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 Video

Updated: Nov 30, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

662

Multimodal Glioma Image Segmentation Using Dual Encoder Structure and Channel Spatial Attention Block.

Run Su1,2, Jinhuai Liu1,2, Deyun Zhang3

  • 1Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China.

Frontiers in Neuroscience
|November 16, 2020
PubMed
Summary

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

Multicenter real world validation of on device single lead ECG parameters for remote cardiac assessment.

NPJ cardiovascular health·2026
Same author

Brain metastatic paraganglioma from liver: a case report and review of the literature.

Journal of medical case reports·2026
Same author

Combined epigenomic landscapes of 5mC, 5hmC, and 6mA modifications in papillary thyroid carcinogenesis.

Communications biology·2026
Same author

Systemic remodeling of the glioblastoma microenvironment via plasma-induced vascular disruption and CSF-propelled oxidative therapy.

Free radical biology & medicine·2026
Same author

Reconstructing 12-lead ECG from 3-lead ECG using variational autoencoder to improve cardiac disease detection of wearable ECG devices.

PLOS digital health·2026
Same author

ECGomics: An Open Platform for AI-ECG Digital Biomarker Discovery.

Health data science·2026

F-S-Net, a new convolutional neural network, enhances glioma segmentation by fusing multimodal medical images. It achieves superior results by projecting images into a shared semantic space and focusing on lesion areas.

Area of Science:

  • Medical imaging analysis
  • Computational neuroscience
  • Artificial intelligence in medicine

Background:

  • Multimodal medical imaging offers complementary information crucial for accurate glioma segmentation.
  • Directly inputting diverse image sources into neural networks can limit segmentation performance.
  • Existing methods struggle to optimally leverage semantic information from varied imaging modalities.

Purpose of the Study:

  • To introduce F-S-Net, a novel convolutional neural network designed for effective multimodal medical image fusion and glioma segmentation.
  • To improve the semantic consistency and detail extraction from multimodal data for enhanced tumor delineation.
  • To establish a new benchmark in glioma segmentation accuracy using a specialized network architecture.

Main Methods:

Keywords:
CSABDESF-S-Netfully convolutional neural networksglioma segmentationmedical image fusion

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

3.2K

Related Experiment Videos

Last Updated: Nov 30, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

662
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

3.2K
  • F-S-Net employs a cascaded architecture with two sub-networks for multimodal image processing.
  • The first sub-network harmonizes images into a common semantic space, ensuring consistent semantic metrics.
  • The second sub-network integrates a dual encoder structure (DES) and channel spatial attention block (CSAB) within U-Net architectures for detailed feature extraction and lesion focus.

Main Results:

  • F-S-Net achieved a Dice coefficient of 0.9052 and Jaccard similarity of 0.8280 on a multimodal glioma dataset.
  • The proposed network demonstrated superior performance compared to several existing segmentation methods.
  • The integration of DES and CSAB effectively improved the focus on critical lesion areas.

Conclusions:

  • F-S-Net effectively fuses multimodal medical images for improved glioma segmentation.
  • The network's architecture successfully addresses the challenge of semantic information integration from diverse image sources.
  • F-S-Net represents a significant advancement in computational methods for brain tumor analysis.