Jove
Visualize
Contact Us

Related Concept Videos

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

You might also read

Related Articles

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

Sort by
Same author

Haploidentical hematopoietic stem cell transplant in paroxysmal nocturnal hemoglobinuria.

Leukemia & lymphoma·2016
Same author

Antimicrobial Blue Light Inactivation of Gram-Negative Pathogens in Biofilms: In Vitro and In Vivo Studies.

The Journal of infectious diseases·2016
Same author

Antimicrobial blue light inactivation of Candida albicans: In vitro and in vivo studies.

Virulence·2016
Same author

Validation and Application of an LC-MS-MS Method for the Determination of Ceftizoxime in Human Serum and Urine.

Journal of chromatographic science·2016
Same author

Antifungal activity of Rubus chingii extract combined with fluconazole against fluconazole-resistant Candida albicans.

Microbiology and immunology·2016
Same author

Biological characterization of metanephric mesenchymal stem cells from the Beijing duck.

Experimental and therapeutic medicine·2016
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: May 21, 2026

Neuronavigation-guided Repetitive Transcranial Magnetic Stimulation for Aphasia
08:48

Neuronavigation-guided Repetitive Transcranial Magnetic Stimulation for Aphasia

Published on: May 6, 2016

Proto-memformer: deformable memory transformer for Parkinson's MRI classification.

Ziyue Wang1,2, Yisong Yao3, Jia Chen4

  • 1Xiangya School of Nursing, Central South University, Changsha, China.

Scientific Reports
|May 19, 2026
PubMed
Summary

This study introduces Proto-MemFormer, a novel deep learning model for Parkinson's Disease (PD) MRI classification. The model achieves high accuracy, demonstrating its effectiveness and robustness in diagnosing PD from MRI scans.

Keywords:
Deformable attentionMRI classificationModel robustnessParkinson’s diseasePrototype memory

More Related Videos

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder
08:20

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder

Published on: August 11, 2015

Hybrid PET/MRI Imaging of Alzheimer's Disease Based on 18F-AV-1451
05:17

Hybrid PET/MRI Imaging of Alzheimer's Disease Based on 18F-AV-1451

Published on: April 18, 2025

Related Experiment Videos

Last Updated: May 21, 2026

Neuronavigation-guided Repetitive Transcranial Magnetic Stimulation for Aphasia
08:48

Neuronavigation-guided Repetitive Transcranial Magnetic Stimulation for Aphasia

Published on: May 6, 2016

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder
08:20

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder

Published on: August 11, 2015

Hybrid PET/MRI Imaging of Alzheimer's Disease Based on 18F-AV-1451
05:17

Hybrid PET/MRI Imaging of Alzheimer's Disease Based on 18F-AV-1451

Published on: April 18, 2025

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neurology

Background:

  • Parkinson's Disease (PD) diagnosis relies on clinical assessment and neuroimaging.
  • Accurate classification of PD using MRI is crucial for early intervention.
  • Existing deep learning models face challenges in capturing complex morphological and semantic features in PD MRI.

Purpose of the Study:

  • To propose a novel deep learning model, Proto-MemFormer, for enhanced Parkinson's Disease (PD) MRI classification.
  • To improve the aggregation of local and global features for more discriminative PD detection.
  • To enhance the robustness and stability of PD classification models.

Main Methods:

  • Developed a Prototype-Guided Deformable Memory Transformer (Proto-MemFormer) model.
  • Integrated a prototype-guided memory mechanism and deformable attention in the encoding stage.
  • Introduced a position-calibrated retrieval module in the decoding stage for improved feature alignment.

Main Results:

  • Achieved high performance on the NTUA-Parkinson dataset: Accuracy (93.45%), Precision (93.72%), Recall (93.21%), F1-Score (93.46%), and AUC (94.81%).
  • Outperformed current state-of-the-art deep learning methods for PD MRI classification.
  • Demonstrated stability and robustness with less than 3% performance fluctuation in scaling experiments.

Conclusions:

  • The Proto-MemFormer model offers a significant advancement in PD MRI classification.
  • The model's architecture effectively captures essential morphological and semantic information.
  • Proto-MemFormer shows promise for reliable and robust clinical application in PD diagnosis.