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 author

On the Use of a Depth Camera for the Assessment of Upper Extremity Movements in Healthy Individuals.

Sensors (Basel, Switzerland)·2026

Same author

Photoacoustic signal to image based convolutional neural network for defect detection.

The Review of scientific instruments·2025

Same author

Enhanced dataset synthesis using conditional generative adversarial networks.

Biomedical engineering letters·2023

Same author

Null Subcarrier Index Modulation in OFDM Systems for 6G and Beyond.

Sensors (Basel, Switzerland)·2021

Same author

Emotion recognition using time-frequency ridges of EEG signals based on multivariate synchrosqueezing transform.

Biomedizinische Technik. Biomedical engineering·2021

Same author

Epileptic seizure classifications using empirical mode decomposition and its derivative.

Biomedical engineering online·2020

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: Apr 10, 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

Breast Cancer Detection with Reduced Feature Set.

Ahmet Mert¹, Niyazi Kılıç², Erdem Bilgili¹

¹Department of Electrical and Electronics, Piri Reis University, 34940 Istanbul, Turkey.

Computational and Mathematical Methods in Medicine

|June 17, 2015

Summary

This summary is machine-generated.

Independent Component Analysis (ICA) reduces breast cancer data features, improving diagnostic accuracy for classifiers like SVM and ANN. This method enhances decision support systems by simplifying complex datasets.

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 Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Published on: March 24, 2015

Related Experiment Videos

Last Updated: Apr 10, 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

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 Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Published on: March 24, 2015

Area of Science:

Computational Biology
Medical Informatics
Machine Learning

Background:

Breast cancer diagnosis relies on complex datasets with numerous features.
Feature reduction is crucial for improving the efficiency and accuracy of diagnostic systems.
Independent Component Analysis (ICA) is a technique for separating mixed signals into independent components.

Purpose of the Study:

To explore the feature reduction capabilities of ICA for breast cancer classification.
To evaluate the impact of reducing the Wisconsin Diagnostic Breast Cancer (WDBC) dataset to a single independent component (IC) on diagnostic accuracy.
To compare the performance of various machine learning classifiers using the reduced feature set against the original dataset.

Main Methods:

Applied ICA to the WDBC dataset, reducing 30 features to a single IC.
Evaluated diagnostic accuracy using classifiers: k-nearest neighbor (k-NN), artificial neural network (ANN), radial basis function neural network (RBFNN), and support vector machine (SVM).
Assessed performance using metrics: specificity, sensitivity, accuracy, F-score, Youden's index, discriminant power, ROC curve, AUC, and 95% CI, with 5/10-fold cross-validation and 20%-40% data partitioning.

Main Results:

Classification using the single IC demonstrated competitive diagnostic accuracy compared to the original 30 features across multiple classifiers.
The ICA-based feature reduction led to improved performance metrics in several evaluated classifiers.
Reduced computational complexity was observed with the one-dimensional feature vector.

Conclusions:

ICA is an effective method for feature reduction in breast cancer decision support systems.
A single independent component can capture sufficient information for accurate tumor classification (benign vs. malignant).
This approach offers a promising strategy for enhancing diagnostic efficiency and reducing computational load in medical decision support.