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

Reducing Line Loss01:18

Reducing Line Loss

168
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
168
Deconvolution01:20

Deconvolution

180
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
180
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.5K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.5K
Convolution Properties II01:17

Convolution Properties II

224
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
224
Convolution Properties I01:20

Convolution Properties I

170
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
170
Upsampling01:22

Upsampling

254
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
254

You might also read

Related Articles

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

Sort by
Same author

EURO-PROBE - Manual segmentations of the prostate and intraprostatic urethra on T2-weighted MRI.

Scientific data·2026
Same author

Quantitative assessment of flow between cerebrospinal and interstitial fluid compartments in humans.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Automatic segmentation of the urethra and prostate zones with deep learning on T2-weighted magnetic resonance imaging.

Physics and imaging in radiation oncology·2026
Same author

Applying nephelometry for analyzing liquid yeast cultures.

Biochemistry and biophysics reports·2026
Same author

Metastasis-directed SBRT for oligometastatic hormone sensitive prostate cancer (METRO): protocol for a prospective randomised phase III trial, NCT04983095.

BMC cancer·2026
Same author

From digital chest tomosynthesis to 3D CT.

Radiation protection dosimetry·2026

Related Experiment Video

Updated: Jul 15, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

568

Improving MR image quality with a multi-task model, using convolutional losses.

Attila Simkó1, Simone Ruiter2, Tommy Löfstedt3

  • 1Department of Radiation Sciences, Umeå University, Umeå, Sweden. attila.simko@umu.se.

BMC Medical Imaging
|October 2, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a multi-task learning model for Magnetic Resonance Imaging (MRI) artefact correction, significantly improving image quality by simultaneously addressing bias fields, super-resolution, motion, and noise. The novel approach outperforms individual correction methods and enhances realism.

Keywords:
Image artefact correctionMachine learningMagnetic resonance imaging

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

439
Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
09:27

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

7.1K

Related Experiment Videos

Last Updated: Jul 15, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

568
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

439
Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
09:27

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

7.1K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Image Processing

Background:

  • Magnetic Resonance Imaging (MRI) data acquisition is susceptible to artefacts from patient, sequence, or hardware factors, degrading image quality.
  • Key challenges in improving MRI image quality include bias field correction, super-resolution, motion correction, and noise correction.
  • While machine learning excels at individual artefact correction, multi-task learning approaches for simultaneous correction are underexplored.

Purpose of the Study:

  • To develop and evaluate a multi-task learning model for simultaneous correction of four major MRI artefacts.
  • To investigate the efficacy of a novel loss function that reconstructs image gradients for sharper, more realistic outputs.
  • To compare the multi-task model's performance against individual artefact correction methods.

Main Methods:

  • Developed a multi-task learning model for simultaneous MRI artefact correction.
  • Trained separate models on brain and pelvic scan datasets with corresponding artefact augmentations.
  • Implemented a novel convolutional loss function focusing on pixel values and image gradients, alongside mean squared error loss for comparison.
  • Utilized Friedman and Nemenyi tests to assess the statistical significance of method differences.

Main Results:

  • The proposed multi-task model consistently achieved equal or superior performance compared to individual artefact correction methods across various metrics.
  • The multi-task model effectively handled images with multiple simultaneous artefacts, unlike sequential application of individual correction models.
  • The novel convolutional loss function significantly outperformed mean squared error loss, particularly in perceptual quality metrics like Visual Information Fidelity.

Conclusions:

  • Two multi-task models for MRI artefact correction (brain and pelvic scans) were successfully trained.
  • A novel loss function was demonstrated to significantly enhance output image quality over standard mean squared error.
  • The developed approach shows robust performance on real-world data, offering insights into artefact detection and correction, with code made publicly available.