Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Apr 23, 2026

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

Optimal query-based relevance feedback in medical image retrieval using score fusion-based classification.

Mohammad Behnam¹, Hossein Pourghassem

¹Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, 517, Najafabad, Isfahan, Iran.

Journal of Digital Imaging

|September 24, 2014

Summary

This study introduces a new content-based medical image retrieval (CBMIR) system. It improves retrieval accuracy by using image classification and a novel relevance feedback (RF) approach for medical X-ray 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

Berberine and Lung Cancer: From Pure Form to Its Nanoformulations.

Asia-Pacific journal of clinical oncology·2024

Same author

Therapeutic potential of Phycocyanin in gastrointestinal cancers and related disorders.

Molecular biology reports·2024

Same author

The role of aquaporin 4 in brain tumors: implications for pathophysiology, diagnosis and therapy.

Molecular biology reports·2022

Same author

PIWI-interacting RNAs and PIWI proteins in glioma: molecular pathogenesis and role as biomarkers.

Cell communication and signaling : CCS·2020

Same author

Therapeutic Potential of Berberine in the Treatment of Glioma: Insights into Its Regulatory Mechanisms.

Cellular and molecular neurobiology·2020

Same author

The correlation of helios and neuropilin-1 frequencies with parkinson disease severity.

Clinical neurology and neurosurgery·2020

Area of Science:

Medical Imaging
Computer Science
Information Retrieval

Background:

Content-based medical image retrieval (CBMIR) systems are crucial for managing large medical image databases.
Existing CBMIR systems face challenges with computational complexity and data fusion for diverse image modalities.
Effective classification and relevance feedback (RF) are essential for improving CBMIR performance.

Purpose of the Study:

To propose a novel CBMIR framework integrating an effective classification method and a new RF approach.
To enhance the efficiency and accuracy of retrieving medical images from large, diverse datasets.
To optimize query selection in the RF process for better retrieval results.

Main Methods:

Implemented query image classification using Gaussian Mixture Models (GMM) for feature descriptors to identify relevant clusters.

Related Experiment Videos

Last Updated: Apr 23, 2026

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

Calculated visual similarity within identified clusters and fused results using a feature similarity ranking level fusion algorithm.

Developed a novel RF approach based on density function estimation of positive images to refine search queries.

Main Results:

The proposed framework demonstrated acceptable performance in both image classification and retrieval on the ImageCLEF 2005 database.
Experimental results indicate improved retrieval accuracy compared to existing CBMIR systems.
The integration of GMM-based classification and the new RF strategy effectively addressed computational complexity and data fusion challenges.

Conclusions:

The developed CBMIR framework offers a promising solution for efficient and accurate retrieval of medical images.
The novel RF approach significantly enhances the relevance of search results.
This work contributes to advancing CBMIR systems for large-scale medical image analysis.