PET Signal Reconstruction Through Segment-Specific Model Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing signal reconstruction methods in PET rely on intuitive selection of fitting models based on scatter plots, leading to inaccurate reconstruction results due to difficulty in measuring scatter point dispersion, affecting precision.

Innovation Solution

Segment the signal based on characteristic information, apply multiple fitting models to signal segments, and determine a final fitting model by comparing fitted parameter values with measurement values to select the most accurate model for each segment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple fitting models are applied to signal segments, then the accuracy of signal reconstruction is improved, but the device complexity increases

Engineering Contradiction:
Improveaccuracy of signal reconstructionVSAvoidcomplexity of fitting model selection
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The signal is divided into multiple signal segments based on characteristic information such as amplitude, rising time, and falling time. Different fitting models are applied to different segments, allowing the system to capture the varying characteristics of the signal across different phases while maintaining manageable complexity through localized model application.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically selects the most appropriate fitting model for each signal segment by comparing fitted parameter values with measurement values. This dynamic selection process adapts to the specific characteristics of each segment, optimizing accuracy without requiring a single complex model for the entire signal.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If multiple fitting models are applied to signal segments, then the precision of signal reconstruction is improved, but the computation time increases

Engineering Contradiction:
Improveprecision of signal reconstructionVSAvoidcomputation time for model selection
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

By segmenting the signal and applying fitting models only to specific segments rather than the entire signal, the computation time is reduced while maintaining precision where it matters most. The segmentation allows focused computational resources on critical signal portions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system applies multiple fitting models only where necessary - specifically to signal segments where characteristic information indicates variability or importance - rather than uniformly across the entire signal. This partial application of multiple models reduces overall computation time while preserving reconstruction precision in critical areas.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3795085B1Method for determining signal fitting mode, reconstruction method, and device
Publication Date: 2025.09.24 RAYCAN TECH CO LTD SU ZHOU
  • EP3795085B1 patent drawingFigure 1(a)~1(c)
  • EP3795085B1 patent drawingFigure 2~3(b)
  • EP3795085B1 patent drawingFigure 3(c)~3(e)

AI summary

The disclosure discloses methods for determining fitting model for a signal, reconstructing a signal and devices thereof. The determination method may comprise the following steps: segmenting a sampled signal based on collected characteristic information of the signal to obtain a plurality of signal segments; fitting sampling points in the plurality of signal segments using a plurality of fitting models; acquiring fitted values for a parameter of interest in each signal segment based on fitting results; comparing each of the fitted values for the parameter of interest under each of the fitting models with an acquired measurement value for the parameter of interest, and determining a final fitting model for reconstructing the signal among the plurality of the fitting models based on comparison results. In the technical solution provided in the disclosure, the accuracy of the signal reconstruction result and precision of the signal reconstruction may be improved.