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

A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction.

Eunhee Kang1, Junhong Min1, Jong Chul Ye1

  • 1Bio Imaging and Signal Processing Lab., Dept. of Bio and Brain Engineering, KAIST, Daejeon, Korea.

Medical Physics
|October 14, 2017
PubMed
Summary
This summary is machine-generated.

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

Development of a Sandwich-Type <i>sxtA4</i> Electrochemical Biosensor for Proactive Environmental Monitoring of STX-Producing Microalgae.

Biosensors·2026
Same author

Building a credibility-based framework for target discovery: Perspectives from tRNA synthetase-linked metabolic diseases.

Briefings in bioinformatics·2026
Same author

Image quality improvement of liver ultrasound using unsupervised deep learning.

PloS one·2026
Same author

Read like a radiologist: Efficient vision-language model for 3D medical imaging interpretation.

Medical image analysis·2026
Same author

Light-induced field effect transistor-based biosensor consisted of aptamer and ReS<sub>2</sub> single crystal layer for exosome detection.

Materials today. Bio·2026
Same author

Wholistic report generation for Breast ultrasound using LangChain.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

This study introduces a novel deep learning algorithm for low-dose X-ray CT reconstruction. The wavelet-domain convolutional neural network effectively reduces artifacts and noise, improving diagnostic reliability in medical imaging.

Area of Science:

  • Medical Imaging
  • Radiology
  • Computer Science

Background:

  • Reducing radiation exposure in X-ray CT scans is crucial to minimize cancer risks.
  • Low-dose CT scans often suffer from severe artifacts, compromising diagnostic accuracy.
  • Existing de-noising methods are computationally expensive or ineffective against CT-specific noise.

Purpose of the Study:

  • Develop an advanced low-dose X-ray CT reconstruction algorithm.
  • Address the limitations of conventional de-noising techniques.
  • Improve the quality and reliability of diagnostic images from low-dose CT scans.

Main Methods:

  • Proposed a deep learning algorithm utilizing a convolutional neural network (CNN).
  • Applied the CNN to wavelet transform coefficients of low-dose CT images.
Keywords:
convolutional neural networkdeep learninglow-dose x-ray CTwavelet transform

Related Experiment Videos

  • Employed a directional wavelet transform and residual learning architecture for enhanced noise suppression and training efficiency.

    • Main Results:

    • The algorithm effectively removed complex noise patterns in low-dose CT images.
    • Demonstrated superior efficiency compared to existing noise reduction methods.
    • Achieved second place in the 2016 Low-Dose CT Grand Challenge, validated by radiologists.

    Conclusions:

    • This work presents the first rigorously evaluated deep learning architecture for low-dose CT reconstruction.
    • The proposed algorithm shows significant potential for improvement with large datasets.
    • Opens new research avenues for low-dose CT image reconstruction.