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 Experiment Videos

Low-dose CT reconstruction using spatially encoded nonlocal penalty.

Kyungsang Kim1, Georges El Fakhri1, Quanzheng Li1

  • 1Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, 125 Nashua Street 6th floor, Suite 660, Boston, MA, 02114, USA.

Medical Physics
|October 14, 2017
PubMed
Summary

This study introduces an iterative method to enhance low-dose computed tomography (CT) images, significantly improving diagnostic quality at a quarter of the standard radiation dose. The optimized technique achieved results comparable to regular-dose CT scans.

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

Open-Geometry PET: Quantifying the Trade-off Between Time-of-Flight Resolution and Angular Coverage.

Physics in medicine and biology·2026
Same author

Integrated Coronary CT Angiography Assessment of Plaque Vulnerability and Clinical Outcomes: The Morphology-Inflammation-Burden (MIB) Score.

JACC. Cardiovascular imaging·2026
Same author

Adaptive thresholding for CT metal artifact reduction via LangGraph.

Physics in medicine and biology·2026
Same author

An Open Multi-Center Whole-Body FDG PET/CT Foundation Model for Tumor Segmentation.

ArXiv·2026
Same author

Influence of an AQP4 haplotype and sleep duration on early Alzheimer's disease.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

An artificial intelligence model for prediction of hepatocellular carcinoma risk in patients with chronic hepatitis C.

Scientific reports·2026

Area of Science:

  • Medical Imaging
  • Image Reconstruction
  • Radiology

Background:

  • Computed tomography (CT) is essential for patient imaging but faces challenges with image quality degradation at reduced radiation doses.
  • Noise and artifacts in low-dose CT images compromise diagnostic accuracy, necessitating advanced reconstruction techniques.
  • Optimizing image quality while minimizing radiation exposure is a critical goal in medical imaging.

Purpose of the Study:

  • To enhance the image quality of quarter-dose CT scans.
  • To identify optimal hyperparameters for the proposed reconstruction method using regular-dose images as a reference.
  • To evaluate the diagnostic performance of the enhanced low-dose CT images.

Main Methods:

  • Developed an iterative CT reconstruction algorithm incorporating a spatially encoded nonlocal penalty and ordered subsets separable quadratic surrogates (OS-SQS).
Keywords:
Grand ChallengeLow-dose CT reconstructionspatially encoded nonlocal penalty

Related Experiment Videos

  • Utilized Nesterov's momentum for acceleration and a diminishing number of subsets strategy for noise consistency.
  • Employed a bias and standard deviation study with regular-dose filtered back-projection (FBP) images as ground truth for hyperparameter tuning.

    • Main Results:

    • The proposed method with optimized hyperparameters significantly improved image quality in quarter-dose CT data.
    • Reconstructed quarter-dose images were found to be comparable to regular-dose FBP images and superior to other low-dose CT reconstruction methods.
    • The method achieved first place in the Low Dose CT Grand Challenge, validated on phantom and patient data by radiologists.

    Conclusions:

    • The proposed iterative reconstruction method effectively enhances image quality and diagnostic features in quarter-dose CT scans.
    • Fine-tuned hyperparameters are crucial for achieving high-quality diagnostic images at reduced radiation levels.
    • Further research is needed to improve performance for small lesion detection and conduct broader clinical evaluations.