Tracer Classification Model for ECT Scan Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In emission computed tomography (ECT) scans, accurately determining the type of tracer used is crucial for improving image reconstruction quality, but existing methods lack efficiency and accuracy in classifying tracers based on scan data.

Innovation Solution

A method and system utilizing a trained machine learning model to classify tracers by processing imaging data from ECT scans, enabling quick and accurate determination of tracer classification information, which can then be used to adjust scan protocols and reconstruction parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional manual methods are used to determine tracer type, then operator control is maintained, but accuracy and efficiency of tracer classification deteriorate

Engineering Contradiction:

Improvetracer classification accuracyVSAvoidclassification efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual operator analysis with an automated machine learning system that processes ECT scan data. The system uses trained models to automatically classify tracer types based on imaging data, eliminating the need for manual interpretation while improving both accuracy and efficiency of tracer identification.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Speed

If tracer classification is performed manually, then flexibility in handling diverse cases is maintained, but time consumption and processing speed increase

Engineering Contradiction:

Improveclassification speedVSAvoidsystem complexity

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically classifying tracers without requiring operator intervention. The machine learning model independently analyzes ECT scan data and determines tracer types, freeing operators from manual classification tasks while maintaining consistent and rapid processing across all cases.

Inventive Principle:

Principle #25Self-service

3Reliability

If no automated classification system is used, then system simplicity is maintained, but image reconstruction quality and data utilization deteriorate

Engineering Contradiction:

Improveimage reconstruction qualityVSAvoidautomation level

Core Design Contradiction:

ReliabilityVSExtent of automation

Solution Approach 1:

The system performs preliminary classification of tracer types before image reconstruction occurs. By automatically identifying the tracer type from ECT scan data first, the system enables subsequent reconstruction processes to be optimized for the specific tracer being used, thereby improving reconstruction quality and data utilization.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20230380778A1Methods, systems, devices, and storage media for tracer classification

Publication Date: 2023.11.30 SHANGHAI UNITED IMAGING HEALTHCARE

AI summary

The embodiments of the present disclosure provide a method for classifying a tracer, a system and a device, and a storage medium. The method for classifying the tracer comprises obtaining imaging data related to an emission computed tomography (ECT) scan of a target object, the target object being injected with a tracer during the ECT scan; and determining classification information of the tracer by processing the imaging data using a tracer classification model, the tracer classification model being a trained machine learning model.