Securing Tuberculosis Disease Detection with IoT-Driven Improved AlexNet and RSA Encryption

This study provides tuberculosis (TB) disease detection method that protects patient data and is accurate. It uses homomorphic filtering to improve chest X-ray images using the Shenzhen dataset, which rallies classification. The advised Improved AlexNet model extracts complex features from pre-processed images to detect tuberculosis. In addition to image processing and classification advances, this paper incorporates Rivest–Shamir–Adleman (RSA) encryption to secure patient data. This RSA algorithms. Guaranteeing patient record confidentiality and integrity ensures ethical and privacy compliance. This method has a Peak Signal-to-Noise Ratio (PSNR) of 49.84, a minimized Bit Error Rate (BER) of 0.39, an SSI of 0.93, model.