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

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

Improved salp swarm algorithm based optimization of mobile task offloading.

PeerJ. Computer science·2025

Same author

Performance of Current Diagnostic Tools in Detecting Latent Tuberculosis Among Healthcare Workers: A Systematic Review.

Cureus·2024

Same author

Diagnostic Test Precision of Modified Carbapenem Inactivation Method and Carbapenemase Nordmann-Poirel Test for Phenotypic Detection of Carbapenemase Production in Enterobacterales: A Systematic Review.

Cureus·2024

Same author

Therapeutic Plasma exchange therapy in Burns.

Journal of cutaneous and aesthetic surgery·2024

Same author

To Study the Correlation of Serum Adenosine Deaminase Levels with Hba1c in Patients of Type 2 Diabetes Mellitus.

The Journal of the Association of Physicians of India·2022

Same author

A Multilevel Transfer Learning Technique and LSTM Framework for Generating Medical Captions for Limited CT and DBT Images.

Journal of digital imaging·2022

Search research articles

Related Experiment Video

Updated: Nov 6, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Augmenting Transfer Learning with Feature Extraction Techniques for Limited Breast Imaging Datasets.

Aswiga R V¹, Aishwarya R², Shanthi A P²

¹Department of Computer Science and Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Chennai, Tamil Nadu, India. aswiga91@gmail.com.

Journal of Digital Imaging

|May 11, 2021

Summary

This study introduces a novel two-level transfer learning framework for classifying digital breast tomosynthesis (DBT) images. The approach effectively utilizes knowledge from non-medical and mammography datasets to improve DBT image classification accuracy, even with limited data.

Keywords:

Deep learning Digital breast tomosynthesis Feature fusion GLCM Transfer learning

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

Related Experiment Videos

Last Updated: Nov 6, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

Area of Science:

Medical Imaging
Artificial Intelligence
Machine Learning

Background:

Computer-aided detection (CADe) and diagnosis (CADx) systems are crucial for medical image classification.
Mammography-based CAD systems face limitations, especially with dense breasts, due to data availability and detection accuracy issues.
Digital breast tomosynthesis (DBT) offers improved imaging but suffers from scarce publicly available datasets.

Purpose of the Study:

To develop a two-level transfer learning framework for classifying digital breast tomosynthesis (DBT) datasets.
To leverage knowledge from readily available non-medical and mammography datasets to enhance DBT image classification.
To improve the accuracy and efficiency of CAD systems for breast cancer detection using DBT.

Main Methods:

Proposed a multilevel transfer learning (MLTL) framework to transfer knowledge from general non-medical and mammography datasets to the target DBT dataset.
Introduced a feature extraction based transfer learning (FETL) framework to further enhance the MLTL framework's performance.
Evaluated three different feature extraction techniques within the FETL framework to optimize classification.

Main Results:

Achieved an area under the receiver operating characteristic (ROC) curve of 0.89.
Demonstrated high classification performance using a small percentage of source (2.08% non-medical), intermediate (5.09% mammography), and target (3.94% DBT) datasets.
The proposed FETL framework significantly improved upon the basic MLTL framework's classification performance.

Conclusions:

The developed two-level transfer learning framework effectively classifies DBT datasets, addressing data scarcity issues.
Transfer learning offers a viable solution for improving CAD systems in medical imaging, particularly for newer modalities like DBT.
The study highlights the potential of combining MLTL and FETL for robust medical image analysis and diagnosis.