Kidney Stone Detection in Medical Imaging Using Transfer Learning with ResNet50

This work presents a method based on transfer learning to identify kidney stones in patients by analyzing medical photographs. The renal ultrasonography and CT pictures are used by the model to extract features using the ResNet50 architecture, a deep convolutional neural network that has been pre-trained on massive datasets. The suggested method improves kidney stone detection accuracy by fine-tuning the pre-trained model. According to experimental data, the model successfully detects kidney stones with high sensitivity and accuracy, making it a useful tool for early diagnosis and treatment planning. The work demonstrates that transfer learning can be used for medical image evaluation and diagnosis.