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

[Effects of electroacupuncture at "Neiguan" (PC 6) on p38 MAPK signaling pathway in rats with cardiac hypertrophy].

Zhongguo zhen jiu = Chinese acupuncture & moxibustion·2012
Same author

Accurate measurement of oxygen consumption in children undergoing cardiac catheterization.

Catheterization and cardiovascular interventions : official journal of the Society for Cardiac Angiography & Interventions·2012
Same author

Glutathione S-transferase polymorphisms and bone tumor risk in China.

Asian Pacific journal of cancer prevention : APJCP·2012
Same author

Systemic oxygen transport derived by using continuous measured oxygen consumption after the Norwood procedure-an interim review.

Interactive cardiovascular and thoracic surgery·2012
Same author

Discovery and optimization of 2,4-diaminoquinazoline derivatives as a new class of potent dengue virus inhibitors.

Journal of medicinal chemistry·2012
Same author

β(3)-Adrenoceptor Antagonist SR59230A Attenuates the Imbalance of Systemic and Myocardial Oxygen Transport Induced by Dopamine in Newborn Lambs.

Clinical Medicine Insights. Cardiology·2012

Related Experiment Video

Updated: Aug 9, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

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

Published on: August 30, 2013

43.0K

Self-attention random forest for breast cancer image classification.

Jia Li1, Jingwen Shi1, Jianrong Chen1

  • 1Department of Intelligent Manufacturing, Wuyi University, Jiangmen, China.

Frontiers in Oncology
|February 23, 2023
PubMed
Summary

Accurate breast cancer image classification is crucial for early diagnosis and improved survival rates. A novel Self-Attention Random Forest (SARF) model enhances classification accuracy using multi-scale fusion features and optimized hyperparameters.

Keywords:
classificationGridSearchCVbreast cancer imagesrandom forestself-attention

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.3K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

168

Related Experiment Videos

Last Updated: Aug 9, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

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

Published on: August 30, 2013

43.0K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.3K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

168

Area of Science:

  • Medical Imaging
  • Machine Learning
  • Computer-Aided Diagnosis

Background:

  • Early breast cancer detection significantly improves patient survival rates.
  • Accurate classification of histopathological images is vital for auxiliary diagnosis.

Purpose of the Study:

  • To develop and validate a Self-Attention Random Forest (SARF) model for enhanced breast cancer image classification.
  • To improve classification accuracy by utilizing multi-scale fusion features and optimized hyperparameters.

Main Methods:

  • Extracting multi-scale fusion features using pyramid gray level co-occurrence matrix.
  • Implementing a Self-Attention Random Forest (SARF) model for adaptive feature refinement.
  • Optimizing model hyperparameters using the GridSearchCV technique.

Main Results:

  • Achieved 92.96% average accuracy for eight-class and 97.16% for binary classification on the BreaKHis dataset.
  • Attained 98.79% average accuracy on the MIAS dataset, outperforming state-of-the-art methods.
  • Demonstrated superior performance and universality of the proposed SARF model.

Conclusions:

  • The proposed SARF model effectively classifies breast cancer images, offering a robust tool for auxiliary diagnosis.
  • The study provides a theoretical basis for future model optimization through feature influence analysis.