We develop image algorithms to support diagnosis and treatment decisions in stroke. We further aim to simplify the CT imaging protocol by developing new techniques to enable single 4D CT scanning, saving radiation dose, contrast agent and time to diagnosis.
The first algorithms have focused on the segmentation of the main cerebral anatomical structures, including the intra-cavity space, blood vessels, white matter, gray matter and cerebrospinal fluid (see image below, and this interview). We then have shifted our focus on the automated detection of neurovascular pathologies and 3D image reconstruction (such as the non-contrast CT) from a 4D CT acquisition.
Aunt Minnie has extensively covered our work: on intra-cavity segmentation, on wm/gm segmentation and on color-mapping to visualize vascular flow disturbances. The work on intra-cavity segmentation was also covered by SPIE Newsroom.