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 Videos

Depression detection from multimodalities based on LeNet with hunter-geese optimization.

Pradeep G1, Oswalt Manoj S2, S Karthikeyini3

  • 1Assistant Professor, Department of Computer Science and Engineering, Sri Krishna College of Engineering and Technology, Anna University, Kuniyamuthur, Coimbatore, 641008, India. pradeep.be2012@gmail.com.

Scientific Reports
|June 14, 2026
PubMed
Summary
This summary is machine-generated.

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

Intelligent emotion and behavior recognition for online learners using deep affective computing.

Scientific reportsยท2026
See all related articles

This study introduces HGMO-LeNet, a novel framework for detecting depression using Magnetic Resonance Imaging (MRI) and speech data. The model achieves high accuracy, offering a robust system for automated depression detection.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Depression diagnosis relies on subjective methods, leading to potential inaccuracies.
  • Single-modality approaches fail to capture the complexity of depression.
  • Early detection is crucial for effective intervention and reducing adverse outcomes.

Purpose of the Study:

  • To develop a novel, multimodal framework for enhanced depression detection.
  • To integrate Magnetic Resonance Imaging (MRI) and speech data for improved diagnostic accuracy.
  • To introduce the Hunter Geese Migration Optimization-based LeNet (HGMO-LeNet) model.

Main Methods:

  • Utilized adaptive Wiener and Gaussian filters for MRI and speech signal preprocessing, respectively.
  • Implemented ROI extraction and feature extraction (volumetric and textural) from MRI data.
Keywords:
Deep learningDepression detectionMagnetic resonance imagingMultimodalitySpeech signal

Related Experiment Videos

  • Employed a LeNet architecture fine-tuned with Hunter Geese Migration Optimization (HGMO) for depression detection from both modalities.
  • Merged outputs from MRI and speech using a correlation coefficient.

    • Main Results:

    • The HGMO-LeNet model achieved high performance metrics.
    • Achieved a maximum specificity of 91.000%, accuracy of 91.276%, and sensitivity of 92.266%.
    • Demonstrated superior performance compared to existing depression detection methods.

    Conclusions:

    • The proposed HGMO-LeNet framework offers a robust and accurate system for automated depression detection.
    • Multimodal data integration (MRI and speech) significantly enhances depression detection capabilities.
    • The study highlights the potential of advanced AI models in psychiatric diagnostics.