Cloud-based magnetic resonance imaging system in the 6G and AI era

Magnetic Resonance Imaging (MRI) plays a vital role in modern medical diagnostics, generating petabytes of critical data each year in healthcare facilities around the world. However, challenges such as big data storage, data accessibility, and data security hinder MRI’s potential to further enhance global healthcare.

To that end, Professor Xiaobo Qu and his research team at Xiamen University have developed a cloud MRI system. This new platform will facilitate seamless data sharing and improve diagnostic capabilities across healthcare institutions.

“Traditional methods of managing MRI data face significant limitations, from storage constraints to barriers to collaborative research,” explains Professor Qu. “Our Cloud MRI system leverages the power of distributed cloud computing, ultra-fast 6G bandwidth, edge computing, federated learning and blockchain technology to address these challenges.”

At the core of the Cloud MRI system is the ability to upload k-space raw data, essential for MRI reconstruction, to an integrated server or local edge node in ISMRMRD format, a standard vendor-neutral file format for MRI research and development, facilitating rapid image reconstruction and enabling advanced artificial intelligence (AI)-driven tasks, significantly improving diagnostic efficiency.

“The first-generation cloud MRI system has been installed at csrc.xmu.edu.cn/CloudBrain.html, and enables multi-vendor data reading, AI-based MRI image reconstruction, blinded image quality assessment by radiologists, metabolic spectrum analysis, and visualized AI programming (no coding),” Professor Qu emphasized, adding, “We expect the success of the cloud MRI system to have a revolutionary impact on medical diagnosis and patient care.”

The research team published their study in the journal Neurology. Magnetic resonance character.

Provided by KeAi Communications Co.