AI-BASED FNAC ANALYSIS FOR BREAST CANCER DIAGNOSIS

Breast cancer remains one of the leading causes of mortality among women worldwide, and early detection is critical for improving survival rates.Fine Needle Aspiration Cytology (FNAC) is commonly employed as a minimally invasive and cost-effective method for preliminary breast cancer diagnosis.However, manual examination of FNAC slides is time-consuming, subjective, and prone to inter-observer variability, which can result in diagnostic delays or errors.This study proposes an Artificial Intelligence (AI)-based automated diagnostic system using deep learning and computer vision to classify FNAC cytology images as benign or malignant.The system employs a Convolutional Neural Network (CNN) trained on publicly available and clinical FNAC image datasets, incorporating preprocessing and data augmentation to enhance model robustness.Experimental results demonstrate high classification accuracy, sensitivity, and generalization capability in identifying malignant cells.The model is deployed through a web-based interface that enables real-time image upload, prediction, and report generation, providing pathologists with efficient decisionsupport tools.This approach aims to improve early cancer detection, reduce manual workload, and enhance clinical decision-making, ultimately contributing to better patient care outcomes.