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

Mitochondrial transcription factor A (TFAM) polymorphisms and risk of late-onset Alzheimer's disease in Han Chinese.

Brain research·2010
Same author

[Central mechanism of electric-acupuncture at Zusanli (ST36) for gastric mucous membrane protection with FMRI].

Zhonghua yi xue za zhi·2010
Same author

[Clinical application of review criteria for complete blood analysis].

Zhonghua yi xue za zhi·2010
Same author

Rhizosphere characteristics of zinc hyperaccumulator Sedum alfredii involved in zinc accumulation.

Journal of hazardous materials·2010
Same author

Rosmarinic acid antagonized 1-methyl-4-phenylpyridinium (MPP+)-induced neurotoxicity in MES23.5 dopaminergic cells.

International journal of toxicology·2010
Same author

Evaluation of sphingolipid metabolism in renal cortex of rats with streptozotocin-induced diabetes and the effects of rapamycin.

Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association·2010

Related Experiment Video

Updated: Jun 18, 2025

Point of Care Transcranial Color-Coded Duplex Ultrasound of the Middle Cerebral Artery
04:01

Point of Care Transcranial Color-Coded Duplex Ultrasound of the Middle Cerebral Artery

Published on: August 9, 2024

623

Attention-enhanced dilated convolution for Parkinson's disease detection using transcranial sonography.

Shuang Chen1, Yuting Shi2,3, Linlin Wan2,3,4,5

  • 1School of Computer Science and Engineering, Central South University, No.932 South Lushan Road, Changsha, 410083, Hunan, China.

Biomedical Engineering Online
|July 31, 2024
PubMed
Summary

A new deep learning model, AMSNet, improves Parkinson's disease diagnosis using transcranial sonography (TCS) by automatically learning complex image features. This AI-driven approach offers higher accuracy than traditional methods for movement disorder diagnosis.

Keywords:
Attention mechanismsComputer-aided diagnosisDeep learningMovement disordersParkinson’s diseaseTranscranial sonography

More Related Videos

Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking
07:26

Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking

Published on: September 26, 2019

7.8K
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

1.8K

Related Experiment Videos

Last Updated: Jun 18, 2025

Point of Care Transcranial Color-Coded Duplex Ultrasound of the Middle Cerebral Artery
04:01

Point of Care Transcranial Color-Coded Duplex Ultrasound of the Middle Cerebral Artery

Published on: August 9, 2024

623
Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking
07:26

Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking

Published on: September 26, 2019

7.8K
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

1.8K

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Neurology and movement disorders

Background:

  • Transcranial sonography (TCS) is vital for Parkinson's disease (PD) diagnosis but faces challenges due to complex features and reliance on expert interpretation.
  • Current machine learning methods for TCS often require extensive feature engineering and may not capture deep image characteristics.
  • Deep learning has potential for TCS but lacks specific applications for movement disorders, leading to limited research.

Purpose of the Study:

  • To introduce AMSNet, a deep learning model designed to enhance the accuracy of diagnosing movement disorders using TCS images.
  • To overcome limitations of traditional machine learning by enabling automatic feature extraction from complex TCS data.
  • To leverage attention mechanisms and multi-scale processing for improved pathological feature identification in TCS.

Main Methods:

  • Developed AMSNet, a deep learning residual network incorporating attention mechanisms and multi-scale feature extraction.
  • Implemented a multi-scale feature extraction module to manage irregular morphological features and reduce noise/artifacts in TCS images.
  • Integrated a convolutional attention module and channel attention within a residual network to capture hierarchical textures and enhance feature representation.

Main Results:

  • The study analyzed TCS images and data from 1109 participants.
  • AMSNet achieved high classification accuracy (92.79%), precision (95.42%), and specificity (93.1%).
  • AMSNet outperformed existing machine learning algorithms and general deep learning models in TCS-based diagnosis.

Conclusions:

  • AMSNet demonstrates the potential of deep learning for automated feature extraction and diagnosis from TCS images, moving beyond manual feature engineering.
  • The model effectively learns deep pathological features, showcasing its capacity to interpret complex imaging data for movement disorder diagnosis.
  • This research highlights the significant promise of advanced deep learning techniques in advancing TCS applications for neurological conditions.