AI Catheter Placement Verification with Patient Coordinate System

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Medical personnel face challenges in visualizing and confirming the proper placement of central venous access catheters (CVCs) and pulmonary artery catheters (PACs), including difficulties in identifying complications, due to limitations in existing imaging systems and the need for precise measurements that account for patient size and orientation.

Innovation Solution

A medical image processing system utilizing Deep Learning (DL) technology to detect and visualize CVCs and PACs, providing a patient-specific coordinate system for accurate placement verification, detection of complications, and real-time alerts for improper placement or complications, while allowing for measurement in patient-specific units.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual assessment and measurement are performed by medical personnel, then flexibility in evaluating placement can be maintained, but time consumption increases and productivity decreases

Engineering Contradiction:
Improveflexibility in evaluationVSAvoidtime consumption
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The system performs self-service by automatically detecting the catheter, calculating placement accuracy, and generating reports without requiring manual measurement and assessment by medical personnel. The AI system independently completes the evaluation process that previously required human intervention, thereby reducing time consumption while maintaining evaluation flexibility through automated adaptive algorithms.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual measurement and visual assessment process with an automated AI-based system. The machine learning model automatically identifies catheter positions, calculates distances in patient-specific units, and determines placement accuracy, substituting the manual mechanical process with an automated computational system that is both faster and equally flexible.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If standard measurement units are used for catheter placement, then simplicity in measurement is maintained, but accuracy decreases when accounting for patient size and orientation variations

Engineering Contradiction:
Improvemeasurement system simplicityVSAvoidplacement accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The system dynamically changes the measurement parameters by calculating distances in patient-specific units rather than using fixed standard units. The AI system adapts the measurement scale and orientation parameters to match each patient's anatomical characteristics, thereby maintaining simplicity in the measurement process while achieving high precision through personalized parameter adjustment.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent applies local quality by tailoring the measurement and evaluation parameters to each specific patient's anatomical characteristics. Instead of using uniform standard measurements, the system creates patient-specific measurement frameworks that account for individual variations in size, orientation, and anatomy, thereby improving precision without complicating the overall system architecture.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If comprehensive complication detection is implemented, then diagnostic accuracy improves, but system complexity increases

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system achieves multi-functionality by using a single unified AI-based platform that simultaneously performs catheter detection, placement accuracy assessment, and complication identification. Rather than requiring separate specialized systems for each function, the patent integrates multiple diagnostic capabilities into one universal system, thereby improving diagnostic accuracy without proportionally increasing system complexity.

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

Solution Approach 2:

The patent merges the functions of catheter detection, measurement, placement evaluation, and complication screening into a single integrated AI system. By combining these previously separate diagnostic tasks into one unified platform, the system achieves comprehensive diagnostic accuracy while avoiding the cumulative complexity that would result from multiple separate systems.

Inventive Principle:
Principle #5Merging (Combining)

4Reliability

If real-time placement verification is provided, then patient safety improves, but computational resources and processing time increase

Engineering Contradiction:
Improvepatient safetyVSAvoidcomputational resource consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary action by pre-processing and analyzing the entire catheter path and surrounding anatomy before final placement verification. The AI model proactively identifies potential complications and placement issues in advance, allowing for real-time safety verification without requiring excessive computational resources at the moment of final assessment, thereby improving patient safety while managing energy consumption.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4374792A1Artificial intelligence system and method for defining and visualizing placement of a catheter with patient coordinate system
Publication Date: 2024.05.29 GE PRECISION HEALTHCARE LLC
  • EP4374792A1 patent drawingFigure 1~3
  • EP4374792A1 patent drawingFigure 4
  • EP4374792A1 patent drawingFigure 5

AI summary

An image processing system (1300) and method is provided. The image processing system (1300) includes a display (1324), a processor (1312), and a memory (1313). The memory (1313) stores processor-executable code (220) that when executed by the processor (1312) causes receiving an image (1701) of a region of interest of a patient with a medical catheter, tube or line (1705) disposed within the region of interest, detecting the medical tube or line (1705) within the image (1701), generating a patient coordinate system (1700) relative to an anatomy of the patient within the image (1701), generating a combined image(1702) by superimposing a first graphical marker (1734) on the image (1701) that indicates an end (1707) of the medical catheter, tube or line (1705), and a second graphical marker (1736) on the image (1701) that indicates patient coordinate system (1700), and displaying the combined image (1702) on the display. In addition, the system (1300) assesses common visualizable complications associated with CVC placement, including but not limited to hydrothorax, pneumothorax, pneumomediastinum and CVC position changes between x-rays taken at different times.