Pulmonary Embolism Imaging Using Blood Flow and Background Lung Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for diagnosing pulmonary embolism, such as contrast-enhanced CT and scintigraphy, pose risks to patients due to contrast media allergy and radiation exposure, are labor-intensive, and struggle with accuracy when differentiating thrombi from other diseases based on blood flow analysis.
Innovation Solution
A pulmonary embolism diagnosis support apparatus and method using radiographic dynamic imaging to analyze blood flow and background lungs, generating diagnosis support information without contrast agents or radiopharmaceuticals, and automatically distinguishing between pulmonary embolism and other conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contrast-enhanced CT is used to diagnose pulmonary embolism, then diagnostic accuracy is improved, but patient exposure to contrast media allergy and radiation increases
Solution Approach 1:
The patent introduces dynamic imaging as an intermediary diagnostic tool that captures blood flow information without requiring contrast media. The system uses temporal changes in X-ray attenuation during the cardiac cycle to infer blood flow patterns, serving as a mediator between conventional imaging and functional assessment, thereby avoiding direct exposure to harmful contrast agents while maintaining diagnostic capability
Solution Approach 2:
The patent replaces the mechanical/chemical approach of contrast media administration with a physical approach using temporal-spatial analysis of natural blood flow. Instead of introducing external contrast agents to visualize blood vessels, the system analyzes natural variations in X-ray attenuation caused by blood movement during the cardiac cycle, substituting chemical contrast enhancement with temporal-dynamic physical measurement
2Object-affected harmful factors
If scintigraphy of pulmonary ventilation and blood flow is used, then contrast media allergy is avoided, but radiation exposure from radiopharmaceuticals and complex preparation procedures occur
Solution Approach 1:
The patent extracts the essential functional information (blood flow dynamics) from the complex scintigraphy procedure. By isolating and analyzing only the temporal-spatial patterns of blood flow through dynamic imaging, the system removes the need for radiopharmaceutical administration and complex multi-step scintigraphy protocols, retaining only the critical diagnostic component
Solution Approach 2:
The patent creates a simplified copy of the blood flow assessment function that scintigraphy provides. Instead of using the full complex scintigraphy workflow with radiopharmaceuticals, the system captures and analyzes dynamic imaging data that replicates blood flow information, producing equivalent diagnostic value through a simpler, radiation-free methodology
3Speed
If blood flow analysis based on dynamic image is used, then radiation exposure is reduced and imaging speed is improved, but ability to identify thrombus location and differentiate from other diseases decreases
Solution Approach 1:
The patent segments the diagnostic process into distinct analytical components: (1) temporal analysis of blood flow dynamics, (2) spatial mapping of perfusion patterns, and (3) comparison with anatomical structures. This segmentation allows the system to process dynamic imaging data through multiple independent analysis streams, each contributing to comprehensive thrombus identification and disease differentiation without requiring complex integrated procedures
Solution Approach 2:
The patent adds the temporal dimension to conventional static imaging by capturing multiple frames throughout the cardiac cycle. This transformation from spatial-only to spatio-temporal analysis enables the system to visualize blood flow dynamics and identify perfusion defects that are invisible in static images, thereby improving thrombus detection accuracy while maintaining rapid imaging speed
4Measurement precision
If AI is applied to learn thrombus identification from training data, then diagnostic accuracy is improved, but difficulty in obtaining large amount of correct regional data increases
Solution Approach 1:
The patent makes the dynamic imaging system universally applicable to multiple diagnostic scenarios by designing a methodology that can identify various pulmonary vascular abnormalities (thrombi, emboli, perfusion defects) using the same fundamental approach. This universal framework eliminates the need for separate specialized systems or extensive disease-specific training data for each condition, as the core temporal-spatial analysis methodology applies across different pathological states
Solution Approach 2:
The patent changes the fundamental parameters used for thrombus identification from static anatomical features to dynamic temporal-spatial blood flow characteristics. By shifting the diagnostic basis from structural morphology to functional dynamics, the system can identify thrombi through their hemodynamic effects rather than requiring direct visualization, thereby reducing dependence on large datasets of annotated anatomical images while maintaining high diagnostic accuracy
Data Source
AI summary
A pulmonary embolism diagnosis support apparatus includes a hardware processor that: obtains a dynamic image of a chest of an examinee captured through radiographic dynamic imaging; analyzes blood flow in the dynamic image to generate blood flow information; generates background lungs information regarding background lungs of the examinee; automatically generates diagnosis support information regarding pulmonary embolism, based on the blood flow information and the background lungs information; and outputs the diagnosis support information regarding pulmonary embolism.