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

You might also read

Related Articles

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

Sort by
Same author

Integrating MRI-based tumour staging within the TNM classification system in modern prostate cancer management.

Insights into imaging·2026
Same author

From resistance to reliance: A human-centered analysis of the spectrum of radiologists' trust in AI.

European journal of radiology open·2026
Same author

Reference standards in AI-assisted MRI readings in prostate cancer screening: primetime for benchmarking.

European radiology·2026
Same author

Quality over quantity: biopsy-anchored CT radiogenomics models outperform all-lesion training in a multi-tumour cohort despite a smaller sample size.

European radiology·2026
Same author

Diffusion weighted MRI-based hypoxic fraction as a prognostic factor in the FLAME trial prostate cancer cohort.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026
Same author

Reply to the Letter to the Editor: Does semi-supervised learning truly reduce annotation burden in heterogeneous real-world MRI networks?

European radiology·2026

Related Experiment Video

Updated: May 24, 2025

Labeling of Breast Cancer Patient-derived Xenografts with Traceable Reporters for Tumor Growth and Metastasis Studies
09:53

Labeling of Breast Cancer Patient-derived Xenografts with Traceable Reporters for Tumor Growth and Metastasis Studies

Published on: November 30, 2016

12.1K

Anatomical Concept-based Pseudo-labels for Increased Generalizability in Breast Cancer Multi-center Data.

Isabela Miranda, Georgios Agrotis, Regina Beets-Tan

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |March 5, 2025
    PubMed
    Summary

    This study enhances breast cancer classification models by integrating anatomical knowledge and a novel loss term for improved accuracy. The research aims to boost early detection and cancer grading using mammography data.

    More Related Videos

    High-Throughput Dissociation and Orthotopic Implantation of Breast Cancer Patient-Derived Xenografts
    06:06

    High-Throughput Dissociation and Orthotopic Implantation of Breast Cancer Patient-Derived Xenografts

    Published on: December 20, 2024

    435
    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
    10:39

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

    Published on: May 24, 2022

    2.3K

    Related Experiment Videos

    Last Updated: May 24, 2025

    Labeling of Breast Cancer Patient-derived Xenografts with Traceable Reporters for Tumor Growth and Metastasis Studies
    09:53

    Labeling of Breast Cancer Patient-derived Xenografts with Traceable Reporters for Tumor Growth and Metastasis Studies

    Published on: November 30, 2016

    12.1K
    High-Throughput Dissociation and Orthotopic Implantation of Breast Cancer Patient-Derived Xenografts
    06:06

    High-Throughput Dissociation and Orthotopic Implantation of Breast Cancer Patient-Derived Xenografts

    Published on: December 20, 2024

    435
    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
    10:39

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

    Published on: May 24, 2022

    2.3K

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence in Healthcare
    • Oncology

    Background:

    • Breast cancer is a leading cause of mortality in women, necessitating advanced diagnostic tools.
    • Mammography is the primary screening method, but accurate interpretation remains challenging.
    • Improving the performance and robustness of AI models for breast cancer classification is crucial for early detection.

    Purpose of the Study:

    • To evaluate the impact of incorporating anatomical knowledge into breast cancer classification models.
    • To enhance model performance and robustness using simulated anatomical variations based on the BI-RADS scale.
    • To introduce a novel loss term for improved cancer grading within the classification model.

    Main Methods:

    • Development of a methodology to generate anatomical pseudo-labels simulating variations in mass size and intensity.
    • Implementation of a novel loss term to facilitate cancer grading learning.
    • Experimental evaluation on public datasets under in-distribution and out-of-distribution scenarios.

    Main Results:

    • The proposed method, incorporating anatomical knowledge and a novel loss term, demonstrates improved performance in breast cancer classification.
    • The model shows enhanced robustness when evaluated on simulated out-of-distribution data.
    • The integration of anatomical variations and cancer grading learning positively impacts classification accuracy.

    Conclusions:

    • Incorporating anatomical knowledge significantly improves the performance and robustness of breast cancer classification models.
    • The novel loss term effectively promotes cancer grading, aiding in more comprehensive analysis.
    • This approach holds promise for advancing AI-assisted mammography interpretation and early breast cancer detection.