Boosting Breast Cancer Detection Using Convolutional Neural Network.

Area of Science:

• Oncology
• Medical Imaging
• Artificial Intelligence

Background:

• Breast cancer is a prevalent and life-threatening disease affecting women globally.
• Accurate and early detection is crucial for effective treatment and improved patient outcomes.
• Current diagnostic methods can be subject to human error and variability.

Purpose of the Study:

• To develop and evaluate a convolutional neural network (CNN) system for automated breast cancer identification.
• To analyze hostile ductal carcinoma tissue zones within whole-slide images (WSIs).
• To compare the performance of CNN architectures against traditional machine learning (ML) algorithms.

Main Methods:

• Utilized various convolutional neural network (CNN) architectures for image analysis.
• Trained and validated the models on a large dataset of approximately 275,000 RGB image patches (50x50 pixels).
• Compared CNN performance against established machine learning (ML) algorithms using quantitative performance measures.

Main Results:

• The proposed CNN system achieved an accuracy of 87% in breast cancer identification.
• The CNN system demonstrated a 9% improvement in accuracy compared to ML algorithms (87% vs. 78%).
• The system successfully identified cancerous tissue zones in whole-slide images.

Conclusions:

• The developed CNN system significantly enhances the accuracy of automated breast cancer detection.
• This AI-driven approach has the potential to reduce diagnostic errors and improve patient care.
• The findings support the integration of advanced AI techniques in histopathological analysis.