RGB Sensor Bilirubin Estimation via Optical Diffusion Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for estimating bilirubin levels, such as blood samples and traditional skin color analysis, are costly and complex, making them inaccessible in low-income countries, and recent technologies like ClikJaundice rely on color calibration charts and central servers, which are sensitive to illumination and positioning.
Innovation Solution
A method using an RGB sensor with a color calibration chart printed via spectral printing, employing optical diffusion models or Monte Carlo simulations to calculate bilirubin levels, allowing for use with low-cost cameras and accommodating different skin types without a reliable internet connection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods (blood samples, centralized skin color analysis) are used, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces complex mechanical and centralized processing systems with a mobile-based optical measurement system. Instead of using centralized laboratories or complex medical equipment, the invention uses a mobile device camera to capture skin color images, processes them through optical diffusion models, and estimates bilirubin levels locally, thereby reducing device complexity while maintaining measurement capability.
Solution Approach 2:
The patent creates a computational model (optical diffusion model) that copies and simulates the physical optical properties of skin under different bilirubin concentrations. This virtual model allows the system to estimate bilirubin levels by comparing captured images against simulated skin colors, replacing the need for physical blood sample analysis while maintaining measurement precision.
2Ease of operation
If color calibration charts are used (as in ClikJaundice), then ease of operation is improved, but reliability deteriorates due to sensitivity to illumination and positioning
Solution Approach 1:
The patent changes the fundamental parameters of the calibration approach by replacing physical color calibration charts with computationally generated skin color models. Instead of relying on external reference objects that are sensitive to illumination and positioning, the system uses optical diffusion models that simulate skin optics under various conditions, making the measurement more reliable while maintaining ease of operation.
Solution Approach 2:
The patent introduces an optical diffusion model as an intermediary between the captured skin image and the bilirubin level estimation. This computational model acts as a mediator that accounts for variations in skin optics, illumination, and camera characteristics, thereby improving reliability without requiring physical calibration artifacts or centralized processing.
3Adaptability or versatility
If spectral printing is used for calibration chart, then adaptability is improved, but manufacturing precision requirements increase
Solution Approach 1:
The patent extracts the calibration functionality from physical printed charts and relocates it to computational models. By removing the need for physically printed calibration references, the system eliminates the manufacturing precision requirements associated with spectral printing while maintaining adaptability to different skin types through software-based optical modeling.
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 simple, reliable, and affordable estimation of bilirubin levels, suitable for low-income settings, using mass-market cameras and accommodating various skin colors, while being independent of reliable internet connections.
Implementation Method 1
receiving a depiction of a skin portion of the subject with a colour calibration chart using an RGB sensor
Implementation Method 2
the level of bilirubin is calculated by comparing simulated skin colours having known bilirubin concentrations with the calibrated skin colour wherein the simulated skin colours are obtained by using an optical diffusion model of skin
Implementation Method 3
the calibration chart comprises a plurality of colour patches printed using spectral printing
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
The invention relates to diagnosis in general and more specifically a system and a method for determining the presence of jaundice in newborn babies, also known as neonatal jaundice. A main objective of the present invention is to provide a simple system and method for determining the presence of jaundice. Particularly since most deaths due to jaundice occur in low-income countries, there is a large unmet need of simple, reliable and affordable technologies able to identify at-risk newborn. The objective is accomplished through receiving a depiction of skin from an RGB sensor, and then using either an optical diffusion model of the skin or Monte Carlo simulations to calculate the bilirubin concentration. A meta model of the optical diffusion model or Monte Carlo simulations can also be used. Colour calibration is also performed by e.g. thin-plate spline interpolation.