PSOWNNs-CNN: A Computational Radiology for Breast Cancer Diagnosis Improvement Based on Image Processing Using...

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Machine Learning

Background:

• Early breast cancer diagnosis is critical for effective treatment.
• Image-based diagnostic techniques are valuable but can face challenges in identifying subtle abnormalities.
• Radiologists benefit from computer-aided detection using image processing and AI.

Purpose of the Study:

• To review various artificial intelligence and image processing approaches for breast cancer detection.
• To present an innovative machine learning method for enhanced breast cancer identification.

Main Methods:

• The study reviews existing AI and image processing techniques for breast cancer detection.
• An innovative approach using a particle swarm optimized wavelet neural network (PSOWNN) is proposed.
• Performance is compared against other machine learning algorithms like Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Convolutional Neural Network (CNN).

Main Results:

• The proposed PSOWNN method demonstrated superior performance compared to CNN and other algorithms.
• The PSOWNN method achieved 98.6% accuracy in correctly identifying disorders across 905 images.
• Specific performance metrics include 98.8% specificity and 98.6% precision, with 95.2% of images correctly classified.

Conclusions:

• Machine learning methods offer significant benefits for breast cancer detection, improving performance, efficiency, and image quality.
• The PSOWNN method shows high accuracy and is a promising tool for advanced medical imaging applications.
• PSOWNNs outperform traditional machine learning algorithms in breast cancer image classification.