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

Multi-kernel inception-enhanced vision transformer for plant leaf disease recognition.

Scientific reports·2025
Same author

AI-driven plant disease detection with tailored convolutional neural network.

Network (Bristol, England)·2025
Same author

An Enhanced Hyper-Parameter Optimization of a Convolutional Neural Network Model for Leukemia Cancer Diagnosis in a Smart Healthcare System.

Sensors (Basel, Switzerland)·2022
Same author

Brain Magnetic Resonance Imaging Classification Using Deep Learning Architectures with Gender and Age.

Sensors (Basel, Switzerland)·2022

Related Experiment Video

Updated: Sep 29, 2025

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging
11:03

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

9.5K

Hippocampus Segmentation Using U-Net Convolutional Network from Brain Magnetic Resonance Imaging (MRI).

Ruhul Amin Hazarika1, Arnab Kumar Maji2, Raplang Syiem2

  • 1Department of Information Technology, North Eastern Hill University, Shillong, Meghalaya, 793022, India. rahazarika@gmail.com.

Journal of Digital Imaging
|March 19, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces an improved U-Net Convolutional Network for segmenting the hippocampus in brain images. The enhanced model achieves a higher accuracy of 96.5% for early dementia detection.

Keywords:
Alzheimer’s DiseaseDeep Neural Network (DNN)HippocampusMachine LearningMagnetic Resonance ImageU-Net

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Related Experiment Videos

Last Updated: Sep 29, 2025

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging
11:03

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

9.5K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • The hippocampus is crucial for memory and intellectual functions, and is an early indicator in dementia like Alzheimer's disease.
  • Accurate segmentation of the hippocampus is vital for early dementia detection, but traditional methods struggle with its complex structure.
  • Machine learning, particularly Convolutional Neural Networks (CNNs), offers advanced capabilities for medical image analysis and prediction.

Purpose of the Study:

  • To develop and evaluate an improved U-Net Convolutional Network for precise hippocampus segmentation from 2D brain images.
  • To enhance the accuracy of early dementia stage classification through detailed hippocampus size and shape analysis.
  • To investigate the impact of architectural modifications on the performance of U-Net for medical image segmentation.

Main Methods:

  • A U-Net Convolutional Network architecture was employed for hippocampus segmentation in 2D brain MRI scans.
  • The original U-Net model was modified by replacing standard kernels with a combination of smaller kernels ([Formula: see text], [Formula: see text], [Formula: see text]) to enhance feature extraction.
  • Performance was evaluated based on segmentation accuracy, comparing the modified U-Net against the original architecture and other state-of-the-art methods.

Main Results:

  • The original U-Net architecture achieved an average hippocampus segmentation performance of 93.6%, outperforming existing methods.
  • The modified U-Net architecture demonstrated a significant improvement, reaching an average performance rate of 96.5%.
  • The enhanced U-Net model convincingly outperformed the original U-Net, highlighting the effectiveness of the architectural modifications.

Conclusions:

  • The modified U-Net Convolutional Network provides a highly accurate and effective method for hippocampus segmentation.
  • This advanced segmentation technique shows promise for improving the early detection and classification of dementia.
  • The study underscores the potential of deep learning for addressing challenges in neurological disorder diagnosis through medical image analysis.