CLOUD-BASED SECURE EHR WITH AES-LSB ENCRYPTION: EMPOWERING LUNG NODULE DETECTION

Abstract

Electronic Health Records (EHRs) have significantly transformed the healthcare landscape recently, which offers patients a fast and interactive environment for patient information, promoting interoperability, and enhancing overall healthcare delivery. However, the current EHR systems lack Interoperability Issues, Usability Concerns, Data Security and Privacy, Data Accuracy and Integrity. To address this challenge, we propose a novel approach utilizing Advanced Encryption Standard with Least Significant Bit (AES-LSB) encryption for securing EHR data in the cloud environment. AES-LSB encryption involves altering the least significant bits of pixel values in an image to embed encrypted information, ensuring minimal visual impact. By manipulating these less noticeable bits, AES-LSB provides a steganographic approach to hide sensitive data within the pixel values of an image, hence providing data security and privacy. Presently, Cellular breakdown in the lungs represents an impressive test in the wellbeing field, addressing a complex and frequently perilous condition that requests thorough consideration because of its high rate, different etiology, and the basic for early recognition and mediation. Therefore, we intend to propose an early lung nodule prediction framework integrating deep learning architecture, enabling precise localization and identification of suspicious regions indicative of cancerous tissues. for early lung nodule prediction, addressing a critical gap in healthcare and underscoring the potential for transformative advancements in both data security and early disease detection.