VGGNet Integration for Kidney Tumor Classification
Anuruk Prommakhot, Jakkree Srinonchat · 2024
Deep convolutional neural networks (DCNNs) have recently become more critical diagnostic tools. DCNNs have been shown in previous studies to have performance levels comparable to those of competent medical professionals, mainly when used in the study of kidney cancers. It was especially true when DCNNs were used to investigate kidney tumors. We relied on very complex convolutional networks, also known as very deep convolutional networks (VGGNet), to ensure our study's accuracy and improve the precision of our large-scale image recognition. These networks are also known as very general-purpose gradient-boosting networks. This was done to ensure that the results of our investigation were reliable. After that, these networks were used to examine the Kidney Tumor dataset, which included various symptoms associated with the illness. Our research findings were encouraging because the model demonstrated astonishingly high accuracy rates of one hundred percent for categorizing normal, cyst, stone, and tumor, respectively. It offered a great deal of solace at difficult times. In the realm of medical diagnostics, a significant new development has just recently been finished being implemented.