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

Acidosis-associated gene signature defines novel subtypes and dual-target therapeutic candidates in breast cancer.

Journal of translational medicine·2026

Same author

[A Transformer-based multimodal model for predicting hospital-acquired infections using imaging and clinical laboratory data].

Nan fang yi ke da xue xue bao = Journal of Southern Medical University·2026

Same author

A comprehensive multi-task deep learning model for kidney cancer: histological subtyping, clinical staging, and anatomical complexity grading.

European radiology·2026

Same author

Dynamic Chest Radiography as an Alternative to Pulmonary Function Tests for Chronic Obstructive Pulmonary Disease.

Radiology·2025

Same author

CTA-Based Carotid Plaque Reporting and Data System Classification Improves Risk Stratification for Ischemic Cerebrovascular Events.

AJNR. American journal of neuroradiology·2025

Same author

Unlocking the potential of training: enhancing inter-reader agreement in background parenchymal enhancement assessment on contrast-enhanced mammography.

The British journal of radiology·2025

Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026

Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026

Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026

Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026

Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026

Same journal

A novel optical respiratory gating system with a hybrid phase-amplitude algorithm for spot-scanning proton therapy.

Medical physics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 26, 2025

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

Multi-scale cascaded networks for synthesis of mammogram to decrease intensity distortion and increase model-based

Gongfa Jiang¹, Zilong He², Yuanpin Zhou¹

¹School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, P. R. China.

Medical Physics

|October 5, 2022

Summary

This summary is machine-generated.

A new deep learning method generates synthetic digital mammograms (SDM) from digital breast tomosynthesis (DBT) with improved image quality. This approach reduces radiation dose while maintaining diagnostic accuracy for breast cancer screening.

Keywords:

breast cancer deep learning digital breast tomosynthesis (DBT)generative adversarial networks (GAN)synthetic mammogram

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

Related Experiment Videos

Last Updated: Aug 26, 2025

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

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

Area of Science:

Medical imaging
Artificial intelligence in healthcare
Radiology

Background:

Synthetic digital mammograms (SDM) are created from digital breast tomosynthesis (DBT) to lower radiation exposure during breast cancer screening.
Previous methods struggled with intensity distortion and perceptual similarity due to texture differences between DBT and full-field digital mammograms (FFDM).
Radiologists require SDM that visually resemble FFDM and preserve critical diagnostic structures like masses and microcalcifications.

Purpose of the Study:

To develop a deep convolutional neural network for generating SDM from DBT.
To improve image quality by reducing intensity distortion and enhancing perceptual similarity.
To create SDM that are visually comparable to FFDM while retaining diagnostic information from DBT.

Main Methods:

A multi-scale cascaded network (MSCN) was proposed, separating the generation of low-frequency (intensity) and high-frequency (texture) structures.
The MSCN consists of two cascaded subnetworks: a low-frequency network trained with mean-squared error (MSE) and a high-frequency network using a gradient-guided generative adversarial network (GAN).
The networks were trained and validated on 1646 FFDM and DBT cases, with testing on 145 cases featuring masses or microcalcification clusters.

Main Results:

The MSCN improved the peak-to-noise ratio from 25.3 to 27.9 dB compared to a baseline network.
Structural similarity increased from 0.703 to 0.724 with the MSCN.
The proposed method significantly enhanced perceptual similarity, generating more visually accurate SDM.

Conclusions:

The developed multi-scale cascaded network (MSCN) effectively stabilizes training for SDM generation.
The method successfully produces SDM with reduced intensity distortion and improved perceptual similarity.
This advancement offers a promising approach for dose reduction in breast cancer screening without compromising image quality or diagnostic utility.