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: Nov 22, 2025

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

3.1K

Medical Image Retrieval Using Empirical Mode Decomposition with Deep Convolutional Neural Network.

Shaomin Zhang1, Lijia Zhi1, Tao Zhou1

  • 1School of Computer Science and Engineering, North Minzu University, Yinchuan 750021, China.

Biomed Research International
|January 11, 2021
PubMed
Summary

This study introduces a deep convolutional neural network (CNN) framework for content-based medical image retrieval (CBMIR). The method enhances feature representation for accurate and fast retrieval of medical images.

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

Three-dimensional helical integration of high-density linear microelectrode arrays and their cross-tissue applications.

Biosensors & bioelectronics·2026
Same author

Engineered Injectable Coaxial Supramolecular Hydrogel for a Minimally Invasive Neural Electrode.

ACS applied bio materials·2026
Same author

Differential Enrichment of Organic Matter in the Da'anzhai Member of the Sichuan Basin: A Response to the Toarcian Oceanic Anoxic Event.

ACS omega·2026
Same author

Chiral D-peptide composite hydrogels enable sustained RepSox delivery and antifibrotic remodeling after myocardial infarction.

Biomaterials·2026
Same author

Cortical and Cortico-Muscular Network Modulation Pattern of Eccentric and Concentric Movements in Fatigue State.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Charge-Engineered COFs for Biointegrated Memristor Nerves.

Advanced materials (Deerfield Beach, Fla.)·2026

Area of Science:

  • Medical Imaging
  • Computer Science
  • Artificial Intelligence

Background:

  • Content-based medical image retrieval (CBMIR) faces challenges in bridging the semantic gap for high-level medical information representation.
  • Feature representation is critical for the accuracy and speed of CBMIR systems.

Purpose of the Study:

  • To propose a novel deep convolutional neural network (CNN) framework for learning concise feature vectors in medical image retrieval.
  • To improve the efficacy of feature representation in CBMIR systems.

Main Methods:

  • Medical images were decomposed into five components using empirical mode decomposition (EMD).
  • A deep CNN was trained in a supervised manner with multicomponent input to learn discriminative features.
  • The learned features were utilized for medical image retrieval and classification tasks.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K

Related Experiment Videos

Last Updated: Nov 22, 2025

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

3.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K

Main Results:

  • The proposed method achieved a mean average precision of 0.86 for the retrieval task on the IRMA dataset.
  • For classification, the method obtained an F1 score of 0.66.
  • These results represent the best performance reported in existing literature for this dataset.

Conclusions:

  • The developed CNN-based framework effectively learns concise feature vectors for enhanced medical image retrieval.
  • The approach demonstrates significant improvements in both retrieval and classification tasks, outperforming previous methods on the IRMA dataset.