Hyperspectral Remote PPG for Tissue-Type Perfusion Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing non-contact PPG imaging technologies fail to accurately differentiate between different tissue types within a single image, averaging perfusion differences that can indicate physiological or pathological conditions, such as ischemia or inflammation, leading to inadequate assessment of tissue health during procedures like intestinal anastomosis.
Innovation Solution
A system utilizing hyperspectral imaging and remote PPG sensing to classify tissue types, estimate oxygenation levels, and derive PPG perfusion maps, combining these to provide a comprehensive tissue status assessment by segmenting images into distinct tissue types and analyzing PPG amplitude and delay maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If general PPG image analysis is used to monitor tissue perfusion, then large tissue areas can be covered, but different tissue types are averaged together losing physiological or pathological information
Solution Approach 1:
The patent applies segmentation by dividing the imaged tissue area into distinct tissue type regions based on spectral characteristics. The system segments the image into different tissue types (e.g., intestine, fat, muscle) and performs separate PPG analysis for each segment, preventing averaging of different tissue types while maintaining comprehensive area coverage
Solution Approach 2:
The patent implements local quality by applying tissue-specific analysis parameters and reference standards to each segmented tissue type. Each tissue region is analyzed with its own characteristics in mind, allowing precise measurement of perfusion changes specific to each tissue type rather than using a uniform analysis approach across all tissues
2Ease of operation
If non-contact PPG imaging is used to monitor skin perfusion, then remote detection is achieved, but accurate differentiation between tissue types is not possible
Solution Approach 1:
The patent utilizes parameter changes by analyzing spectral parameters across multiple wavelengths to differentiate tissue types. The system measures reflectance or absorption at various wavelengths and uses these spectral parameter variations to classify tissue types, enabling accurate differentiation while maintaining non-contact operation
Solution Approach 2:
The patent introduces spectral analysis as an intermediary step between non-contact imaging and tissue characterization. The spectral information acts as a mediator that enables tissue type identification from remote images, bridging the gap between ease of operation and measurement 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
Enables precise separation of perfusion and oxygenation measurements for different tissue types, enhancing the accuracy of tissue health assessment and reducing the risk of complications like leakage during surgical procedures by providing a more complete evaluation of tissue status.
Implementation Method 1
PPG imaging utilizes an off-the-shelf camera and a light source to remotely detect the dynamic changes in blood volume beneath the skin
Implementation Method 2
estimate a presence or level of tissue oxygenation for each tissue type
Data Source
Figure 1(a)~1(b)
Figure 2~3
Figure 4(a)~4(b)
AI summary
A tissue analysis system and method process hyperspectral images to classify tissue types within the images. A presence or level of tissue oxygenation is estimated for each tissue type as well as a PPG perfusion. The estimated tissue oxygenation and PPG perfusion information are combined to provide a tissue status for each tissue type. The system and method uses remote PPG sensing.