Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

BAC quantification complements rather than competes with PREVENT in real-world cardiovascular risk assessment.

European heart journal·2026

Same author

Artificial Intelligence-Driven Fractional Flow Reserve Assessment: Technical Foundations, Clinical Insights, and Future Directions.

Medicina (Kaunas, Lithuania)·2026

Same author

Diagnosis and Management of Loeys-Dietz Syndrome: Evidence Gaps and Future Directions.

Current cardiology reports·2026

Same author

Rhythm-Stratified Performance of an Artificial Intelligence-Electrocardiographic Aortic Stenosis Score: Alignment with Computed Tomography Calcium in Atrial Fibrillation.

Mayo Clinic proceedings. Digital health·2026

Same author

The Association Between Glucagon-like Peptide-1 Receptor Agonists and Clinical Outcomes in Patients with Thoracic Aortic Aneurysm.

Diagnostics (Basel, Switzerland)·2026

Same author

Evaluation of ePLAR, the echocardiographic pulmonary to left atrial ratio, in a large cohort with pulmonary hypertension.

European heart journal open·2026

Search research articles

Related Experiment Video

Updated: Jan 18, 2026

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

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

Published on: May 24, 2022

A Multi-Task Learning Approach for Segmentation of Breast Arterial Calcifications in Screening Mammograms.

Aisha Urooj¹, Theo Dapamede², Bhavika Patel¹

¹Department of Radiology, Mayo Clinic, Phoenix, Arizona.

AMIA ... Annual Symposium Proceedings. AMIA Symposium

|May 26, 2025

Summary

This summary is machine-generated.

This study introduces a novel multi-task learning method for segmenting breast arterial calcification (BAC) from mammograms, improving cardiovascular risk assessment in women. The approach enhances accuracy by incorporating patch position prediction, outperforming existing methods.

More Related Videos

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

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

Published on: August 30, 2013

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

Related Experiment Videos

Last Updated: Jan 18, 2026

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

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

Published on: May 24, 2022

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

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

Published on: August 30, 2013

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

Area of Science:

Radiology and Medical Imaging
Cardiovascular Health
Artificial Intelligence in Medicine

Background:

Screening mammograms are standard for breast cancer risk assessment in women aged 45+.
Breast arterial calcification (BAC) quantification from mammograms offers a non-invasive method for cardiovascular event risk assessment.
Accurate BAC segmentation faces challenges due to small calcifications, low artery-to-breast ratio, and similar imaging characteristics of breast tissue features.

Purpose of the Study:

To develop and evaluate a novel multi-task learning approach for accurate patch-based breast arterial calcification segmentation.
To address the limitations of current state-of-the-art (SOTA) methods in segmenting BAC from mammograms.
To compare the performance of the proposed method against existing baselines and validate its utility on external data.

Main Methods:

A patch-based methodology was adopted to preserve microscopic BAC details at original mammogram resolution.
A multi-task learning framework was proposed, incorporating an auxiliary task of patch position prediction.
The auxiliary task compels the model to learn breast anatomy, identifying regions where BAC is unlikely (e.g., breast boundary).

Main Results:

The proposed multi-task learning method achieved state-of-the-art performance in BAC segmentation compared to baseline methods.
Validation on external data demonstrated the method's utility and robustness.
Survival analysis showed a correlation between BAC score differences and adverse cardiac events, comparable to coronary calcium score (CAC).

Conclusions:

The developed multi-task learning approach significantly improves breast arterial calcification segmentation accuracy.
This method offers a more precise tool for assessing cardiovascular event risk using screening mammograms.
The findings support the integration of advanced AI techniques for enhanced diagnostic capabilities in women's health.