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

Neural network-based method for measuring the impacts of epileptic brain activities on cardiac cycles.

Frontiers in neurology·2025
Same author

Visuoaffective day residue in hypnagogia involves sequential bihemispheric interactions between cortical, subcortical, and cerebellar structures.

Communications biology·2025
Same author

Discrimination of secondary hypsarrhythmias to Zika virus congenital syndrome and west syndrome based on joint moments and entropy measurements.

Scientific reports·2022
Same author

Interdigitated Electrode for Electrical Characterization of Commercial Pseudo-Binary Biodiesel-Diesel Blends.

Sensors (Basel, Switzerland)·2021
Same author

Autofocus Entropy Repositioning Method Bioinspired in the Magnetic Field Memory of the Bees Applied to Pollination.

Sensors (Basel, Switzerland)·2021
Same author

Analysis of Sensitivity and Specificity of Cutoff Points for Resting Heart Rate in 6,794 Brazilian Adolescents: A Cross-Sectional Study.

Arquivos brasileiros de cardiologia·2021

Related Experiment Video

Updated: Feb 25, 2026

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

23.3K

Detecting masses in dense breast using independent component analysis.

Luis Claudio de Oliveira Silva1, Allan Kardec Barros1, Marcus Vinicius Lopes1

  • 1Biological Information Processing Lab, Federal University of Maranhao, Av. dos Portugueses, 1966 Sao Luis MA, Brazil.

Artificial Intelligence in Medicine
|July 31, 2017
PubMed
Summary

Independent Component Analysis (ICA) improves breast cancer detection in dense breasts, outperforming Principal Component Analysis (PCA). This method enhances lesion identification, aiding specialists in diagnosing dense breast tissue more effectively.

Keywords:
ClusteringFilteringImage segmentationMammographic imagesMedical image analysis

More Related Videos

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

43.7K
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

7.0K

Related Experiment Videos

Last Updated: Feb 25, 2026

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

23.3K
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

43.7K
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

7.0K

Area of Science:

  • Medical Imaging
  • Biomedical Engineering
  • Radiology

Background:

  • Breast cancer is a leading cancer affecting women globally.
  • Dense breast tissue can obscure early-stage mass detection.
  • Computer-aided diagnosis (CAD) shows promise but has limited studies on dense breasts.

Purpose of the Study:

  • To propose Independent Component Analysis (ICA) for detecting lesions in dense breasts.
  • To compare ICA's performance against Principal Component Analysis (PCA) for lesion segmentation.
  • To evaluate the accuracy of these methods in dense versus nondense breast tissue.

Main Methods:

  • Independent Component Analysis (ICA) and Principal Component Analysis (PCA) for lesion segmentation.
  • Area overlay measure to quantify segmentation quality.
  • Statistical tests for two proportions to compare detection rates in dense and nondense breasts.
  • Experiments conducted on Mini-MIAS and DDSM databases.

Main Results:

  • ICA demonstrated superior performance in detecting lesions in dense breasts compared to PCA.
  • Achieved 92.71% accuracy in nondense breasts and 79.17% accuracy in dense breasts.
  • A significant difference in mass detection rates between dense and nondense breasts was confirmed.

Conclusions:

  • ICA is an effective method for enhancing lesion detection in dense breast tissue.
  • The study highlights a significant disparity in detection rates between dense and nondense breasts.
  • Findings can assist specialists in improving the diagnosis of breast cancer in dense breasts.