A Novel Enhanced Gray Scale Adaptive Method for Prediction of Breast Cancer

Area of Science:

• Medical Imaging
• Artificial Intelligence in Medicine
• Oncology

Background:

• Breast cancer poses a significant global health challenge, necessitating accurate diagnostic tools.
• Mammography is crucial for breast cancer diagnosis, but diagnostic accuracy requires improvement.
• Existing intelligent techniques detect abnormalities but lack precision in predicting cancer severity.

Purpose of the Study:

• To enhance the accuracy and predictive capabilities of mammogram analysis for breast cancer.
• To introduce a novel algorithm for improved breast cancer detection and classification.

Main Methods:

• Development of the Enhanced Gray Scale Adaptive Method (EGAM).
• EGAM integrates K-Generalized-Likelihood Ratio Test (K-GLCM) and Extreme Fuzzy Learning Machines (EFLM).
• The algorithm analyzes mammograms for Microcalcification, Clusters, Masses, Spiculate lesions, Asymmetry, and Architectural distortions.

Main Results:

• The proposed EGAM algorithm achieved 99% accuracy in classification, detection, and prediction.
• EGAM demonstrated reduced computation time compared to existing intelligent algorithms.
• Significant improvements in diagnostic accuracy for breast cancer detection were observed.

Conclusions:

• EGAM offers a highly accurate and efficient method for breast cancer diagnosis from mammograms.
• The algorithm shows potential for precise prediction of cancer levels, addressing a critical research gap.
• EGAM represents a significant advancement in applying AI for improved breast cancer management.