A new transparent cloud-based model for sharing medical images with data compression and proactive resource elasticity
Thiago Roberto Lima Lopes, Igor Fontana de Nardin, Cristiano André da Costa, Rodrigo da Rosa Righi · International Journal of Electronic Healthcare · 2022
Telemedicine and remote diagnosis are yet challenging because nowadays we do not have scalable and standard solutions for sharing DICOM images across different hospitals. DiCloud is a model to enable DICOM image sharing among different hospitals, enabling patients to access their exams effortlessly. We provide an interoperability module where current DICOM applications do not need to be changed, allowing users to save and retrieve data to/from both the cloud and local PACS. Besides this novelty, DiCloud also brings the following state-of-the-art contributions: 1) ARIMA-based proactive cloud elasticity by anticipating resource reorganisation before under- or overprovisioning situations take place; 2) compression engine for sending and receiving messages at both client and cloud parts transparently. The results demonstrate that it is possible to keep the QoS (0% request errors) and reduce cloud costs. In particular, proactive elasticity enabled fewer connected VMs for more extended periods, saving costs related to cloud usage.