TransConvNet: Enhancing Kidney Abnormality Detection in CT Imaging through Hybrid Transformer-CNN Model with Integrated Explainability

This study introduces TransConvNet, a hybrid model combining Transformer and Convolutional Neural Networks (CNNs) for detecting kidney abnormalities in CT images. The model leverages CNNs for local feature extraction and Transformers for capturing global context. By integrating explainable AI (XAI) through Gradient-weighted Class Activation Mapping (Grad-CAM), the model enhances transparency and interpretability in clinical settings. The proposed model achieves an overall accuracy of 99.90%, with precision, recall, and F1 scores nearing 1.00 across multiple classes, highlighting its potential as a reliable diagnostic tool.