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

A Transfer Learning Based Super-Resolution Microscopy for Biopsy Slice Images: The Joint Methods Perspective.

Jintai Chen, Haochao Ying, Xuechen Liu

    IEEE/ACM Transactions on Computational Biology and Bioinformatics
    |May 2, 2020
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

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

    Sort by
    Same author

    RetinexDA: Progressive Disentanglement Domain Adaptation for Unsupervised Cross-Modality Medical Image Segmentation.

    IEEE journal of biomedical and health informatics·2026
    Same author

    BPX-Net: biomarker-preserved explainable networks for disease diagnosis and prognosis.

    BioData mining·2026
    Same author

    Enhanced predictive performance of artificial intelligence in individualized ovarian stimulation of in vitro fertilization: a retrospective cohort study.

    BMC medicine·2026
    Same author

    Decouple, Reorganize, and Fuse: A Multimodal Framework for Cancer Survival Prediction.

    IEEE transactions on medical imaging·2026
    Same author

    Strengthened s-p orbital hybridization on selenization interphase for stable lean lithium metal batteries.

    Journal of colloid and interface science·2025
    Same author

    Favorable impact of zanubrutinib combined with R-CHOP regimen in MYD88-mutated new-diagnosed diffuse large B-cell lymphoma: a retrospective study with propensity score-matched analysis.

    Cancer immunology, immunotherapy : CII·2025

    Generating high-resolution biopsy images from low-resolution ones is now more efficient. A novel deep super-resolution framework (SRFBN+) and transfer learning strategy (CF-Trans) improve medical image quality and reduce costs.

    Area of Science:

    • Medical Imaging
    • Computer Vision
    • Biotechnology

    Background:

    • High-resolution biopsy slice images are crucial for medical diagnosis but are expensive to acquire.
    • Low-resolution images lack critical details necessary for accurate analysis.
    • Existing super-resolution methods face challenges with diverse biopsy image patterns.

    Purpose of the Study:

    • To develop a cost-effective method for generating high-resolution biopsy slice images from low-resolution inputs.
    • To introduce a novel deep super-resolution framework and a specialized transfer learning strategy tailored for medical imaging.
    • To enhance the diagnostic utility of biopsy images through improved resolution.

    Main Methods:

    • A modified deep super-resolution framework, SRFBN+, based on SRFBN, with a flexible feedback block structure.

    Related Experiment Videos

  • A novel transfer learning strategy, Channel Fusion Transfer Learning (CF-Trans), creating a middle domain for knowledge transfer.
  • Training SRFBN+ using CF-Trans across source, middle, and target biopsy image domains.

    • Main Results:

    • SRFBN+ effectively generates high-resolution biopsy slice images from low-resolution inputs.
    • CF-Trans demonstrated efficiency as a transfer learning strategy for medical image super-resolution.
    • The joint framework successfully improved image quality, preserving fine details.

    Conclusions:

    • The proposed SRFBN+ framework and CF-Trans strategy offer a viable solution for high-resolution medical image generation.
    • This approach can significantly reduce the cost associated with acquiring high-resolution biopsy images.
    • The findings have implications for improving diagnostic accuracy and efficiency in medical practice.