An immune-inspired semi-supervised algorithm for breast cancer diagnosis

Area of Science:

• Artificial Intelligence
• Computational Biology
• Oncology

Background:

• Breast cancer is a leading cause of cancer death among women worldwide.
• Early and accurate diagnosis is crucial for effective breast cancer treatment.
• Existing diagnostic methods often rely on supervised learning, requiring costly labeled data.

Purpose of the Study:

• To develop a semi-supervised learning algorithm for breast cancer diagnosis.
• To reduce the dependency on expensive labeled data in medical diagnostics.
• To integrate advanced life science research with artificial intelligence for improved cancer detection.

Main Methods:

• Proposed a novel semi-supervised learning algorithm.
• Utilized two benchmark breast cancer datasets from the UCI machine learning repository.
• Integrated state-of-the-art life science research with artificial intelligence techniques.

Main Results:

• The proposed algorithm demonstrated effectiveness and efficiency in extensive experiments.
• Experimental results validated the algorithm's performance on benchmark datasets.
• The semi-supervised approach successfully reduced the need for labeled data.

Conclusions:

• The developed semi-supervised learning algorithm is a promising tool for automatic breast cancer diagnosis.
• This approach offers a cost-effective solution for acquiring diagnostic data.
• The integration of AI and life science advances cancer detection capabilities.