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

Multimodal Feature Prototype Learning for Interpretable and Discriminative Cancer Survival Prediction.

IEEE journal of biomedical and health informatics·2026
Same author

Vagus nerve stimulation for patients with tuberous sclerosis complex-related drug-resistant epilepsy: A prospective cohort study.

Epilepsia·2026
Same author

GALNT5 drives colorectal cancer progression and chemoresistance via PI3K/Akt/ABCC1 axis.

Journal of cancer research and clinical oncology·2026
Same author

Carbon Materials as Lithium-Free Anode for Hybrid Lithium-Ion/Metal Batteries: Mechanism, Design Strategy, In Situ Characterization, and Prospects.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Progressive Fusion of Multi-Scale Mamba Context and Local Detail Priors for Infrared Small Target Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Pediatric epilepsy surgery: Global survey of invasive explorations.

Epilepsia·2026

Related Experiment Video

Updated: Jun 13, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

378

Focal cortical dysplasia lesion segmentation using multiscale transformer.

Xiaodong Zhang1,2, Yongquan Zhang3, Changmiao Wang4

  • 1Shenzhen Children's Hospital, Shenzhen, 518000, Guangdong, China.

Insights Into Imaging
|September 12, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a novel transformer-based model for accurate segmentation of focal cortical dysplasia (FCD) lesions in MR images, improving preoperative evaluation for neurosurgeons.

Keywords:
Drug-resistant epilepsyDual-self-attentionFocal cortical dysplasiaLesion segmentationTransformer

More Related Videos

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.2K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

47.9K

Related Experiment Videos

Last Updated: Jun 13, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

378
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.2K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

47.9K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • Accurate segmentation of focal cortical dysplasia (FCD) lesions from MR images is crucial for surgical planning but remains challenging.
  • Existing methods often struggle with the complexity and variability of FCD lesions.

Purpose of the Study:

  • To introduce a novel transformer-based model for end-to-end segmentation of FCD lesions from multi-channel MR images.
  • To improve the accuracy and efficiency of FCD lesion identification for clinical applications.

Main Methods:

  • Developed a model integrating a CNN encoder-decoder with a multiscale transformer for enhanced feature representation.
  • Utilized dual-self-attention modules to capture long-range dependencies and emphasize lesion-relevant features.
  • Trained and evaluated the model on a public dataset of 85 patients using subject-level and voxel-level metrics.

Main Results:

  • The model achieved superior quantitative and qualitative performance compared to five established methods.
  • Successfully identified lesions in 82.4% of patients with a low false-positive rate (0.176 ± 0.381 per patient).
  • Attained an average Dice coefficient of 0.410 ± 0.288.

Conclusions:

  • The integration of transformers significantly enhances feature representation and segmentation performance for FCD lesions.
  • The proposed model shows potential as an assistive tool for rapid and accurate preoperative evaluation of FCD patients.
  • This work provides a valuable benchmark for future research in FCD lesion segmentation.