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

You might also read

Related Articles

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

Sort by
Same author

Dual responsive enzyme mimicking activity of AgX (X=Cl, Br, I) nanoparticles and its application for cancer cell detection.

ACS applied materials & interfaces·2014
Same author

Naphthoquinone-directed C-H annulation and C(sp³)-H bond cleavage: one-pot synthesis of tetracyclic naphthoxazoles.

The Journal of organic chemistry·2014
Same author

Pulmonary toxicity in mice following exposure to cerium chloride.

Biological trace element research·2014
Same author

Role of surgery in the treatment of patients with high-risk neuroblastoma who have a poor response to induction chemotherapy.

Journal of pediatric surgery·2014
Same author

Glutathione-S-transferase polymorphisms (GSTM1, GSTT1 and GSTP1) and acute leukemia risk in Asians: a meta-analysis.

Asian Pacific journal of cancer prevention : APJCP·2014
Same author

Influence of casting solvent on phenyl ordering at the surface of spin cast polymer thin films.

Journal of colloid and interface science·2014
Same journal

Deep infant brain segmentation from multi-contrast MRI.

Conference record. Asilomar Conference on Signals, Systems & Computers·2026
Same journal

Physics-driven Learned Deconvolution of Multi-spectral Cellular MRI with Radial Sampling.

Conference record. Asilomar Conference on Signals, Systems & Computers·2025
Same journal

Multilevel State-Space Models Enable High Precision Event Related Potential Analysis.

Conference record. Asilomar Conference on Signals, Systems & Computers·2024
Same journal

A novel method for 12-lead ECG reconstruction.

Conference record. Asilomar Conference on Signals, Systems & Computers·2024
Same journal

A mechanistically interpretable model of the retinal neural code for natural scenes with multiscale adaptive dynamics.

Conference record. Asilomar Conference on Signals, Systems & Computers·2023
Same journal

Topological Knowledge Distillation for Wearable Sensor Data.

Conference record. Asilomar Conference on Signals, Systems & Computers·2023
See all related articles

Related Experiment Video

Updated: Dec 31, 2025

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis
09:41

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis

Published on: July 19, 2019

11.9K

Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks.

Chi Zhang1,2, Steen Moeller2, Sebastian Weingärtner1,2,3

  • 1Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN.

Conference Record. Asilomar Conference on Signals, Systems & Computers
|January 2, 2020
PubMed
Summary
This summary is machine-generated.

Robust Artificial-neural-networks for k-space Interpolation (RAKI) enhances simultaneous multi-slice (SMS) magnetic resonance imaging (MRI) reconstruction. This deep learning method significantly improves functional MRI image quality, particularly at higher acceleration rates.

More Related Videos

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
08:51

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

9.6K
High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

13.3K

Related Experiment Videos

Last Updated: Dec 31, 2025

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis
09:41

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis

Published on: July 19, 2019

11.9K
Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
08:51

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

9.6K
High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

13.3K

Area of Science:

  • Magnetic Resonance Imaging (MRI)
  • Medical Imaging
  • Artificial Intelligence in Healthcare

Background:

  • Simultaneous multi-slice (SMS) or multi-band (MB) imaging accelerates magnetic resonance imaging (MRI) acquisition by exciting and acquiring multiple slices concurrently.
  • Current SMS/MB reconstruction relies on linear techniques, which may limit achievable image quality and acceleration factors.
  • Robust Artificial-neural-networks for k-space Interpolation (RAKI) is a nonlinear reconstruction method using convolutional neural networks (CNNs) that has shown promise in improving parallel imaging.

Purpose of the Study:

  • To extend the Robust Artificial-neural-networks for k-space Interpolation (RAKI) nonlinear reconstruction method to simultaneous multi-slice (SMS) / multi-band (MB) imaging.
  • To evaluate the performance of RAKI for functional MRI (fMRI) data reconstruction under various acceleration conditions.
  • To optimize CNN network parameters for RAKI in the context of SMS/MB imaging.

Main Methods:

  • Convolutional neural networks (CNNs) were trained using subject-specific calibration data acquired prior to SMS/MB imaging.
  • The RAKI method was adapted for SMS/MB reconstruction, utilizing redundancies in receiver coil arrays.
  • Extensive parameter space search was conducted to optimize CNN network parameters for RAKI.

Main Results:

  • RAKI demonstrated substantial improvements in image quality compared to a standard linear reconstruction algorithm for SMS/MB imaging.
  • Performance gains were particularly notable at higher acceleration rates, indicating enhanced reconstruction capabilities.
  • The optimized RAKI method effectively reconstructed functional MRI (fMRI) time-series data.

Conclusions:

  • The Robust Artificial-neural-networks for k-space Interpolation (RAKI) method can be successfully extended to simultaneous multi-slice (SMS) / multi-band (MB) MRI.
  • RAKI offers superior image reconstruction performance over linear methods for SMS/MB imaging, especially at high acceleration factors.
  • This deep learning approach holds significant potential for advancing accelerated MRI techniques, including fMRI.