Positron emission particle tracking using machine learning

Andrei Nicusan; Christopher Windows-Yule

doi:10.1063/1.5129251

Positron emission particle tracking using machine learning

Andrei Nicusan, Christopher Windows-Yule

Chemical Engineering

Research output: Contribution to journal › Article › peer-review

8 Citations (Scopus)

761 Downloads (Pure)

Abstract

We introduce a new approach to positron emission particle tracking (PEPT) based on machine learning algorithms, demonstrating novel methods for particle location, tracking and trajectory separation.
The method allows radioactively-labelled particles to be located, in three-dimensional space, with high temporal and spatial resolution, requiring no prior knowledge of the number of tracers within the system, and can successfully distinguish multiple particles separated by distances as small as 2 mm. The technique's spatial resolution is observed to be invariant with the number of tracers used, allowing large numbers of particles to be tracked simultaneously, with no loss of data quality.

Original language	English
Article number	013329
Number of pages	15
Journal	Review of Scientific Instruments
Volume	91
Issue number	1
DOIs	https://doi.org/10.1063/1.5129251
Publication status	Published - 24 Jan 2020

ASJC Scopus subject areas

Instrumentation

Access to Document

10.1063/1.5129251Licence: None: All rights reserved

Nicusan_&_Windows_Yule_Positron_emission_particle_tracking_using_machine_learning_Review_of_Scientific_Instruments_2019
This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Nicuşan, A.L. and Windows-Yule, C.R.K., 2020. Positron emission particle tracking using machine learning. Review of Scientific Instruments, 91(1), p.013329, and may be found at: https://doi.org/10.1063/1.5129251.
Accepted author manuscript, 3.36 MBLicence: None: All rights reserved
Nicusan_&_Windows_Yule_Positron_emission_particle_tracking_using_machine_learning_Review_of_Scientific_Instruments_2019
This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Nicuşan, A.L. and Windows-Yule, C.R.K., 2020. Positron emission particle tracking using machine learning. Review of Scientific Instruments, 91(1), p.013329, and may be found at: https://doi.org/10.1063/1.5129251.
Final published version, 12 MBLicence: None: All rights reserved

Cite this

@article{ab2442ad4f584e50a008d198f176b1cf,

title = "Positron emission particle tracking using machine learning",

abstract = "We introduce a new approach to positron emission particle tracking (PEPT) based on machine learning algorithms, demonstrating novel methods for particle location, tracking and trajectory separation.The method allows radioactively-labelled particles to be located, in three-dimensional space, with high temporal and spatial resolution, requiring no prior knowledge of the number of tracers within the system, and can successfully distinguish multiple particles separated by distances as small as 2 mm. The technique's spatial resolution is observed to be invariant with the number of tracers used, allowing large numbers of particles to be tracked simultaneously, with no loss of data quality.",

author = "Andrei Nicusan and Christopher Windows-Yule",

year = "2020",

month = jan,

day = "24",

doi = "10.1063/1.5129251",

language = "English",

volume = "91",

journal = "Review of Scientific Instruments",

issn = "0034-6748",

publisher = "American Institute of Physics",

number = "1",

}

TY - JOUR

T1 - Positron emission particle tracking using machine learning

AU - Nicusan, Andrei

AU - Windows-Yule, Christopher

PY - 2020/1/24

Y1 - 2020/1/24

N2 - We introduce a new approach to positron emission particle tracking (PEPT) based on machine learning algorithms, demonstrating novel methods for particle location, tracking and trajectory separation.The method allows radioactively-labelled particles to be located, in three-dimensional space, with high temporal and spatial resolution, requiring no prior knowledge of the number of tracers within the system, and can successfully distinguish multiple particles separated by distances as small as 2 mm. The technique's spatial resolution is observed to be invariant with the number of tracers used, allowing large numbers of particles to be tracked simultaneously, with no loss of data quality.

AB - We introduce a new approach to positron emission particle tracking (PEPT) based on machine learning algorithms, demonstrating novel methods for particle location, tracking and trajectory separation.The method allows radioactively-labelled particles to be located, in three-dimensional space, with high temporal and spatial resolution, requiring no prior knowledge of the number of tracers within the system, and can successfully distinguish multiple particles separated by distances as small as 2 mm. The technique's spatial resolution is observed to be invariant with the number of tracers used, allowing large numbers of particles to be tracked simultaneously, with no loss of data quality.

UR - http://www.scopus.com/inward/record.url?scp=85078525316&partnerID=8YFLogxK

U2 - 10.1063/1.5129251

DO - 10.1063/1.5129251

M3 - Article

SN - 0034-6748

VL - 91

JO - Review of Scientific Instruments

JF - Review of Scientific Instruments

IS - 1

M1 - 013329

ER -

Positron emission particle tracking using machine learning

Abstract

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this