The method for estimating the ASPECT score according to the present invention includes: a pre-processing step in which the pre-processing unit normalizes and standardizes the characteristics of the image data set; A segmentation step in which the image processing unit separates each lesion within a CT image classified into a supra ganglion level and a ganglion level; And a judging unit determining a stroke of the lesion by independently constructing a neural network that learns positive/negative images for each lesion. A noise removing step of removing noise included in the image; A search step of searching for a skull ellipse to find a skull in the brain CT image; An alignment step of aligning the position of the image based on the center point of the retrieved skull and rotating the image to uniformly align the position and rotation angle of the dataset; And performing a horizontal invert according to the location of the lesion (Lesion-Side); including, the search step, by searching for an adaptive threshold value considering the pixel value distribution of the segmented image, skull An automatic thresholding step of inducing to leave only pixel information corresponding to; A contour search step of detecting an edge based on the thresholded image; And a skull ellipse information acquiring step of acquiring ellipse information of the inner and outer edges of the skull by searching for a skull ellipse from the image where only the edge information is left.
展开▼
