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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Amorphization-Facilitated Synthesis of Pt<sub>2</sub>Bi<sub>2</sub>/Pt Heterojunction Nanorods for Highly Efficient Methanol Electrooxidation.

Nano letters·2026
Same author

Experimental Research on Neutron Dose Assessment Based on the Induced 24 Na Activity in a Newly Developed Voxel Physical Phantom.

Health physics·2026
Same author

Intraocular infection of <i>Moraxella nonliquefaciens</i> accompanied by secondary angle-closure glaucoma: A case report.

The Journal of international medical research·2026
Same author

Deep learning for multitask prediction on thyroid nodule frozen sections.

Frontiers in oncology·2026
Same author

Natural variation in Phosphatidylinositol 4-Kinase OsPI4Kγ7 and its interaction with OsLIC balance rice yield and latitudinal adaptation.

Nature communications·2026
Same author

Polarization-diversity backscatter communication based on programmable information metasurface.

iScience·2026

Related Experiment Video

Updated: Oct 1, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

334

Artificial Intelligence-Based Breast Cancer Diagnosis Using Ultrasound Images and Grid-Based Deep Feature Generator.

Haixia Liu1, Guozhong Cui2, Yi Luo3

  • 1Department of Ultrasound, Cangzhou Central Hospital, Cangzhou, Hebei Province, 061000, People's Republic of China.

International Journal of General Medicine
|March 8, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a novel grid-based deep feature generation technique for enhanced breast cancer detection using ultrasonography. The method achieved 97.18% accuracy in classifying malignant, benign, and normal breast ultrasonic images.

Keywords:
breast ultrasonography (BUS)deep classification frameworkdeep neural networkgrid-based deep feature generatoriterative feature selection

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

718

Related Experiment Videos

Last Updated: Oct 1, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

334
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

718

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Oncology

Background:

  • Breast cancer poses a significant mortality risk, underscoring the need for early detection.
  • Ultrasonography is a key imaging modality for distinguishing between benign and malignant breast tumors.
  • Deep learning methods show promise for improving breast cancer classification in biomedical images.

Purpose of the Study:

  • To present a new deep feature generation technique for breast cancer detection using breast ultrasonography (BUS) images.
  • To enhance the classification performance of artificial intelligence models in identifying breast cancer subtypes.

Main Methods:

  • A grid-based deep feature generator utilizing 16 pre-trained Convolutional Neural Network (CNN) models was developed.
  • Features were generated by applying CNN models to segmented image rows and columns, selecting the top three feature vectors.
  • Iterative Neighborhood Component Analysis (INCA) was employed for optimal feature selection, identifying 980 features.
  • A deep neural network (DNN) was used for the final classification of selected features.

Main Results:

  • The developed model achieved a 97.18% classification accuracy.
  • The model successfully differentiated between three classes: malignant, benign, and normal breast ultrasonic images.

Conclusions:

  • The proposed grid deep feature generator combined with INCA-based feature selection effectively classifies breast ultrasonic images.
  • This approach demonstrates significant potential for improving the accuracy and reliability of AI-driven breast cancer diagnosis.