A Novel Approach for Security in Cloud-Based Medical Image Storage Using Segmentation

Over the past decade, imaging technology has played a vital role in modern medicine. In fact, it is mainly used to improve diagnosis and facilitate collaboration among healthcare professionals. Nevertheless, in order to build and deploy Electronic Medical Records (EMR), systems require powerful platform, including software and hardware. To address these issues, Cloud Computing has been recently introduced to reduce operating costs. In this respect, only needed resources are provided to the clients and billed according to services utilization. Accordingly, Storage-as-a-Service (SaaS) model aims at outsourcing the storage of medical data to a third party. In spite of its economic benefits, Cloud adoption still faces security challenges. Alternatively, various implementations based on traditional encryption algorithms have been suggested. However, most of them do not take into consideration image features, and hence, they are not suitable for medical images. They are also computationally expensive, and distort the medical image quality by using lossy methods. In this study, we rely on a segmentation approach to protect health information without affecting its quality. In this regard, the secret image is split into several portions by means of a K-means algorithm. Furthermore, each party is stored in a distinct Cloud to enhance data privacy. That is why we use DepSky as a Multi-Cloud environment for safeguarding patient's digital records. The implementation results show that our proposal guarantees both security and quality of medical images.