Dynamic PET-MRI Co-Registration for Seizure Focus Localization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current PET procedures have limitations in accurately localizing seizure foci in patients with nonlesional focal epilepsy, particularly when MRI is normal and discordant with other data, leading to less favorable surgical outcomes.

Innovation Solution

A method and system for dynamic positron emission tomography (PET) that includes continuous volumetric radioactive measurement, motion correction, co-registration with MRI, and application of a model-corrected input function (MCIF) using an artificial neural network (ANN) to enhance localization of seizure foci.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If standard PET procedures are used for localization, then the procedure is simple and quick, but the measurement precision and reliability of seizure focus identification deteriorates

Engineering Contradiction:

Improveseizure focus localization precisionVSAvoidPET procedure complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The PET procedure is segmented into multiple discrete processing stages: motion correction of volumetric data, co-registration with MRI scans, and application of MCIF via neural networks. Each segment addresses specific sources of error independently, allowing the system to achieve high precision without requiring complete procedural redesign.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Motion correction is performed as a preliminary step before co-registration and analysis. By correcting motion artifacts in advance, the system prevents degradation of localization precision that would occur if motion were addressed later in the workflow.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If dynamic PET with motion correction and co-registration is implemented, then the seizure focus identification accuracy improves, but the processing time and computational complexity increase

Engineering Contradiction:

Improveseizure focus identification reliabilityVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual or mechanical processing steps with automated computational methods. Neural networks automatically perform MCIF application and co-registration, substituting time-consuming manual operations with faster algorithmic processing that maintains or improves reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transforms static PET data into dynamic parametric maps by changing the temporal parameter dimension. This allows extraction of kinetic parameters that improve reliability while the automated computation manages the time cost through efficient parameter estimation.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If volumetric radioactive measurement data is collected over multiple scanning intervals, then the quantification precision improves, but the scanning duration and patient exposure time increase

Engineering Contradiction:

Improvetracer uptake quantification precisionVSAvoidscanning duration

Core Design Contradiction:

Measurement precisionVSDuration of action of moving object

Solution Approach 1:

The neural network application of MCIF processes the volumetric data to extract essential kinetic information without requiring complete analysis of all temporal details. This partial action approach achieves sufficient quantification precision while reducing the effective processing time compared to exhaustive analysis methods.

Inventive Principle:

Principle #16Partial or excessive action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Improves the noninvasive identification of seizure foci by providing high-resolution parametric quantification, expanding the number of candidates for transformative surgery.

Implementation Method 1

collecting volumetric radioactive measurement data associated with an administered radioactive tracer

Methodology Applied

Scientific EffectRadioactive decay: Radioactive Decay

Implementation Method 2

capturing a magnetic resonance image of the target site

Methodology Applied

Scientific EffectMagnetic resonance:

Data Source

PatentUS12564359B2Systems, methods, and computer readable mediums for performing dynamic positron emission tomography

Publication Date: 2026.03.03 UNIV OF VIRGINIA PATENT FOUND

AI summary

A method for performing dynamic positron emission tomography (PET) is disclosed. The method includes collecting volumetric radioactive measurement data associated with an administered radioactive tracer present in a target site of a subject over multiple scanning intervals, capturing a magnetic resonance image of the target site, and performing a motion correction process to the volumetric radioactive measurement data to produce motion corrected PET data. The method further includes co-registering the magnetic resonance image and motion corrected data to generate a co-registered dynamic PET volume, and applying a model corrected input function (MCIF) to the co-registered dynamic PET volume to calibrate an uptake amount of the radioactive tracer in the target site.