An improved RIME optimization algorithm for lung cancer image segmentation

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computational Biology

Background:

• Lung cancer diagnosis relies heavily on accurate pathological image analysis.
• Image segmentation is a critical step in medical image processing for diagnosis.
• Existing segmentation methods may face challenges with convergence speed and local optima.

Purpose of the Study:

• To develop an advanced swarm intelligence algorithm for multilevel lung cancer image segmentation.
• To improve the convergence speed and accuracy of pathological image segmentation.
• To provide a robust framework for lung cancer image analysis.

Main Methods:

• An improved whale optimization algorithm, WDRIME, incorporating a prey mechanism and random mutation.
• A multilevel image segmentation approach for lung cancer pathological images.
• Performance evaluation against state-of-the-art algorithms using IEEE CEC2014 benchmarks and metrics like PSNR, SSIM, FSIM.

Main Results:

• WDRIME demonstrated superior convergence speed and accuracy compared to existing algorithms.
• The combined WDRIME and multilevel segmentation framework achieved high-quality segmentation results.
• Quantitative evaluation confirmed the effectiveness of the proposed method.

Conclusions:

• The WDRIME algorithm offers a significant advancement in lung cancer image segmentation.
• The proposed method provides a reliable tool for detailed analysis of lung cancer pathology.
• This research supports improved diagnostic accuracy and treatment planning for lung cancer.