Deep-ASPECTS: A Segmentation-Assisted Model for Stroke Severity Measurement

A stroke occurs when an artery in the brain ruptures and bleeds or blood supply to is cut off. Blood oxygen cannot reach brain’s tissues due rupture obstruction resulting tissue death. The Middle cerebral (MCA) largest most commonly damaged vessel stroke. quick onset of a focused neurological deficit caused by interruption flow territory supplied MCA known as Alberta programme early CT score (ASPECTS) used estimate extent ischemic changes patients with This study proposes deep learning-based method scan for ASPECTS. Our work has three highlights. First, we propose novel medical image segmentation detection. Second, show effectiveness AI solution fully-automated ASPECT scoring reduced diagnosis time given non-contrast (NCCT) Scan. algorithms dice similarity coefficient 0.64 anatomy 0.72 infarcts segmentation. Lastly, that our model’s performance inline inter-reader variability between radiologists.