Slice-level classification of kidney organ presence using CNN-ViT features: Toward clinical pre-screening

Kidney stone disease is a major global health concern due to its rising prevalence and related complications. Although computed tomography (CT) is highly sensitive for diagnosis, its volumetric nature increases radiologists' workload and review time. This study proposes a lightweight and low-cost deep learning-based pre-classification model to distinguish between CT slices containing the kidney and those that do not, as a preliminary step for kidney stone detection systems. The model aims to eliminate irrelevant slices and direct only meaningful images to both the second-stage AI model and the radiologist. Vision Transformer (ViT) was used to capture the global spatial context of the kidney, while ResNet18 extracted local features. These features were fused and classified using a shallow neural network. The model was tested within an interactive interface built using real patient data and integrated into a pilot application. Results showed that the proposed system achieved an average of 64.1% time saving per patient (similar to 24 minutes) by filtering out non-relevant slices, with 89.4% accuracy, 89.4% recall, and 89.5% specificity. These findings suggest that the model is a practical and efficient pre-screening component for clinical workflows and highlights the importance of pilot testing and expert feedback before real-world deployment of AI systems.