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

Neural network synthesis of spin echo multiecho sequences.

S Cagnoni1, D Caramella, R De Dominicis

  • 1Department of Electronic Engineering, University of Florence, Italy.

Journal of Digital Imaging
|May 1, 1992
PubMed
Summary

Artificial neural networks can reconstruct synthetic spin echo multiecho brain images. This method preserves contrast and improves signal-to-noise ratio compared to traditional sequences.

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

Is fossil fuel combustion still a major contributor to atmospheric aerosol carbonaceous fractions in the Po Valley? Results from a <sup>14</sup>C-based source apportionment.

Environmental pollution (Barking, Essex : 1987)·2024
Same author

Consistent determination of the heating rate of light-absorbing aerosol using wavelength- and time-dependent Aethalometer multiple-scattering correction.

The Science of the total environment·2021
Same author

Effectiveness of Progressive Muscle Relaxation and Deep Breathing Exercise on Pain, Disability, and Sleep Among Patients With Chronic Tension-Type Headache: A Randomized Control Trial.

Holistic nursing practice·2021
Same author

PROMs in post-mastectomy care: Patient self-reports (BREAST-Q™) as a powerful instrument to personalize medical services.

European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology·2019
Same author

Composition and origin of PM<sub>2.5</sub> in Mediterranean Countryside.

Environmental pollution (Barking, Essex : 1987)·2018
Same author

mRECIST criteria to assess recurrent thyroid carcinoma treatment response after radiofrequency ablation: a prospective study.

Journal of endocrinological investigation·2018

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Spin echo multiecho sequences are underutilized in clinical settings due to single-slice limitations per acquisition.
  • Current multislice techniques often compromise echo information to reduce scan times.
  • T2-weighted imaging is valuable for tissue contrast but limited by sequence constraints.

Purpose of the Study:

  • To investigate the use of artificial neural networks (ANNs) for synthesizing spin echo multiecho (SEME) images.
  • To evaluate the diagnostic utility and image quality of ANN-generated SEME brain images.
  • To determine if ANNs can overcome the limitations of conventional SEME sequences.

Main Methods:

  • Training an artificial neural network using a dataset of spin echo multiecho brain images.

Related Experiment Videos

  • Utilizing the trained ANN to synthesize SEME images from a limited number of input images (two per slice).
  • Comparing the quality and contrast characteristics of synthetic SEME images with true SEME images.

    • Main Results:

    • ANNs successfully reconstructed synthetic SEME brain images.
    • The generated images maintained the contrast properties of true SEME sequences.
    • Synthetic images exhibited an improved signal-to-noise (SNR) ratio compared to original images.

    Conclusions:

    • ANNs offer a viable method to generate high-quality synthetic SEME images.
    • This approach enhances diagnostic information by improving SNR and preserving contrast.
    • Neural network-based synthesis can potentially increase the clinical utility of SEME sequences in brain imaging.