Personalized CT Contrast Injection With Deep Learning Enhancement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional contrast imaging technologies in CT scans rely heavily on large amounts of contrast medium, leading to side effects due to the medium's distinct physical properties from body fluids, and there is a need for improved control over the injection amount to minimize these effects while maintaining diagnostic accuracy.

Innovation Solution

An optimization system using deep learning to personalize contrast medium injection based on patient-specific drug and body information, adjusting the injection amount and speed to achieve optimal pharmacokinetic characteristics, and amplifying contrast components in medical images through a deep learning model.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a large amount of contrast medium is injected to amplify the contrast of the CT image, then the contrast quality is improved, but the side effects increase due to the distinct physical properties of the medium from body fluids

Engineering Contradiction:
Improvecontrast qualityVSAvoidside effects
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent applies parameter changes by optimizing the injection amount and speed of contrast medium based on individual patient characteristics (body weight, body surface area, organ volume) and drug properties (concentration, pharmacokinetics). This personalized approach allows achieving adequate contrast quality while minimizing the total amount of contrast medium injected, thereby reducing side effects.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system performs preliminary calculations of the optimal injection protocol before the actual CT scan. By pre-determining the injection amount and speed based on patient-specific parameters and contrast medium characteristics, the system ensures that the minimum necessary amount of contrast medium is used to achieve the required diagnostic quality, thus preventing excessive exposure to harmful substances.

Inventive Principle:
Principle #10Preliminary action

2Object-affected harmful factors

If the injection amount of contrast medium is reduced to minimize side effects, then the harmful factors are decreased, but the contrast quality may deteriorate

Engineering Contradiction:
Improveside effectsVSAvoidcontrast quality
Core Design Contradiction:
Object-affected harmful factorsVSMeasurement precision

Solution Approach 1:

The patent implements dynamic adjustment of injection parameters (amount and speed) based on real-time patient characteristics and contrast medium properties. The system dynamically optimizes the injection protocol to deliver the precise amount needed for high-quality contrast imaging without excess, thereby maintaining diagnostic quality while minimizing side effects.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system uses feedback mechanisms by continuously monitoring patient-specific parameters (body composition, organ volume) and contrast medium characteristics to adjust the injection protocol. This feedback-driven approach ensures that the injection amount is precisely controlled to achieve adequate contrast enhancement while avoiding over-injection and associated side effects.

Inventive Principle:
Principle #23Feedback

3Manufacturing precision

If a personalized injection protocol is implemented based on patient-specific information, then the optimization precision is improved, but the system complexity increases

Engineering Contradiction:
Improveinjection optimization precisionVSAvoidsystem complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent applies universality by developing an integrated system that combines multiple functions: patient parameter input, body composition analysis, pharmacokinetic modeling, injection protocol calculation, and real-time monitoring. This multi-functional system handles diverse patient characteristics and contrast medium types through a unified approach, achieving personalized optimization without requiring separate complex systems for each function.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system introduces an intermediary computational layer that processes patient-specific information and contrast medium characteristics to generate optimized injection protocols. This intermediary layer acts as a mediator between patient data and injection control, translating complex parameters into practical injection settings while maintaining precision and reducing overall system complexity through centralized intelligence.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4205656B1Optimization system for personalized contrast scan based on deep learning
Publication Date: 2025.12.17 CLARIPI INC
  • EP4205656B1 patent drawingFigure 1
  • EP4205656B1 patent drawingFigure 2
  • EP4205656B1 patent drawingFigure 3

AI summary

Disclosed are an optimization method and system for a personalized contrast scan based on deep learning, in which a contrast medium optimized for each individual patient is injected to implement optimum pharmacokinetic characteristics in a process of acquiring a medical image, the method including: obtaining drug information of a contrast medium and body information of a patient, in a contrast enhanced computed tomography (CT) scan; generating injection information of the drug to be injected into the patient by a predefined algorithm based on the drug information and the body information; injecting the drug into the patient based on the injection information, and acquiring a medical image by scanning the patient; and amplifying a contrast component in the medical image by inputting the medical image to a deep learning model trained in advance.