Related Experiment Video
Updated: Jun 17, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
Breast cancer diagnosis in digital mammogram using multiscale curvelet transform
Mohamed Meselhy Eltoukhy1, Ibrahima Faye, Brahim Belhaouari Samir
1Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 31750 Tronoh, Perak, Malaysia. tokhy2478@yahoo.com
Summary
This study introduces a novel curvelet transform method for breast cancer diagnosis in digital mammograms. The approach achieved a high 98.59% accuracy, showing its potential for medical image analysis.
Area of Science:
- Medical Imaging
- Biomedical Engineering
- Computer-Aided Diagnosis
Background:
- Digital mammography is crucial for early breast cancer detection.
- Accurate classification of mammograms remains a challenge.
Purpose of the Study:
- To develop and evaluate a new method for breast cancer diagnosis using curvelet transform on digital mammograms.
Main Methods:
- Mammogram images were decomposed using curvelet transform.
- Key coefficients were extracted to form a feature vector.
- A supervised classifier was built using Euclidean distance.
Main Results:
- The proposed method achieved a classification accuracy of 98.59%.
- Curvelet transform demonstrated effectiveness in feature extraction for mammograms.
Conclusions:
- Curvelet transform is a promising tool for the analysis and classification of digital mammograms.
- This technique can enhance the accuracy of breast cancer diagnosis.
