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 Experiment Video

Updated: Mar 1, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.0K

Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification.

Saeid Asgari Taghanaki1, Jeremy Kawahara1, Brandon Miles1

  • 1Medical Image Analysis Lab, Simon Fraser University, Canada.

Computer Methods and Programs in Biomedicine
|May 30, 2017
PubMed
Summary

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

Diffusing caveolin-1 scaffolds regulate mechanosignalling.

Nature cell biology·2026
Same author

HDCluster: High-Degree Graph Clustering for Robust Analysis of Single Molecule Localization Microscopy.

bioRxiv : the preprint server for biology·2025
Same author

nERdy: network analysis of endoplasmic reticulum dynamics.

Communications biology·2025
Same author

Physician-in-the-Loop Active Learning in Radiology Artificial Intelligence Workflows: Opportunities, Challenges, and Future Directions.

AJR. American journal of roentgenology·2025
Same author

BiasPruner: Mitigating bias transfer in continual learning for fair medical image analysis.

Medical image analysis·2025
Same author

SuperResNET: Model-Free Single-Molecule Network Analysis Software Achieves Molecular Resolution of Nup96.

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)·2025

This study introduces a novel multi-objective deep auto-encoder for breast cancer diagnosis. By optimizing both reconstruction and classification error, it achieves higher accuracy than traditional methods.

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Machine Learning

Background:

  • Feature reduction is crucial for computer-aided breast cancer diagnosis.
  • Traditional auto-encoders optimize only reconstruction error, neglecting classification performance.
  • Optimizing auto-encoders is sensitive to initial weights and doesn't directly address classification error.

Purpose of the Study:

  • To investigate if extending auto-encoders to multi-objective optimization yields more discriminative features for improved breast cancer classification.
  • To compare the proposed multi-objective approach against single-objective and other multi-objective methods.

Main Methods:

  • Introduced a novel multi-objective deep auto-encoder optimizing Mean Squared Reconstruction Error (MRE) and Mean Classification Error (MCE) simultaneously.
Keywords:
Auto-encoderBreast cancerComputer aided diagnosisFeature reductionMulti-objective optimization

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

Related Experiment Videos

Last Updated: Mar 1, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.0K
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
  • Utilized a non-dominated sorting genetic algorithm to find Pareto-optimal solutions for both objectives.
  • Tested the method on 949 X-ray mammograms across 12 classes.

    • Main Results:

    • Achieved a classification accuracy of up to 98.45% using features from the proposed algorithm.
    • Demonstrated superior classification performance compared to state-of-the-art methods.
    • The identified features were more discriminative for breast cancer classification.

    Conclusions:

    • Integrating classification error as an objective in auto-encoder optimization enhances feature discriminability.
    • Evolutionary multi-objective optimization for Pareto-optimal solutions improves feature extraction for breast cancer diagnosis.
    • The proposed method offers a promising advancement in computer-aided diagnosis systems.