This invention relates to the field of
image processing technology, specifically to an automated intracranial
aneurysm detection
system based on CT images. The
system includes: analyzing all local regions of each vascular segment based on vascular CT images to obtain the probability of local vascular abnormalities; identifying potential abnormal bulging regions based on these probabilities; further obtaining candidate regions for the vascular segment and candidate regions for bifurcation points; obtaining a first
aneurysm probability based on the degree of protrusion and perpendicularity of the growth direction of the candidate regions, and distinguishing between physiological curvature and
aneurysm regions based on the first aneurysm probability; calculating a second aneurysm probability based on the positional difference value and
sphericity matching degree of the candidate regions for bifurcation points, and distinguishing between natural bulges at bifurcation points and aneurysm regions based on the second aneurysm probability. By analyzing different morphologies and structures of intracranial vessels, the
system distinguishes between normal vascular structures and aneurysm regions, thereby achieving accurate identification of intracranial aneurysms.