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 Video

Updated: Jul 16, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Interpretable 2D Deep Learning for Alzheimer's Detection from sMRI: A Lightweight Residual CNN Approach with

Vyshnavi Ramineni1, Jun-Hyung Kim1, Goo-Rak Kwon1

  • 1Department of Information and Communication Engineering, Chosun University, Gwangju 61452, Republic of Korea.

Sensors (Basel, Switzerland)
|July 15, 2026
PubMed
Summary

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

Refractive and Visual Outcomes of SmartSight NOVA Refractive Lenticule Extraction for Myopia and Myopic Astigmatism at 3 Months: a Retrospective Case Series.

Ophthalmology and therapy·2026
Same author

APOE ε4 Allele Dose and Time to Clinical Conversion from Mild Cognitive Impairment to Alzheimer's Disease Dementia: An ADNI Survival Analysis.

Biomedicines·2026
Same author

APOE ε4 as a predictor of cognitive decline and its interaction with hippocampal volume in Alzheimer's disease.

Frontiers in aging neuroscience·2026
Same author

Cryoballoon Ablation of Atrial Fibrillation in Patients With Hypertrophic Cardiomyopathy: From the Korean Cryoballoon Ablation Registry.

Korean circulation journal·2025
Same author

Cryoballoon Ablation for Elderly Patients With Atrial Fibrillation: Results From the Korean Cryoballoon Registry.

Korean circulation journal·2025
Same author

Antioxidant and Antiaging Activity of <i>Houttuynia cordata</i> Thunb. Ethyl Acetate Fraction in <i>Caenorhabditis elegans</i>.

Nutrients·2024

This study introduces an advanced deep learning model for early Alzheimer's disease (AD) detection using structural MRI scans. The framework effectively identifies AD biomarkers, improving diagnostic accuracy for AD and mild cognitive impairment (MCI).

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Neurology

Background:

  • Early detection of Alzheimer's disease (AD) is crucial for timely intervention.
  • Structural MRI (sMRI) is a promising neuroimaging modality for AD diagnosis.
  • Existing deep learning models can be computationally intensive.

Purpose of the Study:

  • To develop an enhanced deep learning framework for early AD detection using sMRI data.
  • To extract critical AD biomarkers with improved efficiency.
  • To achieve superior multiclass classification performance for AD and mild cognitive impairment (MCI).

Main Methods:

  • A novel Convolutional Neural Network (CNN) architecture with residual and skip connections was designed.
  • A comprehensive preprocessing pipeline included quality control, resizing, normalization, and data augmentation of 3D MRI scans into 2D slices.
Keywords:
Alzheimer’s Disease Neuroimaging Initiative (ADNI)Alzheimer’s disease (AD)convolutional neural network (CNN)structural magnetic resonance imaging

Related Experiment Videos

Last Updated: Jul 16, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

  • Stratified, subject-level data partitioning and bootstrapping were used for validation.

    • Main Results:

    • The proposed CNN achieved efficient feature extraction with lower computational cost than VGG-16.
    • The framework demonstrated superior multiclass classification performance across AD, early MCI, late MCI, and cognitively normal groups.
    • Grad-CAM interpretability maps highlighted disease-relevant regions, including the hippocampus and temporal lobe.

    Conclusions:

    • The enhanced deep learning framework shows significant potential for accurate and efficient early AD detection.
    • The model's ability to identify key brain regions involved in AD progression was confirmed.
    • This approach facilitates timely clinical intervention by improving diagnostic capabilities.