Multispectral Imaging Augmentation for Surgical Tissue Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for functional imaging in surgery lack the ability to provide real-time, high-resolution images of tissue perfusion and oxygenation, and are not adaptable to varying lighting conditions commonly found in surgical environments.

Innovation Solution

A method and system for generating augmented images of tissue using multispectral information, which involves estimating the spectral composition of illuminating light, obtaining multispectral images, and applying a machine learning-based regressor or classifier to derive tissue parameters, while adapting to changing illumination conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If linear estimation approaches based on the modified Beer-Lambert law are used, then the imaging speed is fast, but the measurement precision of tissue parameters is limited and unrealistic assumptions about tissue composition are required

Engineering Contradiction:

Improveimaging speedVSAvoidtissue parameter precision

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

The patent changes the fundamental parameters of the estimation approach by transitioning from linear estimation methods to non-linear optimization methods. This involves changing the mathematical model parameters and optimization criteria to achieve both speed and precision simultaneously, resolving the contradiction between fast imaging and accurate measurement.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If Monte Carlo methods are used for accurate tissue parameter assessment, then the measurement precision is high, but the processing time is too slow for real-time estimation

Engineering Contradiction:

Improvetissue parameter precisionVSAvoidprocessing speed

Core Design Contradiction:

Measurement precisionVSSpeed

Solution Approach 1:

The patent applies partial action by using a simplified version of the Monte Carlo method that captures the essential physics without the full computational complexity. This allows achieving sufficient measurement precision for surgical applications while reducing processing time to enable real-time imaging during surgery.

Inventive Principle:

Principle #16Partial or excessive action

3Loss of information

If existing multispectral imaging methods are used, then functional information can be detected, but the system cannot adapt to varying lighting conditions in surgical environments

Engineering Contradiction:

Improvefunctional information detectionVSAvoidadaptability to lighting conditions

Core Design Contradiction:

Loss of informationVSAdaptability or versatility

Solution Approach 1:

The patent introduces dynamic adaptation mechanisms that allow the imaging system to adjust to varying lighting conditions in real-time. This involves dynamic calibration and parameter adjustment based on the actual illumination environment, enabling the system to maintain measurement accuracy across different surgical lighting scenarios.

Inventive Principle:

Principle #15Dynamics

4Productivity

If real-time imaging at 25 Hz or above is implemented, then immediate feedback to the surgeon is provided, but motion artifacts and blurring increase

Engineering Contradiction:

Improvereal-time feedback rateVSAvoidimage quality reliability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent implements feedback mechanisms that use the high-rate imaging data to dynamically adjust exposure parameters and processing algorithms. This feedback loop allows the system to maintain high frame rates for immediate surgical feedback while compensating for motion effects through real-time parameter adjustment and image processing.

Inventive Principle:

Principle #23Feedback

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 the generation of real-time, high-resolution augmented images that provide immediate feedback to surgeons, reducing motion artifacts and improving precision in surgical procedures, even under varying lighting conditions.

Implementation Method 1

Since oxygen saturated hemoglobin and oxygen un-saturated hemoglobin have different light absorption properties depending on wavelength, oxygenation can in principle be determined by multispectral imaging

Methodology Applied

Scientific EffectLight absorption: Absorption (EM radiation)

Data Source

PatentUS12329491B2Method and system for augmented imaging in open treatment using multispectral information

Publication Date: 2025.06.17 DEUTES KREBSFORSCHUNGSZENT STIFTUNG DES OFFENTLICHEN RECHTS

AI summary

Disclosed herein is a method of generating augmented images of tissue of a patient undergoing open treatment, in particular open surgery, wherein each augmented image associates at least one tissue parameter with a region or pixel of the image of the tissue, said method comprising the following steps: estimating a spectral composition of light illuminating a region of interest of the tissue, obtaining one or more multispectral images of the region of interest, applying a machine learning based regressor or classifier to the one or more multispectral images, or an image derived from said multispectral image, to thereby derive one or more tissue parameters associated with image regions or pixels of the corresponding multispectral image, wherein said regressor or classifier has been trained to predict the one or more tissue parameters from a multispectral image under a given spectral composition of illumination, wherein the regressor or classifier employed is made to match the estimated spectral composition of light illuminating said region of interest of the tissue.