Optimized Deep learning Frameworks for the Medical Image Transmission in IoMT Environment

Abstract The Internet of Medical Things (IoMT) is reforming healthcare by enabling interconnected medical devices and systems to facilitate efficient data collection, transmission, and analysis. While IoMT has significantly improved real-time monitoring and personalized care, the transmission of high-resolution medical images remains a challenge due to bandwidth constraints, latency issues, data loss, and computational overhead. Efficient and secure medical image transmission is critical to ensuring reliable diagnostics and timely patient care in this ecosystem. This research presents an optimized Deep Learning (DL) architecture developed to overcome the limitations of medical image transmission in IoMT environments. The proposed solution incorporates Convolutional Neural Networks (CNNs) for spatial feature extraction and dimensionality reduction while preserving diagnostic-critical information, and Long Short-Term Memory (LSTM) networks to manage sequential data and mitigate transmission issues such as packet loss and latency. The framework incorporates robust encryption mechanisms to ensure data security without significantly increasing computational overhead. Once predictions are made, the data is securely transferred to the cloud for further analysis and storage. Furthermore, Hippopotamus Optimization is utilised to enhance the model's performance and fine-tune hyperparameters, improving both efficiency and accuracy. Performance evaluations were conducted using real-world medical image datasets under varying IoMT network conditions. The results demonstrate that the proposed CNN-LSTM framework delivers superior performance across key metrics, like Peak Signal-to-Noise Ratio (PSNR), accuracy, F1 score, specificity, and sensitivity. Additionally, the framework optimizes encryption and decryption times and reduces bandwidth consumption, ensuring efficient and secure data transmission. This approach showcases a significant advancement in IoMT-based medical imaging, paving the way for enhanced reliability and efficiency in healthcare delivery systems.