Abstract

Medical imaging is essential for accurate diagnosis, treatment planning, and continuous patient monitoring. However, the rapid growth of high-resolution imaging modalities such as MRI, CT, and ultrasound has created major challenges in data storage and transmission.Conventional lossless compression techniques often struggle to provide high efficiency while preserving complete image fidelity.This paper examines advanced AI-based lossless compression methods that utilize deep learning to improve entropy coding, predictive modeling, and adaptive data representation. It presents a comparative evaluation of modern approaches, highlights key performance metrics, and discusses current limitations along with future research opportunities aimed at improving storage optimization and integration into clinical workflows.