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: Jan 8, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Advanced Multi-architecture Deep Learning Framework for BIRADS-Based Mammographic Image Retrieval: Comprehensive

M D Shaikh Rahman¹, Feiroz Humayara², Syed Maudud E Rabbi³

¹Department of Computer Science, Universiti Sains Malaysia, Penang, Malaysia. shaikhrahman25@gmail.com.

Journal of Imaging Informatics in Medicine

|December 16, 2025

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

Robust Autism Spectrum Disorder Screening Based on Facial Images (For Disability Diagnosis): A Domain-Adaptive Deep Ensemble Approach.

Diagnostics (Basel, Switzerland)·2025

Same author

Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization.

Diagnostics (Basel, Switzerland)·2024

Same author

Empirical Study of Autism Spectrum Disorder Diagnosis Using Facial Images by Improved Transfer Learning Approach.

Bioengineering (Basel, Switzerland)·2022

Same journal

Kolmogorov-Arnold Guided Local-Global Attention for Medical Image Classification.

Journal of imaging informatics in medicine·2026

Same journal

Artificial Intelligence-Assisted Inner Ear Computed Tomography Analysis: Radiomics-Based Comparison of Affected and Unaffected Ears in Idiopathic Sudden Sensorineural Hearing Loss.

Journal of imaging informatics in medicine·2026

Same journal

High Adoption, Higher Expectations: A Cross-Sectional Survey of Radiologist Engagement with Artificial Intelligence in the United Arab Emirates.

Journal of imaging informatics in medicine·2026

Same journal

Complex-valued Multi-scale Hybrid Attention Network for Fast MRI via Sparsified Data Learning.

Journal of imaging informatics in medicine·2026

Same journal

Automatic Phase and Sequence Identification in Gd-EOB-DTPA-Enhanced Liver MRI Using Deep Convolutional and Sequential Learning.

Journal of imaging informatics in medicine·2026

Same journal

Ultrasound-Based AI in Predicting Hormone Receptor Status in Breast Cancer: Is "Digital Biopsy" Possible.

Journal of imaging informatics in medicine·2026

See all related articles

This summary is machine-generated.

This study introduces an advanced framework for mammographic image retrieval, achieving state-of-the-art performance in five-class Breast Imaging Reporting and Data System (BIRADS) classification. DenseNet121 with advanced fine-tuning and test-time augmentation significantly improved accuracy and reduced computational costs.

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Content-based mammographic image retrieval is complex, requiring precise five-class Breast Imaging Reporting and Data System (BIRADS) matching.
Previous studies faced limitations in sample size, patient separation, and statistical validation, hindering clinical application.

Purpose of the Study:

To develop and evaluate a comprehensive framework for comparing Convolutional Neural Network (CNN) architectures and training strategies for five-class BIRADS retrieval.
To establish a new state-of-the-art model for accurate and efficient mammographic image retrieval.

Main Methods:

Systematic comparison of CNN architectures (DenseNet121, ResNet50, VGG16) using advanced training strategies: fine-tuning, metric learning, and super-ensemble optimization.

Keywords:

BIRADS classification Deep learning Ensemble methods Mammography Medical image retrieval Statistical validation

More Related Videos

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

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

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jan 8, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

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

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

Published on: November 30, 2022

Rigorous evaluation with patient-stratified data splits (1003 patients), 602 test queries, and bootstrap confidence intervals (1000 resamples) for reliable assessment.

Implementation of advanced fine-tuning and test-time augmentation (TTA) for the DenseNet121 model.

Main Results:

DenseNet121 with advanced fine-tuning and TTA (DenseNet121_AdvancedFT_TTA) achieved a precision@10 of 34.71%, a 25.74% improvement over the baseline ResNet50.
Super-ensemble and metric learning approaches demonstrated robust performance across architectures under patient-exclusive splits.
Statistical analysis confirmed significant performance gains and reproducibility (bootstrap CIs, t-tests p < 0.001, Cohen's d > 0.8).

Conclusions:

DenseNet121_AdvancedFT_TTA represents the new state-of-the-art for five-class BIRADS mammographic image retrieval.
The developed framework ensures reliable assessment and validates significant improvements in retrieval accuracy.
The findings suggest a more computationally efficient and accurate approach to mammographic image analysis.