Tissue Parameter Estimation from RGB Endoscopic Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current intra-operative imaging techniques for minimally invasive surgery are constrained by the need to switch imaging modalities, requiring specialist hardware and long exposure times, which complicates and prolongs surgical procedures.
Innovation Solution
A method and apparatus that utilize standard RGB images from existing endoscope systems to estimate physical parameters like oxygenation and total haemoglobin in biological tissue by applying a physical model and iterative estimation techniques, without the need for hardware modifications or modality switches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multispectral imaging is performed using liquid crystal tuneable filter (LCTF) to capture images across multiple narrow spectral bands, then spectral resolution is improved, but temporal resolution deteriorates and signal blur occurs due to serial acquisition at each wavelength
Solution Approach 1:
The patent uses periodic modulation of the illumination source at known frequencies to encode spectral information in the temporal domain. By illuminating the tissue with light that is modulated at distinct frequencies for different wavelengths, the system captures spectral data through periodic sampling rather than serial wavelength scanning, thereby improving temporal resolution while maintaining spectral resolution.
Solution Approach 2:
The patent transforms the spectral dimension into the temporal dimension by using frequency-modulated illumination. Instead of acquiring images sequentially at different wavelengths (spatial/spectral dimension), the system encodes spectral information in the time domain through periodic modulation, allowing simultaneous capture of multiple spectral bands and eliminating the temporal resolution penalty of serial acquisition.
2Measurement precision
If image registration is performed to correct for tissue motion relative to the camera between image captures for each spectral band, then alignment accuracy is improved, but procedural complexity increases
Solution Approach 1:
The patent performs image registration on a single representative image from the captured set rather than requiring registration between all spectral band images. By pre-aligning the images using motion correction techniques before spectral analysis, the system achieves accurate alignment without the complexity of multi-step registration procedures, thereby reducing procedural complexity while maintaining alignment accuracy.
3Ease of operation
If standard RGB camera is used instead of specialist hardware, then device complexity is reduced and ease of operation is improved, but spectral resolution deteriorates
Solution Approach 1:
The patent changes the temporal parameter of the illumination source by applying periodic modulation at known frequencies. This transforms the static spectral measurement problem into a dynamic temporal measurement problem, allowing a standard RGB camera to extract spectral information through frequency analysis of the modulated light signal, thereby maintaining spectral resolution while using conventional hardware.
Solution Approach 2:
The patent replaces the mechanical/optical filtering system (LCTF) with an electrical modulation system applied to the illumination source. Instead of physically filtering light at different wavelengths through moving or switching optical components, the system uses electronic modulation of the light source and computational extraction of spectral information, simplifying the hardware while preserving 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 real-time or near real-time estimation of tissue parameters, reducing procedural complexity and time, and providing accurate overlays on conventional images, thus enhancing surgical guidance.
Implementation Method 1
acquiring a colour image of the biological tissue... extracting from the colour image at least two images in respective optical wavebands
Implementation Method 2
Several pathological signals, such as melanin and haemoglobin concentration, may correspond to tissue structure and viability, and are detectable by their characteristic attenuation of light in the visible wavelength range
Data Source
Figure 1
Figure 2
Figure 3A~3C
AI summary
A method and apparatus are provided for estimating the value of a physical parameter of biological tissue. The method comprises acquiring a colour image of the biological tissue from a single image capture device; extracting from the colour image at least two images in respective optical wavebands having a different spectral sensitivity from one another, whereby a given location in the biological tissue is present in each of the extracted images; providing a physical model of the optical properties of the biological tissue, wherein the optical properties of the biological tissue are sensitive to the value of said physical parameter; and estimating the value of the physical parameter at said given location based on an intensity value at that location for each extracted image. The estimating utilises the physical model of the optical properties of the biological tissue and the spectral sensitivity for each respective waveband.