Automated Stroke Assessment Using CT Atlas Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for assessing ischemic stroke in non-contrast computed tomography (CT) scans are subjective and time-consuming, often relying on manual identification of thrombi and visual inspection, which can lead to inconsistencies and delays in treatment.
Innovation Solution
A computer-implemented method that receives computed tomography imaging data and brain atlas data to generate registered imaging data, which is then used to provide automated stroke information, including the location of blood clots, affected brain regions, and density reductions, using a set of algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual visual inspection and ASPECT score are used for stroke assessment, then the method is simple and widely available, but the assessment is subjective and time-consuming
Solution Approach 1:
The patent replaces the manual mechanical process of visual inspection and scoring with an automated computer-based image processing system. The system uses algorithms to automatically analyze CT images, calculate ASPECT scores, and identify affected brain regions, eliminating subjective human judgment and reducing assessment time while improving reliability.
Solution Approach 2:
The system enables self-assessment of stroke severity by automatically processing CT images and generating ASPECT scores without requiring manual intervention. The automated algorithms independently perform the assessment tasks that previously required radiologist expertise, making the process more efficient and consistent.
2Measurement precision
If CTA scan is performed to reliably determine affected regions and localize thrombus, then the measurement precision is improved, but the device complexity and cost increase
Solution Approach 1:
The patent segments the brain into standardized anatomical regions based on the ASPECT score framework, allowing precise localization of affected areas and thrombus location without requiring complex CTA imaging. By dividing the brain into 10 specific regions, the system achieves accurate spatial identification using simpler non-contrast CT data.
Solution Approach 2:
The patent introduces an automated image analysis system as an intermediary between the CT scan and clinical interpretation. This intermediary process enhances the information from simple CT scans by automatically detecting and localizing thrombi and affected regions, achieving precision comparable to CTA without the added complexity of contrast-enhanced imaging.
3Productivity
If automated algorithms are used for stroke assessment, then the productivity and consistency are improved, but the device complexity increases
Solution Approach 1:
The patent implements a universal automated assessment system that performs multiple functions: image acquisition, preprocessing, ASPECT score calculation, affected region identification, and report generation. This multi-functional system handles the entire assessment workflow through a single integrated platform, improving productivity while managing complexity through consolidation rather than multiplication of components.
Data Source
AI summary
At least one example embodiment relates to a computer-implemented method for providing stroke information, the method comprisingreceiving computed tomography imaging data of an examination area of a patient, the examination area of the patient comprising a plurality of brain regions, at least one brain region of the plurality of brain regions being affected by a stroke,receiving brain atlas data,generating registered imaging data based on the computed tomography imaging data and the brain atlas data, the registered imaging data being registered to the brain atlas data,generating the stroke information regarding the stroke based on a set of algorithms and the registered imaging data, andproviding the stroke information.