Voxel Registration for Lung Phenotyping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing and characterizing Chronic Obstructive Pulmonary Disease (COPD) and lung cancer are limited by their reliance on static imaging, which fails to accurately differentiate between COPD phenotypes and lung function variations due to the dynamic nature of lung tissue, leading to inadequate treatment planning and inefficient screening.
Innovation Solution
A system and method that utilize inspiratory and expiratory volumetric images to register and analyze lung tissue changes voxel-by-voxel, calculating continuous probabilities of tissue destruction and ventilation deficits to provide detailed, three-dimensional representations of lung function and disease probability, enabling precise phenotyping and personalized treatment approaches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If static CT imaging is used to diagnose COPD, then the diagnostic process is simple and quick, but the accuracy of differentiating between COPD phenotypes is insufficient
Solution Approach 1:
The patent transitions from static single-phase CT imaging to dynamic two-phase (inspiration and expiration) CT imaging. By capturing lung images at both inspiration and expiration phases and performing voxel-by-voxel registration and comparison, the system dynamically assesses lung tissue changes during breathing, enabling accurate differentiation between emphysema and air trapping phenotypes while maintaining a systematic analytical approach.
Solution Approach 2:
The patent segments the lung into individual voxels and performs registration and analysis at the voxel level. By dividing the lung volume into discrete three-dimensional elements and analyzing each voxel's density changes between inspiration and expiration phases, the system achieves precise localization and characterization of different COPD phenotypes in specific lung regions.
2Measurement precision
If the entire lung is analyzed using Hounsfield Unit thresholds, then the assessment is comprehensive, but the localization of disease in particular portions is limited
Solution Approach 1:
The patent implements voxel-level segmentation and analysis by registering inspiration and expiration CT scans and evaluating density changes at each voxel. This segmentation approach enables precise localization of emphysema and air trapping to specific lung regions and lobes while preserving comprehensive assessment of overall lung function through aggregation of voxel-level findings across the entire lung volume.
Solution Approach 2:
The patent applies local quality analysis by characterizing different lung regions with phenotype-specific metrics. By calculating inspiration-to-expiration density ratios and volume changes at each voxel and aggregating results by anatomical region, the system provides both localized disease characterization and comprehensive lung function assessment simultaneously.
3Measurement precision
If only single-phase CT imaging is used, then the imaging process is simple, but the dynamic nature of lung expansion during breathing cannot be assessed
Solution Approach 1:
The patent employs periodic action by acquiring CT images at two distinct phases of the breathing cycle (inspiration and expiration). This periodic imaging approach captures the dynamic changes in lung density and volume that occur during normal breathing, enabling assessment of ventilation function and differentiation of COPD phenotypes while maintaining efficient two-phase acquisition protocol.
4Measurement precision
If defined cut-off values are used for disease determination, then the diagnosis is straightforward, but the differentiation between phenotypes in mixed disease is inadequate
Solution Approach 1:
The patent changes the diagnostic parameter from simple Hounsfield Unit thresholds to inspiration-to-expiration density ratios and volume change metrics. By calculating the ratio of expiratory to inspiratory density values and the magnitude of volume change at each voxel, the system distinguishes between emphysema (characterized by minimal density change) and air trapping (characterized by significant density increase on expiration), enabling accurate phenotype differentiation in mixed disease cases.
Data Source
AI summary
Methods and systems for assessing lung function using volumetric images obtained at inspiration and expiration. The method may include processing the first and second set of images to identify known anatomical structures of the lungs, registering the first set of images to the second set of images to match voxels of the first set of images to voxels of the second set of images as matched pairs of inspiratory and expiratory voxels, calculating a continuous probability of a lung characteristic at a location of the matched pairs of voxels, and displaying the result on a display. The method may also include classifying lung tissue at each location as normal, having air trapping without emphysema, or being emphysematous.