ASPECT ASPECT SCORE ESTIMATION SYSTEM AND METHOD

摘要

The present invention relates to a system and a method for estimating an ASPECT score to estimate an ASPECT score, which is a factor for differentiating a stroke disease in a brain CT image. The method comprises: a pre-processing step of normalizing and standardizing a feature of an image dataset; a segmentation step of separating each lesion within CT images classified into a supra ganglion level and a ganglion level; and a determination step of determining whether a lesion is stroke by independently constructing a neural network, which learns positive/negative images for each lesion. By using a brain CT image of a patient, the ASPECT score, which is an objective indicator for diagnosing a condition of a stroke patient, may be estimated.