Breakthrough in Breast Cancer Screening: AI-Powered Infrared Thermography

Strategic Insights -

Researchers at Majmaah University have made a significant breakthrough in breast cancer screening using artificial intelligence-powered infrared thermography. The new system, which utilizes convolutional neural networks (CNNs) and enhanced particle swarm optimization algorithm, has achieved a superior classification accuracy of 98.8%. This marks a significant improvement over conventional CNN implementations in terms of both computational speed and predictive accuracy.

Key Takeaways:

  • The study found that breast cancer remains the most prevalent cause of cancer-related mortality among women worldwide, with an estimated incidence exceeding 500,000 new cases annually.
  • Conventional diagnostic tools such as mammography are often invasive, costly, and exhibit reduced efficacy in patients with dense breast tissue.
  • The proposed system is a non-invasive and economical alternative to mammography, with the ability to accurately distinguish between malignant and benign thermographic breast images.
  • The enhanced particle swarm optimization algorithm is used to automatically fine-tune CNN hyperparameters, minimizing manual effort and enhancing computational efficiency.
  • The methodology incorporates advanced image preprocessing techniques, including Mamdani fuzzy logic-based edge detection, Contrast-Limited Adaptive Histogram Equalization (CLAHE), and median filtering.
  • The proposed model outperforms conventional CNN implementations in both computational speed and predictive accuracy.
  • The research suggests that the developed system has substantial potential for early, reliable, and cost-effective breast cancer screening in real-world clinical environments.
  • The study's lead author is Riyadh M. Alzahrani, from the Dept. of Medical Equipment Technology, College of Applied Medical Science, Majmaah University.

Statistics:

  • Estimated incidence of breast cancer worldwide: 500,000 new cases annually.
  • Classification accuracy of the proposed system: 98.8%.
  • Computational speed of the proposed system: significantly faster than conventional CNN implementations.
  • Predictive accuracy of the proposed system: significantly higher than conventional CNN implementations.
  • Number of research authors: 8.

Sources:

  • Early breast cancer detection via infrared thermography using a CNN enhanced with particle swarm optimization. Scientific Reports, 2025;15(1):25290.
  • NewsRx. Majmaah University Reports Findings in Breast Cancer Screening (Early breast cancer detection via infrared thermography using a CNN enhanced with particle swarm optimization). Journal of Engineering. July 28, 2025; p 1473.