Mechanical Tissue Characterization from Imaging Data Without Excitation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing non-invasive methods for determining mechanical tissue characteristics, such as classical elastography, are inadequate for assessing the risk of osteoarthritis in stiff tissues like cartilage due to limited mechanical excitations, and invasive methods carry surgical risks.

Innovation Solution

A system using in-vivo imaging and a machine learning architecture to determine mechanical tissue characteristics based on image features indicative of structural properties, without requiring mechanical excitations, allowing for accurate assessment of tissue state.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If classical elastography is used for non-invasive imaging, then the procedure is non-invasive and avoids surgical risks, but the mechanical excitations are insufficient for stiff tissues like cartilage leading to inadequate information

Engineering Contradiction:

Improveaccuracy of mechanical tissue characteristic determinationVSAvoidinsufficient mechanical excitation for stiff tissues

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the mechanical excitation system of classical elastography with a machine learning-based prediction system. Instead of using sound waves to mechanically excite the tissue and measure the response, the system uses imaging data (such as MRI images showing structural properties) as input to a trained machine learning model that predicts mechanical tissue characteristics. This substitution eliminates the need for mechanical excitation while providing accurate mechanical property assessment for stiff tissues like cartilage.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If invasive mechanical probing such as arthroscopy is performed, then accurate mechanical tissue characteristics can be obtained, but surgical and anesthetic risks are introduced

Engineering Contradiction:

Improveaccuracy of mechanical tissue characteristic determinationVSAvoidsurgical and anesthetic complications

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent replaces invasive mechanical probing systems with a non-invasive imaging and machine learning prediction system. Instead of physically inserting instruments into the body to mechanically probe the tissue, the system uses external imaging modalities to capture structural properties and feeds these images into a machine learning model trained on paired imaging-mechanical data. This approach achieves measurement precision comparable to invasive methods while completely avoiding surgical and anesthetic risks.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a virtual model or copy of the mechanical tissue characteristics through machine learning prediction, based on imaging data that captures the tissue's structural properties. The machine learning model learns the mapping between imaging features and mechanical properties from training data, then uses this learned relationship to predict mechanical characteristics without physical contact. This virtual copying approach provides accurate mechanical information while maintaining non-invasiveness.

Inventive Principle:

Principle #26Copying

3Loss of information

If mechanical examinations are performed to determine tissue state, then mechanical tissue characteristics can be assessed, but invasive procedures are required

Engineering Contradiction:

Improvecompleteness of tissue state informationVSAvoidinvasiveness of the procedure

Core Design Contradiction:

Loss of informationVSEase of operation

Solution Approach 1:

The patent replaces invasive mechanical examination systems with a non-invasive imaging and computational prediction system. The system captures comprehensive tissue state information through imaging modalities that visualize structural properties, then uses machine learning to translate these visual features into mechanical tissue characteristics. This substitution maintains the completeness of tissue state information while eliminating the need for invasive procedures, making the assessment easier and safer to perform.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12423811B2System for determing mechanical tissue characteristics from imaging data

Publication Date: 2025.09.23 HELMHOLTZ ZENTRUM HEREON GMBH

AI summary

A system and methods for determining a mechanical tissue characteristic (Ψ) are provided. The system comprises a providing unit for providing a set of images of a tissue region of interest, wherein the provided set of images comprises image features indicative of one or more structural properties (α, a0, CO, PG) of the tissue region of interest and has been acquired using an imaging modality suitable for in-vivo imaging of the tissue region of interest. The system further comprises a determining unit for determining, based on the provided set of images, a mechanical tissue characteristic (Ψ) indicative of a mechanical responsiveness of the tissue region of interest. The determining unit comprises a machine learning architecture adapted to receive the provided set of images as an input and to provide the mechanical tissue characteristic as an output.