Related Experiment Video
Updated: Jul 2, 2026
08:32
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
Published on: October 2, 2020
An information-theoretical model for breast cancer detection
D Blokh1, N Zurgil, I Stambler
1The Biophysical Interdisciplinary Jerome Schottenstein Center for the Research and the Technology of the Cellome, Physics Department, Bar Ilan University, Ramat Gan 52900, Israel.
Methods of Information in Medicine
|August 12, 2008
Summary
This study introduces a novel formal diagnostic model for breast cancer detection using information theory. The model accurately diagnosed 23 of 24 healthy individuals and all 34 patients, demonstrating its effectiveness.
Area of Science:
- Biomedical research
- Medical diagnostics
- Computational biology
Background:
- Formal diagnostic modeling is crucial in biological and medical research.
- Current models lack a unified mathematical approach for parameter correlation and decision rule construction.
- This deficiency hinders theoretical/biomedical substantiation and reduces diagnostic efficacy.
Purpose of the Study:
- To construct a formal diagnostic model for breast cancer detection.
- To address the limitations of existing diagnostic models by proposing a unified approach.
- To enhance the accuracy and applicability of diagnostic models in clinical settings.
Main Methods:
- Developed a formal diagnostic model for breast cancer detection based on information theory.
- Utilized normalized mutual information to assess parameter relevance.
- Employed the nearest neighbor rule with weighted Hamming distance for diagnosis, incorporating cellular fluorescence polarization and cell receptor expression.
Main Results:
- The model was tested on 24 healthy individuals and 34 breast cancer patients.
- Achieved a high diagnostic accuracy, correctly identifying 23 of 24 healthy subjects and all 34 patients.
- Demonstrated the practical effectiveness of the proposed information-theory-based diagnostic approach.
Conclusions:
- The developed diagnostic model is open, allowing for the integration of additional parameters.
- This adaptability suggests potential for increased diagnostic effectiveness with further development.
- The study provides a robust framework for advanced breast cancer diagnostics.
