A SURVEY ON ARTIFICIAL INTELLIGENCE AND EDGE COMPUTING USED FOR MEDICAL IMAGING OF HEALTH CARE

Abstract

The integration of Artificial Intelligence (AI) and Edge Computing in medical imaging is transforming healthcare by enhancing diagnostic accuracy, reducing latency, and improving accessibility. This survey explores the synergistic use of AI and edge computing in the analysis and interpretation of medical images, particularly in areas such as radiology, cardiology, and pathology. AI technologies, especially deep learning models, have shown great promise in automating image segmentation, detecting anomalies, and aiding in clinical decision-making. However, the computational requirements of AI models often demand substantial resources, which can be a challenge when applied to large-scale imaging datasets. Edge computing addresses this challenge by enabling localized processing of data on devices such as portable imaging systems and smartphones, thus reducing reliance on centralized cloud infrastructure. This approach not only enhances real-time analysis but also improves data privacy and security, which are critical in the healthcare domain. Despite the advantages, there are significant challenges, including hardware limitations, data integration across diverse devices, and the need for regulatory compliance. This survey reviews current trends, technologies, applications, and case studies related to AI and edge computing in medical imaging. It also discusses the opportunities and challenges facing the integration of these technologies into clinical practice, providing insights into future research directions aimed at further advancing the field.