Lung Cancer Detection using Probabilistic Neural Network with modified Crow-Search Algorithm.

Area of Science:

• Medical Imaging
• Artificial Intelligence in Oncology
• Computational Pathology

Background:

• Lung cancer is a leading cause of cancer mortality worldwide.
• Early detection is crucial for improving patient outcomes.
• Current diagnostic methods often identify cancer at advanced stages.

Purpose of the Study:

• To develop an automated classification methodology for early-stage lung cancer detection.
• To enhance the accuracy of lung cancer diagnosis using medical imaging.
• To investigate the efficacy of a novel feature selection algorithm in improving classification performance.

Main Methods:

• Utilized computed tomography (CT) lung images for analysis.
• Employed a Probabilistic Neural Network (PNN) for classification.
• Implemented Gray-Level Co-Occurrence Matrix (GLCM) for feature extraction.
• Proposed a Chaotic Crow Search Algorithm (CCSA) for optimized feature selection.

Main Results:

• The proposed method achieved a classification accuracy of 90%.
• CCSA-based feature selection demonstrated superior performance compared to methods without CCSA.
• Key performance metrics included specificity, sensitivity, and predictive values.

Conclusions:

• Automated classification using PNN with CCSA-based feature selection improves lung cancer detection efficiency.
• The study highlights the potential of advanced computational techniques for early cancer diagnosis.
• Optimized feature selection is critical for enhancing the performance of diagnostic AI models.