Boosting Multi-Cancer Classification: A Deep Dive into VGG and Efficient Net

Developing a trustworthy CNN-based multi-cancer classifier for the diagnosis of breast, lung, colon, brain, kidney, lymphoma, cervical, and oral cancers is the goal of the current work. The purpose of this study was to determine how well we can distinguish between cancerous and non-cancerous medical images using CNNs called VGG and Efficient Net networks. According to the comparison of experimental findings, the suggested VGG outperforms Efficient Net in a number of metrics, such as accuracy, precision, recall, and F1 score. According to the experimental data, the VGG also had a more efficient learning rate and a faster rate of convergence. According to the findings, the VGG model can be used to speed up cancer treatment techniques and is helpful for multi-cancer differentiating jobs. findings of this research suggest that the VGG network can be a valuable tool in speeding up cancer diagnosis processes, making it suitable for integration into clinical workflows. Its high performance in multi-cancer classification could potentially contribute to earlier detection and improved treatment strategies for patients, thus reducing the burden on healthcare systems..