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

STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC.

Proceedings of machine learning research·2026
Same author

Training AI to Improve Distinction of Triple-Negative Invasive Breast Cancer from Cysts and Fibroadenomas on Ultrasound.

Diagnostics (Basel, Switzerland)·2026
Same author

Integrated transcriptomic and metabolomic analyses elucidate the molecular mechanisms underlying quality formation during Rosa acicularis fruit ripening.

Food research international (Ottawa, Ont.)·2026
Same author

Geometry-Guided Local Alignment for Multi-View Visual Language Pre-Training in Mammography.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

CAUSAL MODELING OF FMRI TIME-SERIES FOR INTERPRETABLE AUTISM SPECTRUM DISORDER CLASSIFICATION.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

TOWARDS ZERO-SHOT TASK-GENERALIZABLE LEARNING ON FMRI.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026

Related Experiment Video

Updated: Jun 13, 2025

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

SIFT-DBT: SELF-SUPERVISED INITIALIZATION AND FINE-TUNING FOR IMBALANCED DIGITAL BREAST TOMOSYNTHESIS IMAGE

Yuexi Du1, Regina J Hooley2, John Lewin2

  • 1Department of Biomedical Engineering, Yale University, New Haven, CT.

Proceedings. IEEE International Symposium on Biomedical Imaging
|September 12, 2024
PubMed
Summary

A new method called SIFT-DBT uses self-supervised learning to improve the identification of abnormal Digital Breast Tomosynthesis (DBT) images. This approach effectively addresses data imbalance issues in breast cancer screening, achieving high accuracy.

Keywords:
Data ImbalanceDigital Breast TomosynthesisSelf-Supervised Contrastive Pre-training

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
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

42.8K

Related Experiment Videos

Last Updated: Jun 13, 2025

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
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
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

42.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Radiology

Background:

  • Digital Breast Tomosynthesis (DBT) enhances breast cancer screening with 3D imaging.
  • Significant data imbalance exists in DBT, with minimal suspicious tissue, hindering model performance.
  • Existing models often predict the majority class due to data imbalance.

Purpose of the Study:

  • To develop a novel method for identifying abnormal DBT images.
  • To address the data imbalance challenge in DBT analysis.
  • To improve the accuracy of breast cancer detection using AI.

Main Methods:

  • Proposed SIFT-DBT (Self-supervised Initialization and Fine-Tuning for DBT) using view-level contrastive learning.
  • Introduced a patch-level multi-instance learning method to maintain spatial resolution.
  • Evaluated the method on 970 unique DBT studies.

Main Results:

  • Achieved a volume-wise Area Under the Curve (AUC) of 92.69%.
  • SIFT-DBT effectively mitigates data imbalance issues in DBT analysis.
  • The patch-level approach preserved crucial spatial resolution for accurate detection.

Conclusions:

  • SIFT-DBT offers a promising solution for accurate abnormal DBT image identification.
  • The proposed method enhances AI performance in breast cancer screening.
  • This approach can lead to more reliable and effective diagnostic tools in radiology.