Abstract

The exponential growth of medical imaging datasets has necessitated robust methods for secure data transmission and accurate image analysis. Conventional methods often struggle with maintaining a balance between data security and processing efficiency, especially in sensitive domains like healthcare. The integration of cryptographic techniques with deep learning has shown promise in addressing these challenges. This work presents an AES-based cryptographic framework integrated with Deep Convolutional Neural Networks (Deep CNN) for enhanced medical document image processing and analysis. The AES encryption ensures secure transmission of sensitive medical data, safeguarding patient confidentiality. Once securely transmitted, the encrypted images are decrypted and analyzed using a Deep CNN model tailored for feature extraction and classification tasks in medical imaging datasets. The system was evaluated on publicly available datasets, including chest X-ray and brain MRI scans, comprising 10,000 images across various conditions. The proposed method achieved a classification accuracy of 98.7%, outperforming existing approaches by 3.4%. The encryption and decryption times were measured at 0.012 seconds and 0.015 seconds per image, ensuring minimal overhead during secure transmissions. Additionally, the system demonstrated an F1-score of 0.982 and a sensitivity of 97.8%, indicating its effectiveness in detecting anomalies in medical images.