Classification of Breast Cancer Using Transfer Learning and Advanced Al-Biruni Earth Radius Optimization

Area of Science:

• Oncology
• Medical Imaging
• Artificial Intelligence

Background:

• Breast cancer is a leading cause of death in women, necessitating improved diagnostic tools.
• Manual mammography interpretation is time-consuming and prone to errors.
• Existing AI approaches face challenges like feature extraction and model training.

Purpose of the Study:

• To develop a novel, computationally automated mechanism for breast cancer classification.
• To enhance breast cancer detection accuracy using advanced AI techniques.

Main Methods:

• A framework incorporating data augmentation, AlexNet-based transfer learning for feature extraction, and optimized Convolutional Neural Network (CNN) classification.
• Utilized the Advanced Al-Biruni Earth Radius (ABER) optimization algorithm for improved classification.
• Validated the model on two public breast cancer datasets.

Main Results:

• Achieved an average classification accuracy of 97.95%.
• Demonstrated improved accuracy compared to recent AI-based breast cancer detection methods.
• Statistical tests (ANOVA, Wilcoxon) confirmed the methodology's effectiveness and significance.

Conclusions:

• The proposed AI-driven framework significantly enhances breast cancer classification accuracy.
• The novel optimization algorithm and transfer learning approach offer a promising solution for early breast cancer detection.
• This method holds potential for improving patient outcomes through more reliable and efficient diagnosis.