Search research articles

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 4, 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

A hybrid cost-sensitive ensemble for imbalanced breast thermogram classification.

Bartosz Krawczyk¹, Gerald Schaefer², Michał Woźniak¹

¹Department of Systems and Computer Networks, Wrocław University of Technology, Wyb. Wyspianskiego 27, 50-370 Wrocław, Poland.

Artificial Intelligence in Medicine

|August 31, 2015

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

Cellular and Molecular Effects of Targeting the CBP/β-Catenin Interaction with PRI-724 in Melanoma Cells, Drug-Naïve and Resistant to Inhibitors of BRAF<sup>V600</sup> and MEK1/2.

Cells·2025

Same author

Morphological alterations of peridroplet mitochondria in human liver biopsy.

Scientific reports·2025

Same author

Clinical examination performance in rural longitudinal medical programmes.

Education for primary care : an official publication of the Association of Course Organisers, National Association of GP Tutors, World Organisation of Family Doctors·2025

Same author

Two-photon microscopy using picosecond pulses from four-wave mixing in a Yb-doped photonic crystal fiber.

Biomedical optics express·2025

Same author

Pathological significance of intranuclear structures in liver biopsy samples.

Hepatology research : the official journal of the Japan Society of Hepatology·2025

Same author

Artificial Intelligence vs. Human Cognition: A Comparative Analysis of ChatGPT and Candidates Sitting the European Board of Ophthalmology Diploma Examination.

Vision (Basel, Switzerland)·2025

This study introduces a novel cost-sensitive classifier ensemble for analyzing breast thermograms, improving early breast cancer detection. The method effectively handles imbalanced datasets, enhancing diagnostic accuracy for malignant cases.

Area of Science:

Medical imaging
Machine learning
Oncology

Background:

Early breast cancer detection is critical for survival.
Medical thermography offers potential for detecting smaller tumors than mammography.
Standard classification methods struggle with imbalanced datasets common in medical diagnosis.

Purpose of the Study:

To develop an advanced classification system for breast thermograms.
To address the challenge of imbalanced datasets in breast cancer diagnosis.
To improve the accuracy of early breast cancer detection using medical thermography.

Main Methods:

Feature extraction from breast thermograms focusing on bilateral symmetries.
Development of a hybrid cost-sensitive classifier ensemble using decision trees.

Keywords:

Breast cancer detection Classifier ensemble Cost-sensitive classification Ensemble pruning Evolutionary algorithm Imbalanced classification Thermogram

Related Experiment Videos

Last Updated: Apr 4, 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

Optimization using a genetic algorithm for feature selection and classifier fusion, balancing misclassification cost and diversity.

Main Results:

Achieved 83.10% sensitivity and 89.44% specificity on a dataset of approximately 150 thermograms.
Demonstrated statistically superior performance compared to state-of-the-art algorithms for imbalanced classification.
Provided an effective approach for analyzing breast thermograms, improving malignant case recognition.

Conclusions:

The proposed hybrid cost-sensitive ensemble facilitates highly accurate early breast cancer diagnosis from thermogram features.
The method effectively overcomes challenges posed by imbalanced patient group distributions.
This approach enhances the reliability of thermography in breast cancer screening.