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

Improving Translational Accuracy02:07

Improving Translational Accuracy

11.7K
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...
11.7K

You might also read

Related Articles

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

Sort by
Same author

Robust Construction of Diffusion MRI Atlases with Correction for Inter-Subject Fiber Dispersion.

Computational diffusion MRI : MICCAI Workshop·2017
Same author

Robust Fusion of Diffusion MRI Data for Template Construction.

Scientific reports·2017
Same author

Learning-Based Multimodal Image Registration for Prostate Cancer Radiation Therapy.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2017
Same author

Segmenting hippocampal subfields from 3T MRI with multi-modality images.

Medical image analysis·2017
Same author

Joint Discriminative and Representative Feature Selection for Alzheimer's Disease Diagnosis.

Machine learning in medical imaging. MLMI (Workshop)·2017
Same author

Single- and Multiple-Shell Uniform Sampling Schemes for Diffusion MRI Using Spherical Codes.

IEEE transactions on medical imaging·2017

Related Experiment Video

Updated: Jul 31, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

458

Two-Stage Self-Supervised Cycle-Consistency Transformer Network for Reducing Slice Gap in MR Images.

Zhiyang Lu, Jian Wang, Zheng Li

    IEEE Journal of Biomedical and Health Informatics
    |May 1, 2023
    PubMed
    Summary

    This study introduces a Two-stage Self-supervised Cycle-consistency Transformer Network (TSCTNet) to reconstruct high-resolution (HR) magnetic resonance (MR) images from low-resolution (LR) data. TSCTNet effectively reduces slice gaps without requiring paired images, outperforming existing self-supervised learning methods.

    More Related Videos

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.8K
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.9K

    Related Experiment Videos

    Last Updated: Jul 31, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    458
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.8K
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.9K

    Area of Science:

    • Medical Imaging
    • Deep Learning
    • Computer Vision

    Background:

    • Clinical magnetic resonance (MR) imaging often uses large slice gaps, resulting in low-resolution (LR) images in the through-plane direction.
    • Reconstructing high-resolution (HR) MR images is desirable but challenging due to the scarcity of paired LR/HR training data required for fully supervised deep learning (DL) methods.
    • Conventional Convolutional Neural Networks (CNNs) struggle to capture long-range dependencies across spatially distant slices, limiting their ability to integrate relevant information.

    Purpose of the Study:

    • To develop a novel deep learning (DL) method for reconstructing high-resolution (HR) magnetic resonance (MR) images by reducing the slice gap.
    • To address the limitation of requiring paired low-resolution (LR) and HR images for training, which are difficult to obtain in clinical settings.
    • To improve the capture of long-range image dependencies across neighboring slices for more effective image reconstruction.

    Main Methods:

    • A Two-stage Self-supervised Cycle-consistency Transformer Network (TSCTNet) was proposed, integrating both Transformer and CNN architectures.
    • A novel two-stage self-supervised learning (SSL) strategy was designed, utilizing a cycle-consistency constraint for robust network pre-training and specialized refinement.
    • The hybrid architecture enables the exploration of both local and global slice representations for image interpolation.

    Main Results:

    • TSCTNet demonstrated superior performance in reducing the slice gap for MR image reconstruction compared to other self-supervised learning (SSL) based algorithms.
    • The proposed SSL strategy effectively enabled robust network pre-training and specialized refinement without the need for paired LR/HR data.
    • The hybrid Transformer and CNN structure successfully captured both local and global image dependencies for improved reconstruction quality.

    Conclusions:

    • The proposed TSCTNet offers an effective solution for reconstructing high-resolution (HR) MR images from low-resolution (LR) data, overcoming the limitations of paired data acquisition.
    • The novel two-stage self-supervised learning (SSL) strategy and hybrid network architecture provide a robust and high-performing approach for slice gap reduction in MR imaging.
    • TSCTNet represents a significant advancement in deep learning applications for medical image enhancement, particularly in scenarios with limited supervised training data.