Breast cancer recognition using a novel hybrid intelligent method

Area of Science:

• Oncology
• Artificial Intelligence
• Machine Learning

Background:

• Breast cancer is a leading cause of cancer death in women, emphasizing the need for early diagnosis and effective detection methods.
• Early diagnosis significantly improves breast cancer curability, highlighting the importance of accurate tumor recognition systems.

Purpose of the Study:

• To develop and evaluate a novel hybrid intelligent method for accurate breast cancer tumor recognition.
• To enhance the performance of breast cancer detection systems through advanced feature extraction and optimized classification techniques.

Main Methods:

• A hybrid intelligent system comprising feature extraction, classification, and optimization modules was developed.
• Fuzzy features were employed for efficient pattern characteristic extraction.
• A support vector machine (SVM) classifier was utilized for its generalization capabilities.
• The bees algorithm (BA) was implemented to optimize SVM hyperparameters for improved recognition accuracy.

Main Results:

• The proposed hybrid system demonstrated high accuracy in breast cancer tumor recognition.
• Simulation results on the Wisconsin Breast Cancer database validated the system's effectiveness.

Conclusions:

• The novel hybrid intelligent method offers a promising approach for accurate and efficient breast cancer detection.
• Optimizing SVM classifiers with algorithms like the bees algorithm can significantly improve diagnostic performance in medical applications.