Hybrid Deep Learning Models with Genetic Algorithm Optimization for Enhanced Kidney Tumor Detection

Accurate and timely segmentation of kidney tumors from medical images is crucial for effective treatment and prognosis. This research study proposes a novel hybrid deep learning framework incorporating Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for enhanced kidney tumor segmentation. To optimize model performance, Genetic Algorithms (GA) are employed to fine-tune hyperparameters and network architecture. The proposed method effectively captures both local and global image features, leading to improved segmentation accuracy compared to existing techniques. Experimental results on a publicly available dataset demonstrate the superiority of our approach in terms of recall, F1-score, and precision. This research contributes to the advancement of computer-aided diagnosis for kidney cancer.