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

KDTViT knowledge distillation, transfer learning and transformer based deep learning framework for efficient

Aarv Mankodi1, Praveen Kumar Shukla2, Hitesh Tekchandani3

  • 1Department of IOT & IS, Manipal University Jaipur, Jaipur, Rajasthan, 303007, India.

Scientific Reports
|May 5, 2026
PubMed
Summary

Related Concept Videos

Classification of Epithelial Tissues: Overview01:22

Classification of Epithelial Tissues: Overview

24.2K
Epithelial tissues are classified according to the shape of the cells and the number of cell layers formed. Cell shapes can be squamous (flattened and thin), cuboidal (square-like, as wide as it is tall), or columnar (rectangular, taller than it is wide). Additionally, the nucleus shape helps identify the type of epithelial cells. Squamous cells have flattened disc-shaped nuclei, cuboidal cells have spherical nuclei, and columnar cells have elongated nuclei.
Based on the number of cell layers,...
24.2K

You might also read

Related Articles

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

Sort by
Same author

Enhanced content-based image retrieval via hybrid color, texture, and deep learning features.

Scientific reports·2026
Same author

Classification of epileptic seizure using hybrid deep learning framework with time and time-frequency Hjorth features.

Computer methods in biomechanics and biomedical engineering·2026
Same author

Nano-assisted delivery tools for plant genetic engineering: a review on recent developments.

Environmental science and pollution research international·2024
Same author

Network pharmacology of apigeniflavan: a novel bioactive compound of <i>Trema orientalis</i> Linn. in the treatment of pancreatic cancer through bioinformatics approaches.

3 Biotech·2023
Same author

Network pharmacology-based anti-pancreatic cancer potential of kaempferol and catechin of Trema orientalis L. through computational approach.

Medical oncology (Northwood, London, England)·2023
Same author

Performance improvement of mediastinal lymph node severity detection using GAN and Inception network.

Computer methods and programs in biomedicine·2020

This study introduces a unified deep learning model for breast cancer detection in histopathology images, effectively handling multiple magnifications. The novel approach achieves high accuracy across all magnification levels, improving scalability for real-world applications.

Area of Science:

  • Digital Pathology
  • Computational Biology
  • Artificial Intelligence in Medicine

Background:

  • Manual breast cancer detection in histopathology images is complex due to tissue variability and multi-magnification requirements.
  • Existing methods often necessitate separate models for each magnification level, hindering scalability and practical deployment.

Purpose of the Study:

  • To develop a unified deep learning model for analyzing histopathology images across multiple magnification levels.
  • To address the limitations of magnification-specific models in breast cancer detection.

Main Methods:

  • Leveraged Transfer Learning and Knowledge Distillation with transformer architectures.
  • Developed a unified model trained sequentially across magnification levels to refine learned representations.
Keywords:
Breast cancerBreast cancer modelCancer detection rateKnowledge distillationTransfer learningTransformers

Related Experiment Videos

  • Prioritized common features for effective generalization across different magnifications.

    • Main Results:

    • Achieved an average accuracy of 95.43% across all magnifications.
    • Attained an average precision of 94.45%, average recall of 99.20%, and average F1 score of 96.76%.
    • Demonstrated a high Area Under the Curve (AUC) of 0.9930 on the BreakHis dataset.

    Conclusions:

    • The proposed unified model effectively generalizes across multiple magnification levels in histopathology images.
    • This approach offers a scalable and practical solution for automated breast cancer detection.
    • The model's high performance across metrics indicates its potential for clinical utility.