Cancer staging classification Using VGG16 Architecture Algorithms (TNM staging system)

Abstract

Understanding the cancer stage aids doctors in developing a prognosis and creating a treatment plan for individual patients. Cancer staging is the process of identifying the amount and location of cancer in the body. It describes the severity of a person's cancer based on the size of the original (primary) tumor as well as the extent to which the cancer has spread in the body. Staging gives medical professionals a standard vocabulary to use when discussing a patient's cancer and working together to choose the best course of action. In recent years, deep learning has emerged as a powerful tool for has been applied to the analysis of pathological images for the detection and classification of diseases. Because deep learning can evaluate enormous volumes of data rapidly and effectively, it is important for the categorization of cancer. This can enhance overall results and assist physicians in making better-informed decisions about patient care. Furthermore, small patterns and traits that might not be visible to the human eye can be trained into deep learning models, enabling earlier identification and more successful therapy. A VGG16 model was developed for cancer classification, and the pre-trained Visual Geometry Group 16 (VGG16) architecture has been applied on convolutional neural network (CNN)-based automatic cancer classification. Some research has studied the use of modified VGG configurations, such as VGG16, to classify cancerous tumors in human tissue images. Studies have shown high efficiency of applying VGG16 in cancer classification, as it was found to be particularly effective in achieving high accuracy rates. The VGG16 model with training was particularly effective in achieving high accuracy rates for cancer classification.