Related Experiment Video
Updated: Jun 16, 2026
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
Associative Classification of Mammograms using Weighted Rules
Sumeet Dua1, Harpreet Singh, H W Thompson
1Department of Computer Science, Department of Computer Science, Louisiana Tech University, P.O. Box 10348, Ruston, LA 71270 and with the School of Medicine, LSU Health Sciences Center, 2020 Gravier Street, New Orleans, LA 70112. (; fax: 318-257-4922; e-mail: sdua@coes.latech.edu ).
This study introduces a new weighted association rule classifier for mammogram classification. The novel method achieves high accuracy, outperforming other rule-based techniques in breast cancer detection.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Machine Learning
Background:
- Mammography is crucial for early breast cancer detection.
- Accurate classification of mammograms remains a challenge in medical diagnostics.
Purpose of the Study:
- To develop and evaluate a novel weighted association rule-based classifier for mammogram classification.
- To improve the accuracy and efficacy of automated mammogram analysis.
Main Methods:
- Preprocessing mammograms to identify regions of interest.
- Extracting and discretizing texture components from segmented image regions.
- Deriving weighted association rules based on texture component dependencies for classification.
Main Results:
- The proposed method achieved classification accuracies as high as 89% on a standard mammography dataset.
- Experimental results demonstrated the efficacy of the weighted association rules under various classification scenarios.
- The novel approach surpassed the performance of existing rule-based classification techniques.
Conclusions:
- The developed weighted association rule-based classifier is effective for mammogram classification.
- This method offers a promising advancement in automated analysis of medical images for cancer detection.
- The approach provides a robust and accurate alternative to current mammogram classification techniques.
