Cervical cancer: empowering diagnosis with VGGNet transfer learning

Abstract

This study addresses the critical issue of cervical cancer, which stands as the fourth most prevalent cancer among women. With early detection being pivotal for successful treatment, the research focuses on evaluating the effectiveness of deep learning-based models in cervical cancer detection. Leveraging the widely employed Papanicolaou (Pap) smear test, the study proposes a transfer learning approach, incorporating contrast limited adaptive histogram equalization for image enhancement. Convolutional neural network models, including AlexNet, visual geometry group (VGGNet)-16, and VGGNet-19, are employed to accurately distinguish between cancerous and non-cancerous cervical cell images. The evaluation metrics encompass accuracy, precision, sensitivity, specificity, F1-score, and the matthew correlation coefficient (MCC). Notably, the findings reveal the exceptional performance of the VGGNet-19 model, achieving an accuracy of 98.71%, sensitivity of 98.33%, and specificity of 99% for a single smear cell. This research marks a significant advancement in the application of deep learning for precise cervical cancer detection. The promising results underscore the potential of these models to enhance early diagnosis and contribute to improved treatment outcomes, thereby addressing a crucial aspect of women's health.