MRI Scans for Deep Learning-Based Chronic Nephropathy Detection: A Comparison of CNN, MobileNet, VGG16, and ResNet-50 Models

Prolonged Nephropathy Given that detection usually shows no signs in its early phases and has a high morbidity rate, it presents a serious danger to world health. This research paper proposes a machine learning architecture that uses models based on deep learning (CNN, MobileNet, VGG16, ResNet-50) to identify illness using MRI data. 12,446 images in the dataset obtained through Kaggle are categorized as normal, cyst, stone, and malignancy. The study evaluates the models' performances, and ResNet-50 exhibits the highest accuracy. The VGG16 and ResNet-50 designs for the proposed system are presented, with a focus on their characteristics. Pre-processing, instruction, classification, and collection of data are all included in the implementation. Users may upload their photos to be classified by different algorithms. The results demonstrate the effectiveness of the ResNet-50 model, which had an overall 98% classification accuracy for renal diseases. In conclusion, the application of deep learning specifically, the ResNet-50 model shows promise as a quick and dependable technique for detection, therefore alleviating a major healthcare issue.