Computed Contrast-Enhanced MRI Using Native Quantitative Mapping

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional contrast-enhanced medical imaging techniques require invasive administration of contrast agents, which pose risks and complications, particularly in patients with kidney issues, and are cumbersome, limiting their clinical applicability and patient tolerability.

Innovation Solution

A method using machine learning processors trained on contrast-agent-free quantitative mapping images to predict computed contrast-enhanced medical images, eliminating the need for contrast agents by leveraging native quantitative mapping and image processing algorithms to mimic the appearance and sensitivity of contrast-enhanced images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If contrast agents are administered to enhance image differentiation and provide pharmacokinetic information, then diagnostic accuracy and tissue differentiation are improved, but patient safety deteriorates due to risks of nephrogenic systemic fibrosis and contrast-induced nephropathy

Engineering Contradiction:

Improvetissue differentiation accuracyVSAvoidpatient safety

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent creates a synthetic contrast-enhanced image that copies the appearance and diagnostic information of traditional contrast-enhanced images without using actual contrast agents. The generative adversarial network learns the mapping between native and contrast-enhanced images to produce realistic synthetic images that preserve diagnostic accuracy while eliminating contrast agent exposure

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces the physical-chemical mechanism of contrast agents with a computational mechanism using deep learning. Instead of relying on gadolinium-based agents to alter tissue signal properties, the system uses a generative adversarial network to computationally transform native images into contrast-enhanced images, substituting mechanical/chemical processes with information processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If contrast-enhanced imaging procedures are performed to improve diagnostic capability, then disease detection sensitivity is improved, but scan time increases to over 45 minutes making procedures cumbersome

Engineering Contradiction:

Improvedisease detection sensitivityVSAvoidscan procedure duration

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs the contrast enhancement transformation computationally and instantaneously after acquiring native images, eliminating the need for additional contrast agent administration and extended scanning. The generative adversarial network processes native images to produce synthetic contrast-enhanced images in real-time, condensing what would traditionally require separate scanning phases into a single rapid computation step

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates synthetic copies of contrast-enhanced images from native images, preserving diagnostic information while eliminating the time-consuming aspects of actual contrast agent administration and multi-phase scanning protocols

Inventive Principle:

Principle #26Copying

3Loss of information

If contrast agents are used to enhance image quality and provide pharmacokinetic information, then diagnostic information is improved, but patient tolerability deteriorates due to invasive cannulation and procedure complexity

Engineering Contradiction:

Improvepharmacokinetic informationVSAvoidpatient tolerability

Core Design Contradiction:

Loss of informationVSEase of operation

Solution Approach 1:

The patent replaces the invasive mechanical process of intravenous cannulation and contrast agent injection with a non-invasive computational process. The generative adversarial network extracts pharmacokinetic information and enhances images through algorithmic transformation of native images, eliminating needle insertion, contrast agent handling, and associated patient discomfort

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates synthetic images that copy the diagnostic value and pharmacokinetic information of contrast-enhanced imaging while removing the invasive administration process, making the procedure as simple as acquiring native images without any additional patient burden

Inventive Principle:

Principle #26Copying

Data Source

PatentUS12499524B2Enhancement of medical images

Publication Date: 2025.12.16 OXFORD UNIVERSITY INNOVATION LTD

AI summary

A method and apparatus for enhancing magnetic resonance images to produce contrast-enhanced images without the need to administer contrast agent to a patient. The image processing apparatus utilises a trained machine learning algorithm as an image processor, preferably a generative adversarial network, to produce images from contrast agent-free magnetic resonance images with the produced images having similar appearance and better image quality and better pathological sensitivity and being able to differentiate more pathological conditions than actually acquired contrast-enhanced images.