Gated Recurrent Assisted Vision Transformer for Kidney Tumor Segmentation with Effective Optimization Algorithm

The prognosis and severity of kidney cancer significantly impact the chances of recovery, necessitating accurate and timely diagnostic methods. However, manual segmentation remains a challenging and time-consuming task. In order to overcome these challenges, a novel deep learning (DL) based segmentation framework, which integrates pre-processing and segmentation stages. Initially, the quality of the images is improved by the probabilistic wiener filter and statistical HU windowing mechanism. A novel Bidirectional recurrent gated vision transformer (Bi-ReGaViT) approach is introduced for precise kidney and tumor segmentation. Finally, the hyperparameters in the classifier models are fine-tuned using the enhanced Elk herd optimization algorithm (EEHOA), which improves model accuracy significantly. The effectiveness of the proposed approach is validated using the KiTS19 dataset, which demonstrates a superior segmentation performance with a dice similarity coefficient (DSC) of 94.89%, accuracy of 97.4% and sensitivity of 96.0%. For the CT kidney dataset, the proposed model has obtained an accuracy of 98.3%. The experimental results confirm that the proposed model enhances segmentation accuracy, robustness and computational efficiency, making it a promising tool for clinical kidney cancer diagnosis. The proposed model can be integrated into a computed aided diagnosis (CAD) system to assist radiologists in real-time kidney tumor detection, reducing manual efforts and improving diagnostic accuracy. This approach can also be deployed in automated surgical planning systems to improve precision in robotic-assisted kidney surgeries.