Automated CT Image Analysis for Myocardium Perfusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for analyzing time-series dynamic images of the heart, such as those used in myocardium perfusion assessments, are subjective and prone to variability among analysts due to manual setting of regions of interest (ROI), leading to ambiguous results and a lack of objectivity.

Innovation Solution

An automated computer program analyzes time-series CT images by determining intra-organ pixel positions and changes in CT values over time, using function approximation to calculate arrival times and base values without manual ROI setting, enabling objective and detailed analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual ROI setting is used for analyzing time-series dynamic images, then the analysis can be performed with existing methods, but the results are subjective and show variability among analysts

Engineering Contradiction:
Improveanalysis objectivityVSAvoidmanual operation requirement
Core Design Contradiction:
Measurement precisionVSExtent of automation

Solution Approach 1:

The system automatically identifies and sets ROIs by detecting contrast medium arrival patterns in the images themselves, without requiring manual intervention. The computer program autonomously analyzes the time-series images to determine optimal ROI positions based on the physiological data contained within the images.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The manual mechanical process of ROI setting by analysts is replaced with an automated computational system that uses image processing algorithms to objectively determine ROI positions and perform the analysis.

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

2Measurement precision

If multiple different inspections are performed for coronary stenosis assessment and myocardium ischemia assessment, then diagnostic accuracy is improved, but the time required and medical staff resources increase

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidinspection time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent combines coronary stenosis assessment and myocardium ischemia assessment into a single integrated inspection process. By simultaneously analyzing contrast medium arrival patterns, the system evaluates both the coronary arteries and myocardial perfusion in one examination, eliminating the need for separate inspections.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The image analysis system performs multiple diagnostic functions simultaneously - assessing coronary stenosis, evaluating myocardium perfusion, and detecting ischemia - all from the same set of time-series images, making the inspection method multi-functional and highly efficient.

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

Data Source

PatentEP3170454B1Computer program, and image processing device and method
Publication Date: 2020.05.20 FUJIFILM RI PHARMA CO LTD
  • EP3170454B1 patent drawingFigure 1
  • EP3170454B1 patent drawingFigure 2
  • EP3170454B1 patent drawingFigure 3(A)~3(B)

AI summary

An analysis method is provided that ensures objective and quantitative analysis for analyzing time-series images. For implementing the method, are provided an image data storage unit 11 that stores therein image data on a plurality of time-series computed tomography (CT) images of an organ of a subject captured after a contrast medium has been administered; a target pixel extraction unit 31 configured to extract an intra-organ pixel position, which is a position of a pixel in a region of the organ; a change-over-time determining unit 33 configured to determine a change-over-time of a CT value of the pixel at the determined intra-organ pixel position, based on image data on the time series CT images in the plurality of frames; and a function approximation processing unit 37 configured to determine an arrival time at which the contrast medium has arrived at an organ at the intra-organ pixel position and a base value, which is a CT value serving as a base of the pixel at the intra-organ pixel position, based on the determined change-over-time.