# US 2023/0058112 A1 · Machine learning-based scintillator resonse modelling for increased spatial resolution in nuclear imaging

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0058112 A1
- Document ID: US20230058112A1
- Status: Published application
- Kind: A1
- Application number: 17/782,942
- Filed: 2020-12-03
- Published: 2023-02-23
- Earliest claimed: 2019-12-11
- Assignees: Koninklijke Philips N.V.
- Applicants: Koninklijke Philips N.V.
- Inventors: Andre Frank SALOMON
- Web page: https://patentgrep.com/patent/US20230058112A1

## CPC

- G01T 1/161: Applications in the field of nuclear medicine, e.g. in vivo counting {(apparatus for radiation diagnosis A61B6/00)}
- G01T 1/17: Circuit arrangements not adapted to a particular type of detector {(pulse-selection circuits H03K, G01R)}
- G01T 1/20: with scintillation detectors
- G06N 20/00: Machine learning
- G01T: MEASUREMENT OF NUCLEAR OR X-RADIATION (radiation analysis of materials, mass spectrometry G01N23/00; tubes for determining the presence, intensity, density or energy of radiation or particles H01J47/00)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system (PP) and related methods for supporting nuclear imaging such as PET or other. The system comprises an input interface (IN) for receiving event data that represents an interaction event of gamma-radiation with a pixelated scintillator (SC) of a nuclear imaging apparatus (NIA). A pre-trained machine learning component (MLC) estimates a point spread function, PSF, for the said event. An output interface (OUT) outputs a representation of the PSF. The PSF may be used in emission image reconstruction for improved spatial resolution.

## Claims

### Claim 1

System (PP) for supporting nuclear imaging, comprising:
an input interface (IN) for receiving event data that represents an interaction of gamma-radiation with a pixelated scintillator (SC) of a nuclear imaging apparatus (NIA);
a pre-trained machine learning component (MLC) for estimating a point spread function, PSF, for the said event;
an output interface (OUT) for outputting a representation of the PSF.

### Claim 2 (depends on 1)

System of claim 1, comprising a reconstruction module (RECON) operable to implement a reconstruction algorithm to reconstruct from plural such event data and their estimated PSFs, an emission image.

### Claim 3 (depends on 1)

System of claim 1, wherein the pre-trained machine learning component includes a neural network model (M).

### Claim 4 (depends on 1)

System of claim 1, wherein said event data includes least one observable (O) that represents in-scintillator interaction of a gamma radiation.

### Claim 5 (depends on 1)

System of claim 1, wherein the PSF representation includes a probability distribution.

### Claim 6 (depends on 1)

System of claim 1, wherein the reconstruction algorithm includes tube-of-response modelling based on the PSF.

### Claim 7 (depends on 1)

A nuclear imaging arrangement (NIR) comprising:
system (PP) of claim 1;
the nuclear imaging apparatus (NIA) having the pixelated scintillator.

### Claim 8

System (TS) for training a machine-learning component for supporting nuclear imaging, comprising:
input interface (IN) for receiving training input event data representative of gamma-radiation interaction with scintillator material;
a tester (TT) for applying the training input event data to a machine learning model to obtain training output data;
an updater (UD) configured to update one or more parameters of the model based on a deviation between the training output data and a target associated with the input event data, the target representing an expected PSF.

### Claim 9 (depends on 8)

System of claim 8, the training input event data previously obtained, based on measurement or simulation.

### Claim 10 (depends on 9)

System of claim 9, wherein the simulation is based on a Monte-Carlo-simulation algorithm.

### Claim 11

Method for supporting nuclear imaging, comprising:
receiving event data that represents an interaction of gamma-radiation with a pixelated scintillator (SC) of a nuclear imaging apparatus (NIA);
estimating, based on a pre-trained machine learning component (MLC), a point spread function, PSF for the said event;
outputting a representation of the PSF.

### Claim 12

Method of training a machine-learning component for supporting nuclear imaging, comprising:
receiving training input event data representative of gamma-radiation interaction with pixelated scintillator material;
applying the training input event data to a machine learning model to obtain training output data;
adjusting one or more parameters of the model based on a deviation between the training output data and a target associated with the input event data, the target representing an expected PSF.

### Claim 13

Method of generating training data for training a machine-learning component for supporting nuclear imaging, comprising:
simulating gamma photon versus scintillator interactions to obtain, for a set of prescribed locations (P=pi) of first gamma-phono versus pixelated scintillator interaction, instances of an observable (Oi); and
estimating, based on a given one of the said instances (Oi), a distribution of said prescribed locations (P=pi) to obtain a representation of a PSF for the given one of said instance.

### Claim 14 (depends on 11)

A computer program element, which, when being executed by at least one processing unit (PU), is adapted to cause the processing unit (PU) to perform the method as per claim 11.

### Claim 15 (depends on 14)

At least one computer readable medium having stored thereon the program element of claim 14.
