Cervical Cancer Diagnosis using Convolutional Neural Networks

Abstract

Cervical cancer is a major health concern, and early detection plays a crucial role in improving patient outcomes. This paper presents a deep learning-based system for the automated detection of cervical cancer using Pap smear images. Multiple state-of-the-art convolutional neural network architectures, including NASNet, VGG19, Xception, ResNet50, InceptionV3, and MobileNet, are evaluated for their classification performance. The models are trained on a dataset containing various cervical cell images, categorized as either cancerous or non-cancerous. Performance evaluation is conducted using key metrics such as accuracy, precision, recall, and F1-score. The results indicate significant variations in classification accuracy, with the Xception model outperforming other architectures. The study highlights the effectiveness of deep learning in medical image analysis and its potential for early cervical cancer detection, contributing to AI-driven advancements in healthcare diagnostics.