution in cataract datasets.

    Main Results:

    • The proposed model achieved high Precision (78.22%), F1-score (68.35%), Kappa (64.38%), and MCC (64.49%) on the multi-granularity cataract classification dataset.
    • Demonstrated superior performance compared to state-of-the-art methods in multi-granularity cataract classification.
    • The framework offers promising reliable quantitative evaluations for physicians.

    Conclusions:

    • The developed framework provides a promising solution for multi-granularity cataract classification.
    • The approach aids physicians in making informed treatment decisions by offering reliable quantitative evaluations.
    • The study highlights the potential of Transformer networks and Refocal loss in advancing automated cataract diagnosis.