Secure IoT-Integrated Cloud-Based Medical Image Processing Using Optimized Stereoscopic Scalable Quantum CNN for Efficient Diagnosis
Rejin Paul Nallathambi Rajamani, D. Vetrithangam, Harsh Namdev Bhor, Ram Singar Verma
Abstract
Healthcare data have increased significantly as a result of the quick development of medical imaging technology, necessitating accurate diagnosis, safe transmission, and effective storage. Using a hybrid model known as stereoscopic scalable quantum convolutional neural network-Gooseneck Barnacle optimization (SSQ-CNN-GBO), this study suggests an innovative, safe, and scalable cloud-based medical image analysis framework that is integrated with the Internet of Things (IoT). The system uses quasi-cross bilateral filtering (QBF) for feature preservation and noise reduction, as well as dual elliptic curve-based lightweight authentication and data encryption (DEC-LADE) to guarantee data security. The GBO algorithm is utilized to optimize anSSQ-CNN for classification, while the multiview fuzzy clustering based on anchor graph (MVFCAG) approach is employed for accurate segmentation. Tests on the brain tumor MRI and chestX-ray14 datasets show that the suggested model outperforms current techniques in terms of diagnosis and encryption efficiency, achieving 99.97% accuracy and 98.57% precision. IoT-enabled healthcare systems can process medical images securely, accurately, and in real time thanks to this integrated solution.