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

Search research articles

Related Experiment Video

Updated: Feb 22, 2026

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

Automated Analysis of Unregistered Multi-View Mammograms With Deep Learning.

Gustavo Carneiro, Jacinto Nascimento, Andrew P Bradley

IEEE Transactions on Medical Imaging

|September 19, 2017

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

AutoCumulus: an automated mammographic density measure created using artificial intelligence.

BMC cancer·2026

Same author

Deep learning Algorithm for Wound assessment after total kNee (DAWN) arthroplasty : a prospective study protocol.

Bone & joint open·2026

Same author

Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

AI-based BRAIx risk score for the intermediate-term prediction of breast cancer: a population cohort study.

The Lancet. Digital health·2026

Same author

The problem with the 'truth': rethinking ground truth for artificial intelligence in endometriosis diagnosis.

Human reproduction (Oxford, England)·2026

Same author

EndoCompass Project: Artificial Intelligence in Endocrinology.

Hormone research in paediatrics·2025

Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026

Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026

Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026

Same journal

The Ritz Adjoint Method for MRI Pulse Design.

IEEE transactions on medical imaging·2026

Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026

Same journal

Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning.

IEEE transactions on medical imaging·2026

See all related articles

This study introduces a novel deep learning method for analyzing mammograms to predict breast cancer risk. The system holistically classifies entire exams, achieving high accuracy in distinguishing benign from malignant findings.

Area of Science:

Radiology and Medical Imaging
Artificial Intelligence in Healthcare
Oncology

Background:

Accurate breast cancer risk estimation is crucial for early detection and personalized screening.
Current methods often focus on individual lesion classification, potentially overlooking holistic exam patterns.
Automated analysis of mammographic views (cranio-caudal and medio-lateral oblique) requires robust methodologies.

Purpose of the Study:

To develop and validate an automated deep learning methodology for breast cancer risk assessment using mammography.
To jointly classify unregistered mammogram views and lesion segmentation maps for a holistic exam analysis.
To evaluate the system's performance using both semi-automated and fully automated approaches.

Main Methods:

More Related Videos

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Published on: November 7, 2025

Related Experiment Videos

Last Updated: Feb 22, 2026

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

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Published on: November 7, 2025

Utilized deep learning models for the joint classification of cranio-caudal (CC) and medio-lateral oblique (MLO) mammography views and segmentation maps of breast lesions (masses, micro-calcifications).

Developed a holistic methodology to classify entire mammographic exams, integrating view and segmentation data.

Tested on publicly available datasets (INbreast, DDSM) using both manual and automated segmentation maps.

Main Results:

Semi-automated approach achieved Volume Under ROC Surface (VUS) > 0.9 for a 3-class problem (normal, benign, malignant) and Area Under ROC Curve (AUC) > 0.9 for 2-class problems (benign vs. malignant, screening).
Fully automated approach demonstrated VUS > 0.7 and AUC > 0.78 for benign vs. malignant classification, and AUC = 0.86 for breast screening.
The system effectively utilizes automated segmentation maps, maintaining accurate classification performance.

Conclusions:

The proposed deep learning methodology offers a promising, holistic approach to breast cancer risk estimation from mammography.
The system demonstrates high accuracy in classifying mammographic exams, even when using automated lesion segmentation.
This automated methodology has the potential to enhance breast cancer screening and diagnosis.