Automated Vascular Pathology Detection in CT Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current acute stroke diagnosis methods using computed tomography (CT) imaging are inefficient and lack automation in detecting brain aneurysms, arteriovenous malformations, and other vascular pathologies, leading to suboptimal clinical workflows and diagnostic accuracy.
Innovation Solution
The development of a system and method that processes various types of CT imaging data, including non-contrast, angiography, and dual energy data, using shape and texture-based algorithms to detect and visualize pathological conditions such as aneurysms, arteriovenous malformations, and vasospasm, by selecting appropriate processing algorithms and superimposing processed data onto original vasculature images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple separate imaging protocols (CT, CTA, CTV, dynamic CT perfusion) are used to diagnose vascular pathologies, then diagnostic comprehensiveness is improved, but device complexity and workflow efficiency deteriorate
Solution Approach 1:
The patent combines multiple separate imaging protocols (CT, CTA, CTV, and dynamic CT perfusion) into a single integrated imaging workflow. The system processes multi-phase dynamic CT perfusion data to simultaneously generate NCT, CTA, and CTV phases, eliminating the need for separate scanning protocols while maintaining comprehensive diagnostic coverage for vascular pathologies including aneurysms, AVMs, and vasospasm.
Solution Approach 2:
The imaging system is designed to perform multiple diagnostic functions using a single protocol. The dynamic CT perfusion scan protocol can extract NCT, CTA, and CTV phases from the same data set, making the system universal for detecting various vascular pathologies without requiring separate specialized equipment or protocols for each condition.
2Measurement precision
If manual detection methods are used for vascular pathologies, then diagnostic accuracy can be maintained, but productivity and time efficiency deteriorate
Solution Approach 1:
The system implements automated detection algorithms that perform pathology detection without requiring manual intervention. The processor automatically analyzes imaging data to detect aneurysms, AVMs, and vasospasm, and generates visualizations superimposing detected pathologies on original images, enabling the system to serve itself in the diagnostic process while maintaining accuracy and improving throughput.
Solution Approach 2:
The patent replaces manual visual inspection and manual measurement methods with automated computer-based detection algorithms. The system uses processing routines to automatically analyze imaging data, identify pathological features, and generate diagnostic visualizations, substituting the mechanical process of manual review with automated computational analysis that maintains diagnostic accuracy while dramatically improving productivity.
3Measurement precision
If separate CTA and CTV scans are performed in addition to dynamic CT perfusion, then vascular detail detection is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary extraction of CTA and CTV phases from the dynamic CT perfusion data before any additional scanning is performed. By processing the dynamic perfusion data to extract the necessary vascular phases (NCT, CTA, CTV) in advance, the system eliminates the need for time-consuming separate CTA and CTV scans while maintaining the ability to detect vascular details with the same level of precision.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables automated and integrated detection of vascular pathologies, improving diagnostic accuracy and streamlining clinical workflows by providing a comprehensive and efficient analysis of CT imaging data, enhancing the ability to rule out brain aneurysms and other conditions.
Implementation Method 1
Dual energy CTA provides an ability to separate iodine in a contrast-enhanced vasculature from calcium or bone
Implementation Method 2
Dual energy CTA also provides an ability to reduce or eliminate beam-hardening effects, which are seen within the cranium
Data Source
AI summary
Certain embodiments of the present invention provide systems, methods and computer instructions for detecting a pathological condition of a vasculature. Certain embodiments provide a method for detecting a pathological condition of a vasculature. The method includes accessing imaging data indicative of the vasculature and having a data type, selecting a detection process corresponding to the data type from among a plurality of detection processes, each of the detection processes processing data of a different data type. The method also includes processing the imaging data having the data type with the selected detection process, and superimposing the processed imaging data on the imaging data indicative of the pathological condition of the vasculature.