Associative algorithm and policy with advance loading and self-tuning for medical imaging storage in hybrid cloud

Advances in medical imaging have resulted in rapid growth in the amount and also the size of medical images that are stored in the medical imaging information systems. As a result of such rapid growth in storage requirements, public and private storage clouds have special appeal to medical imaging storage applications. Another factor that makes cloud storage attractive to medical imaging is that the time span of data retention has been increasing and in many cases it is now for the life of patient and many years beyond. In addition, Cloud solutions facilitate accessing data from any device and anywhere. Wide variety of cloud based solutions that are currently available cannot be effectively applied to medical imaging applications because of inefficient support for specific characteristics of the medical imaging data access. For many practical reasons including access speed requirements, off premise public/private clouds cannot be an optimum solution for medical imaging and hybrid cloud solutions are preferred and primarily used. However the existing hybrid cloud solutions primarily use public cloud as the backup for on-premise storage or as an archive for old/inactive records or as a copy for Healthcare Information Exchange with other healthcare entities. This paper provides a solution for optimizing total cost of ownership associated with volume, growth and scalability of medical imaging storage systems. It models medical imaging storage as a three level cache. It introduces a cache algorithm and policy that is devised based on the characteristics of medical imaging applications such as the inherent association of cache entries through patient attribute and the recognizable data usage patterns such as cancer treatment plans. Healthcare Information Exchange is an easy extension to this solution where images in public clouds can be shared and exposed to the other healthcare providers or entities of interest.