The Perfusion Measurement Platform v1 is a cloud-based image processing software that automatically quantifies cerebral perfusion parameters from arterial spin labeling MRI scans. It helps clinicians by providing semi-quantitative maps of cerebral blood flow and arterial transit time, aiding the diagnosis and evaluation of brain perfusion without requiring direct user interface interaction.
The Perfusion Measurement Platform (PMP) v1 is an image processing software device to be used by trained professionals including but not limited to physicians and medical technicians. The software is hosted on a cloud platform and can be used to perform medical image processing. Data and images are acquired through connection to DICOM compliant imaging devices and modalities. PMP v1 provides automatic semi-quantitative quantification of Arterial Spin Labelling (ASL) data acquired from Magnetic Resonance Imaging (MRI) scanners at 1.5T and 3.0T. PMP v1 is able to process single-delay and multi-delay ASL data from SIEMENS XA31+, GE 3D ASL scanners to generate multiple perfusion parameters (Relative Cerebral Blood Flow/relCBF, Arterial Transit Time/ATT) and exports the results of ASL image analysis as DICOM images.
The platform is implemented in Python, hosted on Google Cloud Platform, and connects to DICOM servers to receive imaging data. It consists of modules for orchestration, DICOM storage, workflow event triggering, image processing pipeline, polling, and pushing results back as DICOM images. It applies pre- and post-processing steps including motion correction, quality control checks, and fits a fast variational Bayesian kinetic model to produce perfusion parameter maps (relCBF, ATT). It supports image registration to structural MRI for anatomical overlay. There is no direct user interface; processing occurs server-side on the cloud.
Non-clinical performance testing using computational simulations and reference datasets from GE and Siemens demonstrated statistically similar accuracy in perfusion parameter estimation compared to predicate devices. Software verification and validation, cybersecurity testing, and human factors/usability validation were conducted. The technological differences compared to the predicate device do not raise different safety or effectiveness questions.
No predicate devices specified
Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.