AI Stroke Diagnosis Apparatus for ASPECT Score Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current stroke diagnosis methods using non-contrast CT images face challenges in consistency and accuracy due to variability in scoring among clinicians, leading to potential errors in determining the severity and prognosis of stroke, particularly in assessing large vessel occlusion.
Innovation Solution
An AI-based stroke diagnosis apparatus and method that preprocesses CT images by removing noise, aligning anatomical structures, and classifying hemorrhage, followed by normalization and extraction of Regions of Interest (ROIs) using a standard mask template, enabling objective estimation of the ASPECT score and determination of large vessel occlusion for precise treatment decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual ASPECT score assessment by clinicians is used, then diagnostic flexibility is maintained, but scoring variability and inconsistency increase
Solution Approach 1:
The patent replaces the manual mechanical assessment process with an AI-based automated system that processes CT images through deep learning algorithms. The AI model objectively calculates ASPECT scores by analyzing ischemic changes in brain regions, eliminating human variability and providing consistent, reliable diagnostic results across different clinicians and institutions.
Solution Approach 2:
The system creates a standardized digital representation of brain anatomy through template matching and region-of-interest extraction. By copying and analyzing standardized anatomical regions across multiple CT images, the system ensures consistent measurement boundaries and improves the reliability of ASPECT score assessment.
2Productivity
If manual stroke diagnosis assessment is used, then clinical judgment can be applied, but time consumption increases
Solution Approach 1:
The system performs preliminary automated processing of CT images including noise filtering, skull stripping, and pre-segmentation of brain regions before final ASPECT score calculation. This preliminary action prepares the data in advance, enabling rapid clinical decision-making without sacrificing diagnostic quality.
Solution Approach 2:
The AI-based automated assessment system replaces time-consuming manual evaluation with rapid algorithmic processing that can analyze multiple brain regions simultaneously, significantly reducing the time required for stroke diagnosis and treatment planning.
3Measurement precision
If standardized mask template is used for ROI extraction, then consistency is improved, but adaptability to individual anatomical variations decreases
Solution Approach 1:
The system applies local quality adjustment by allowing the standardized mask template to be locally adapted to individual patient anatomy. The template matching process identifies corresponding anatomical landmarks and adjusts the ROI boundaries locally to accommodate natural anatomical variations while maintaining overall standardization for consistent ASPECT score calculation.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided is a stroke diagnosis apparatus based on AI (Artificial Intelligence) that includes: an image obtainer obtaining a non-contrast CT image related to the brain of at least one patient; a preprocessor pre-processing the non-contrast CT image and determining whether the at least one patient is in a non-hemorrhage state or a hemorrhage state on the basis of the pre-processed image; an image processor normalizing the pre-processed image and dividing and extracting an ROI (Region of Interest) using a preset standard mask template; and a determiner determining whether there is a problem with a cerebral large vessel of the at least one patient using the divided and extracted ROI, in which the determiner estimates an ASPECT score of the at least one patient using the divided and extracted ROI when there is a problem with the cerebral large vessel of the at least one patient, and determines that the at least one patient is a patient to whom mechanical thrombectomy can be applied only when the estimated ASPECT score is a predetermined value or more.