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

9.3K
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...
9.3K
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

9.7K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
9.7K

You might also read

Related Articles

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

Sort by
Same author

Image reconstruction from incomplete data via approximated pseudo-inverse and dual-domain coupled diffusion posterior sampling.

Quantitative imaging in medicine and surgery·2026
Same author

Detail preservation sparse-view CT image reconstruction via range-null space decomposition based diffusion priors.

Journal of X-ray science and technology·2026
Same author

Visual language model-assisted CT denoising via text-guided diffusion and fidelity maintenance.

Journal of X-ray science and technology·2026
Same author

Accelerating direct material decomposition via diffusion probabilistic model for Sparse-view spectral computed tomography.

Journal of X-ray science and technology·2025
Same author

Visual language model-assisted spectral CT reconstruction by diffusion and low-rank priors from limited-angle measurements.

Physics in medicine and biology·2025
Same author

Implicit neural prior-guided diffusion for spectral CT reconstruction.

Medical physics·2025

Related Experiment Video

Updated: Mar 13, 2026

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

3.6K

An interpretable cascaded residual iterative network for sparse-view spectral CT imaging.

Xinrui Zhang1, Shaoyu Wang2, Ningning Liang1

  • 1Key Laboratory of Imaging and Intelligent Processing, Information Engineering University, Zhengzhou, China.

Quantitative Imaging in Medicine and Surgery
|March 12, 2026
PubMed
Summary

A new interpretable cascaded residual iterative network (ICRIN) addresses challenges in spectral computed tomography (CT) imaging. This advanced deep learning framework enhances image reconstruction and material decomposition, improving quantitative analysis in spectral imaging.

Keywords:
Sparse-view imagingimage reconstructionmaterial decompositionmodel interpretabilityspectral computed tomography (spectral CT)

More Related Videos

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

763

Related Experiment Videos

Last Updated: Mar 13, 2026

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

3.6K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

763

Area of Science:

  • Medical Imaging
  • Computational Imaging
  • Artificial Intelligence

Background:

  • Sparse-view spectral tomographic image reconstruction is an ill-posed problem causing image distortion and noise.
  • Deep learning (DL) shows promise but faces challenges in interpretability, generalizability, and data consistency.
  • Existing DL methods lack a general framework for handling multiple dependent tasks in spectral imaging.

Purpose of the Study:

  • To establish a general framework for integrating multi-scene spectral imaging issues.
  • To develop a deep learning model capable of simultaneously handling spectral image reconstruction and material decomposition.
  • To improve interpretability, generalizability, and data consistency in spectral imaging tasks.

Main Methods:

  • Developed the interpretable cascaded residual iterative network (ICRIN) as a hybrid-domain iterative framework.
  • Integrated physical model-driven, compressed sensing, and data-driven priors for stability and data consistency.
  • Employed a residual iterative mechanism with a transformer attention module and an alternating minimization method for joint optimization.
  • Incorporated a feedback mechanism to enhance stability and performance in spectral imaging tasks.

Main Results:

  • ICRIN demonstrated superior interpretability and generalizability compared to state-of-the-art methods.
  • Achieved significant peak signal-to-noise ratio (PSNR) improvements: ~6.9 dB (low-energy images), ~6.6 dB (high-energy images), ~4.0 dB (bone), and ~8.4 dB (tissue).
  • The feedback mechanism further improved reconstructed images by ~3 dB and material images by ~1-3 dB.

Conclusions:

  • Established ICRIN as a general iterative framework with advantages in interpretability, generalizability, and data consistency.
  • ICRIN offers a robust solution for spectral computed tomography (CT) imaging tasks.
  • The framework enables multi-task imaging and material quantification in clinical settings.