Kidney stone disease is a common and painful urological disorder that requires timely diagnosis and intervention. Traditional diagnostic methods such as ultrasound and CT scans demand significant clinical expertise for interpretation, often leading to diagnostic delays or inconsistencies. In response to this challenge, we propose an Artificial Intelligence (AI) driven model designed for the automatic detection and classification of kidney stones using medical imaging modalities. This research introduces an advanced AI-based framework for the automated detection and classification of kidney stones using medical ultrasound imaging. The model employs Convolutional Neural Networks (CNNs) to enhance diagnostic accuracy and reduce the time needed for clinical decision-making. Trained on a comprehensive dataset of 7400 ultrasound images—comprising 3800 kidney stone cases and 4000 normal images—the system is capable of automatically extracting and learning significant features related to kidney stone presence, size, and location. The model achieved an impressive accuracy of approximately 97%, with high precision and recall, indicating strong potential for real-world clinical deployment.