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

Naming learner agency at the bedside: FPTAL (from passive reception to active learning) as a dialogic bridge.

Academic medicine : journal of the Association of American Medical Colleges·2026
Same author

CitNAC71-CitNAC76 coordinate cellulose and hemicellulose biosynthesis to regulate high-temperature-mediated granulation in citrus.

The Plant cell·2026
Same author

Inflammatory protein mediators linking gut microbiota to degenerative lumbar spine disorders: cross-disease genetic evidence.

Frontiers in immunology·2026
Same author

Targeting N<sup>1</sup>-methyladenosine modification in osteoblasts through tRNA methyltransferase 10C reverses mitochondrial dysfunction and ameliorates osteoporosis.

Signal transduction and targeted therapy·2026
Same author

Mapping the iceberg: from focal trauma to a spectrum of systemic complications in spinal cord injury.

Science bulletin·2026
Same author

Spinal cord injury induces acute microbiome shock and system-wide transcriptomic reprogramming.

iMeta·2026
Same journal

Iron overload induces ROS-mediated neural stem/progenitor cells apoptosis via mTOR pathway.

BMC neuroscience·2026
Same journal

Combined maternal separation and limited bedding-nesting increase goal tracking, delay discounting, and impulsive action, and moderate sign-tracking-perseverance associations in male rats.

BMC neuroscience·2026
Same journal

Glycine as a potential neuroprotective adjuvant to reduce cisplatin-induced brain inflammation in mice.

BMC neuroscience·2026
Same journal

Using combined ROC curves to improve the diagnostic usefulness of glutaminase, prostaglandins, and 8-isoprostane as biomarkers of autism spectrum disorders;Role in the Glu-GABA-Gln cycle.

BMC neuroscience·2026
Same journal

Age-related susceptibility to paraquat-induced neurotoxicity in male wistar rats: effects on neurobehaviour, substantia nigra cytoarchitecture, and alpha-synuclein levels.

BMC neuroscience·2026
Same journal

Proteomic profiling reveals structural and adhesion pathways regulated by the inverted CHRFAM7AΔ2bp variant in human neural progenitor cells.

BMC neuroscience·2026
See all related articles

Related Experiment Video

Updated: Jul 16, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

440

A spine segmentation method based on scene aware fusion network.

Elzat Elham Yilizati-Yilihamu1, Jintao Yang2, Zimeng Yang1

  • 1Department of Orthopaedics, Qilu Hospital of Shandong University, Shandong University, Jinan, China.

BMC Neuroscience
|September 14, 2023
PubMed
Summary
This summary is machine-generated.

A novel deep learning network, SAFNet, enhances lumbar spine MRI analysis by improving segmentation accuracy for conditions like disc herniation and stenosis. This automated approach aims to reduce diagnostic errors and increase efficiency in radiological interpretations.

Keywords:
3D segmentationDeep learningMRISpine

More Related Videos

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites
07:45

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites

Published on: September 27, 2024

2.2K
Three-dimensional Quantification of Dendritic Spines from Pyramidal Neurons Derived from Human Induced Pluripotent Stem Cells
10:18

Three-dimensional Quantification of Dendritic Spines from Pyramidal Neurons Derived from Human Induced Pluripotent Stem Cells

Published on: October 10, 2015

11.6K

Related Experiment Videos

Last Updated: Jul 16, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

440
Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites
07:45

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites

Published on: September 27, 2024

2.2K
Three-dimensional Quantification of Dendritic Spines from Pyramidal Neurons Derived from Human Induced Pluripotent Stem Cells
10:18

Three-dimensional Quantification of Dendritic Spines from Pyramidal Neurons Derived from Human Induced Pluripotent Stem Cells

Published on: October 10, 2015

11.6K

Area of Science:

  • Radiology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Lumbar spine diseases such as intervertebral disc herniation and degenerative lumbar spinal stenosis affect various age groups.
  • Magnetic Resonance Imaging (MRI) is crucial for diagnosing lumbar spine lesions due to its high soft tissue resolution.
  • Current diagnostic accuracy relies heavily on radiologist experience, leading to subjectivity, inter-observer variability, and diagnostic inefficiencies.

Purpose of the Study:

  • To develop a standardized and automated method for interpreting and classifying lumbar spine MRI.
  • To address the challenges of subjective errors and diagnostic inconsistencies in current lumbar spine MRI analysis.
  • To introduce a deep learning network, SAFNet, for objective and consistent interpretation of lumbar spine MRI.

Main Methods:

  • Extraction of low-level, mid-level, and high-level features from spine MRI scans.
  • Application of Atrous Spatial Pyramid Pooling (ASPP) for processing high-level features.
  • Utilization of multi-scale feature fusion to enhance perception of low-level and mid-level features.
  • Integration of global adaptive pooling and Sigmoid function for refining high-level features.
  • Concatenation of processed features at the channel dimension for final output.

Main Results:

  • SAFNet achieved an average Dice Similarity Coefficient (DSC) of 80.32% ± 5.00% for segmenting 17 vertebral structures across five folds.
  • Individual fold DSC scores ranged from 78.82% ± 7.97% to 81.32% ± 3.45%.
  • The proposed SAFNet demonstrated superior segmentation results compared to existing methods.

Conclusions:

  • SAFNet is a highly accurate and robust deep learning network for spine segmentation.
  • The network provides effective anatomical segmentation crucial for diagnostic purposes.
  • The study highlights the potential of SAFNet in improving the accuracy of radiological diagnoses for spinal and lumbar diseases.