Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same journal

Multi-Scale convolutional neural networks integrated with self-attention for motor imagery EEG decoding.

Biomedical engineering letters·2026

Same journal

Low-power analog and mixed-signal circuit techniques for next-generation miniature implantable neural interface systems.

Biomedical engineering letters·2026

Same journal

Advances in semiconductor materials and device architectures for biomedical systems: a mini review.

Biomedical engineering letters·2026

Same journal

A Multi-perception fusion using shared-control method for brain-mobile robot.

Biomedical engineering letters·2026

Same journal

SSA-DCNet: a cross-session MI-EEG classification network based on deformable convolution and spatial-shift attention.

Biomedical engineering letters·2026

Same journal

Advanced silicon nanomembrane based bioelectronics for flexible and stretchable implantable systems.

Biomedical engineering letters·2026

See all related 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: Jun 3, 2025

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Innovative breast cancer detection using a segmentation-guided ensemble classification framework.

P Manju Bala¹, U Palani²

¹Computer Science and Engineering, IFET College of Engineering, Villupuram, Tamilnadu India.

Biomedical Engineering Letters

|January 9, 2025

Summary

This summary is machine-generated.

This study presents a new deep learning model for breast cancer (BC) detection. The model achieves 99.57% accuracy in identifying malignant, benign, and normal breast tumors from ultrasound images.

Keywords:

Attention U-Net BC Breast Ultrasound images Classification Ensemble classifiers Random forest meta-classifier Segmentation

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

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

Related Experiment Videos

Last Updated: Jun 3, 2025

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

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

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

Area of Science:

Medical Imaging
Artificial Intelligence
Oncology

Background:

Breast cancer (BC) is a major global health concern requiring improved early detection methods.
Current deep learning models often miss small masses, leading to diagnostic errors.
Accurate BC diagnosis is crucial for reducing morbidity and mortality.

Purpose of the Study:

To develop a novel segmentation-guided classification model to enhance breast cancer detection accuracy.
To improve the identification of malignant, benign, and normal breast tumor classes.
To reduce false positive and false negative outcomes in BC diagnosis.

Main Methods:

A two-phase approach was employed: Phase I used Attention U-Net for breast cancer segmentation, focusing on suspicious regions.
Phase II introduced an ensemble classification method with diverse feature extraction, base classifiers (SVM, Decision Trees, KNN, ANN), and a Random Forest meta-classifier.
The segmentation results guided the ensemble classifier for precise region-of-interest analysis.

Main Results:

The integrated model achieved an overall accuracy of 99.57% on an ultrasound image dataset.
Segmentation performance reached a 95% F1-score, indicating high precision in identifying relevant areas.
The model demonstrated strong discriminative power for malignant, benign, and normal breast tissue.

Conclusions:

The segmentation-guided ensemble model significantly improves breast cancer detection accuracy.
This approach enhances the ability to differentiate between various breast tumor types.
Early and accurate detection facilitated by this model can lead to better patient outcomes and reduced mortality.