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

Computed Tomography01:10

Computed Tomography

4.6K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
4.6K
Deconvolution01:20

Deconvolution

197
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
197
Imaging Studies III: Computed Tomography01:27

Imaging Studies III: Computed Tomography

29
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
29

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Clinical Characteristics and Risk Factors for Syphilis Among People Living With Human Immunodeficiency Virus: A Nationwide Population-Based Cohort Study in Korea.

Journal of Korean medical science·2026
Same author

Trends in cancer incidence among people with human immunodeficiency virus in South Korea: a nationwide National Health Insurance Service data-based study.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2026
Same author

Improving the efficiency of normalized metal artifact reduction via a unified forward projection.

Physics in medicine and biology·2026
Same author

Korean HIV/AIDS Cohort Study: Past Achievements, Present Directions, and Future Perspectives.

Jugan geon-gang gwa jilbyeong·2026
Same author

Dose-aware denoising diffusion model for low-dose CT.

Physics in medicine and biology·2025
Same author

Standardization of Lung CT Number Using COPD Gene2 Phantom Under Various Scanning Protocols.

Sensors (Basel, Switzerland)·2025

Related Experiment Video

Updated: Jul 24, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.9K

Chest tomosynthesis deblurring using CNN with deconvolution layer for vertebrae segmentation.

Yunsu Choi1, Hanjoo Jang1, Jongduk Baek2

  • 1School of Integrated Technology, Yonsei University, Incheon, South Korea.

Medical Physics
|July 4, 2023
PubMed
Summary

This study introduces a novel deblurring method for chest tomosynthesis, significantly improving vertebrae segmentation. The new technique enhances image quality and diagnostic accuracy by addressing artifacts from limited scan angles.

Keywords:
CNNDeblurTomosynthesis

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Related Experiment Videos

Last Updated: Jul 24, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.9K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Biomedical Engineering

Background:

  • Limited scan angles in tomosynthesis cause severe distortions and artifacts, degrading diagnostic performance.
  • Accurate vertebrae segmentation is critical for diagnosing spinal pathologies in chest tomosynthesis images.
  • Existing deblurring methods struggle with spatially varying properties of tomosynthesis images, leading to PSF estimation errors.

Purpose of the Study:

  • To develop an accurate vertebrae segmentation method for chest tomosynthesis by improving deblurring techniques.
  • To address the limitations of existing point-spread-function (PSF)-based deblurring methods that do not account for spatially varying properties.
  • To enhance deblurring performance by accurately estimating the PSF using sub-convolutional neural networks (CNNs).

Main Methods:

  • A novel deep learning (DL)-based deblurring network architecture was proposed, comprising four modules: block division, partial PSF, deblurring block, and assembling block.
  • The method was compared against the Feldkamp-Davis-Kress (FDK) algorithm, total-variation iterative reconstruction (TV-IR), 3D U-Net, FBPConvNet, and a two-phase deblurring method.
  • Performance was evaluated using vertebrae segmentation metrics (pixel accuracy, IoU, F-score) and pixel-based metrics (RMSE, VIF), along with 2D analyses (ASF, FWHM).

Main Results:

  • The proposed method significantly recovered original structures and improved image quality, outperforming existing techniques.
  • Quantitative evaluations showed substantial improvements: Intersection-over-Union (IoU) increased by 53.5%, F-score by 28.7%, and Visual Information Fidelity (VIF) by 63.2%.
  • Root Mean Squared Error (RMSE) was reduced by 80.3%, demonstrating effective restoration of vertebrae and surrounding soft tissue.

Conclusions:

  • A novel chest tomosynthesis deblurring technique was developed, specifically addressing vertebrae segmentation by accounting for spatially varying properties.
  • Quantitative results confirmed superior vertebrae segmentation performance compared to existing deblurring methods.
  • The proposed method offers a promising solution for enhancing diagnostic accuracy in chest tomosynthesis.