A Robust Automated Cervical Cancer Detection System Using Elephant Herding Optimized MCNN
S. Maheswari, C. N. Marimuthu, Xavier N. Fernando · 2025
Cervical cancer is a leading cause of cancer-related deaths among women, and early detection is crucial for improving survival rates. This research proposes an automated system for classifying cervical cancer using medical images. The system starts with image preprocessing, where images are resized and noise is removed using a Median Filter. Segmentation is performed using K-Means Clustering to isolate cancerous regions. The Local Binary Pattern (LBP) technique is applied for feature extraction, capturing texture patterns to distinguish normal from abnormal tissues. Classification is achieved using a Modified Convolutional Neural Network (MCNN), with optimization through the Elephant Herding Optimization (EHO) algorithm to fine-tune the model's parameters. This approach aims to assist healthcare professionals in diagnosing cervical cancer more efficiently and accurately, improving patient outcomes. The system can provide rapid, reliable results, enabling timely treatment and potentially reducing the global burden of cervical cancer.