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

Four-dimensional on-beam computed tomography reconstruction using projection-difference images.

Physics in medicine and biology·2026
Same author

Source-free domain adaptation for multi-institutional chest X-ray images.

Journal of applied clinical medical physics·2026
Same author

Diffusion prior-guided implicit neural representation for metal artifact reduction in sparse-view CT reconstruction.

Physics in medicine and biology·2026
Same author

X-ray Source Motion Deblurring Framework for Fast Scan in Digital Breast Tomosynthesis.

IEEE transactions on bio-medical engineering·2026
Same author

A 3D scan-driven method for activity estimation under complex source-detector geometries.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026
Same author

A strategy for simulation-driven CT metal artifact reduction toward improving network generalizability.

Medical physics·2026

Related Experiment Video

Updated: Sep 19, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.6K

Asymmetric scatter kernel estimation neural network for digital breast tomosynthesis.

Subong Hyun1, Seoyoung Lee1, Ilwong Choi2

  • 1KAIST, Department of Nuclear and Quantum Engineering, Daejeon, Republic of Korea.

Journal of Medical Imaging (Bellingham, Wash.)
|June 16, 2025
PubMed
Summary
This summary is machine-generated.

A novel deep learning approach inspired by asymmetric scatter kernel superposition improves scatter estimation in digital breast tomosynthesis (DBT). This physics-informed method enhances scatter correction for clearer medical imaging.

Keywords:
convolutional neural networkdigital breast tomosynthesisscatter correction

More Related Videos

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

43.0K
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

6.4K

Related Experiment Videos

Last Updated: Sep 19, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.6K
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

43.0K
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

6.4K

Area of Science:

  • Medical Imaging
  • Radiology
  • Deep Learning

Background:

  • Scatter radiation significantly degrades image quality in digital breast tomosynthesis (DBT).
  • Existing deep learning (DL) methods for scatter estimation often neglect the underlying physics of scatter formation.
  • End-to-end DL training approaches lack interpretability regarding scatter characteristics.

Purpose of the Study:

  • To propose a novel DL approach for scatter estimation in DBT, inspired by asymmetric scatter kernel superposition.
  • To develop a physics-informed method that accounts for the physical processes of scatter generation.
  • To improve the accuracy and reliability of scatter correction in DBT.

Main Methods:

  • A DL network was designed to generate scatter amplitude distribution, scatter kernel width, and asymmetric factor maps.
  • Euclidean distance maps and projection angle information were integrated to estimate the asymmetric factor, accounting for breast variations.
  • The proposed method was evaluated against UNet-based end-to-end and symmetric kernel approaches.

Main Results:

  • The proposed approach outperformed existing methods in scatter estimation accuracy on both numerical phantom and physical experimental data.
  • Quantitative metrics including signal-to-noise ratio (SNR) and structural similarity index measure (SSIM) showed significant improvements in scatter-corrected images.
  • The method demonstrated robust performance in handling variations in breast thickness and shape.

Conclusions:

  • The developed DL method represents a significant advancement in scatter estimation for DBT projections.
  • The physics-informed approach enables robust and reliable scatter correction, leading to enhanced diagnostic image quality.
  • This method holds promise for clinical applications requiring accurate scatter reduction in DBT.