Evaluating a Deep-Learning System for Automatically Calculating the Stroke ASPECT Score

Abstract

The stroke is one of the leading causes of death around the world. It is a dangerous disease that results in a permanent disability. CT and MRI are representative imaging diagnostic tools for diagnosing the stroke. Particularly, CT has an advantage of examining the disease quickly. The Alberta Stroke Program Early CT Score (ASPECTS) is widely used as a tool to demonstrate the severity of the stroke based on CT images. However, it has a scoring variability issue among medical experts. This study proposed an object and automated ASPECT Score estimation system based on the image processing and deep learning technology for resolving the issue.