Deep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators

Abstract Accurate localisation of the first point of interaction (FPoI) of incident gamma photons in monolithic scintillators is crucial for many radiation-based imaging applications - in particular, accurate estimation of the lines of response in positron emission tomography (PET). This is particul...

Full description

Saved in:
Bibliographic Details
Main Authors: Mushen Shen, Ragy Abraham, Elise Cribbin, Harrison Gregor, Mitra Safavi-Naeini, Daniel Franklin
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-13339-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763788634456064
author Mushen Shen
Ragy Abraham
Elise Cribbin
Harrison Gregor
Mitra Safavi-Naeini
Daniel Franklin
author_facet Mushen Shen
Ragy Abraham
Elise Cribbin
Harrison Gregor
Mitra Safavi-Naeini
Daniel Franklin
author_sort Mushen Shen
collection DOAJ
description Abstract Accurate localisation of the first point of interaction (FPoI) of incident gamma photons in monolithic scintillators is crucial for many radiation-based imaging applications - in particular, accurate estimation of the lines of response in positron emission tomography (PET). This is particularly challenging in thick nanocomposite and ceramic scintillator materials, which exhibit high levels of Rayleigh scattering compared to monocrystalline scintillators. In this work, we evaluate deep neural network-based approaches for (1) classifying the mode of photon interaction using an InceptionNet-based classifier and (2) accurately estimating the location of the FPoI based on scintillation photon distributions in several monolithic nanocomposite and ceramic scintillators using both CNN- and InceptionNet-based regression networks. The classifier was able to correctly categorise single-energy deposition events with an accuracy $$\ge$$  90.1%, two-deposition interactions with an accuracy $$\ge$$  77.6% and three-plus deposition interactions with an accuracy $$\ge$$  66.7%. Across the evaluated materials, median total localisation error ranged from 0.58 mm to 2.91 mm with the CNN and 0.59 mm to 2.10 mm with InceptionNet, assuming 50% detector quantum efficiency. Localisation in nanocomposites using the InceptionNet-based regression network improved the most relative to previously-reported results based on classical techniques, in some cases approaching the accuracy achieved with ceramic scintillators.
format Article
id doaj-art-19cbaeb905b34b2e8aae902a08d8ff61
institution DOAJ
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-19cbaeb905b34b2e8aae902a08d8ff612025-08-20T03:05:18ZengNature PortfolioScientific Reports2045-23222025-08-0115111410.1038/s41598-025-13339-yDeep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillatorsMushen Shen0Ragy Abraham1Elise Cribbin2Harrison Gregor3Mitra Safavi-Naeini4Daniel Franklin5School of Electrical and Data Engineering, University of Technology SydneySchool of Electrical and Data Engineering, University of Technology SydneySchool of Electrical and Data Engineering, University of Technology SydneySchool of Electrical and Data Engineering, University of Technology SydneyAustralian Nuclear Science and Technology Organisation (ANSTO)School of Electrical and Data Engineering, University of Technology SydneyAbstract Accurate localisation of the first point of interaction (FPoI) of incident gamma photons in monolithic scintillators is crucial for many radiation-based imaging applications - in particular, accurate estimation of the lines of response in positron emission tomography (PET). This is particularly challenging in thick nanocomposite and ceramic scintillator materials, which exhibit high levels of Rayleigh scattering compared to monocrystalline scintillators. In this work, we evaluate deep neural network-based approaches for (1) classifying the mode of photon interaction using an InceptionNet-based classifier and (2) accurately estimating the location of the FPoI based on scintillation photon distributions in several monolithic nanocomposite and ceramic scintillators using both CNN- and InceptionNet-based regression networks. The classifier was able to correctly categorise single-energy deposition events with an accuracy $$\ge$$  90.1%, two-deposition interactions with an accuracy $$\ge$$  77.6% and three-plus deposition interactions with an accuracy $$\ge$$  66.7%. Across the evaluated materials, median total localisation error ranged from 0.58 mm to 2.91 mm with the CNN and 0.59 mm to 2.10 mm with InceptionNet, assuming 50% detector quantum efficiency. Localisation in nanocomposites using the InceptionNet-based regression network improved the most relative to previously-reported results based on classical techniques, in some cases approaching the accuracy achieved with ceramic scintillators.https://doi.org/10.1038/s41598-025-13339-y
spellingShingle Mushen Shen
Ragy Abraham
Elise Cribbin
Harrison Gregor
Mitra Safavi-Naeini
Daniel Franklin
Deep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators
Scientific Reports
title Deep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators
title_full Deep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators
title_fullStr Deep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators
title_full_unstemmed Deep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators
title_short Deep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators
title_sort deep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators
url https://doi.org/10.1038/s41598-025-13339-y
work_keys_str_mv AT mushenshen deeplearningbasedlocalisationandclassificationofgammaphotoninteractionsinthicknanocompositeandceramicmonolithicscintillators
AT ragyabraham deeplearningbasedlocalisationandclassificationofgammaphotoninteractionsinthicknanocompositeandceramicmonolithicscintillators
AT elisecribbin deeplearningbasedlocalisationandclassificationofgammaphotoninteractionsinthicknanocompositeandceramicmonolithicscintillators
AT harrisongregor deeplearningbasedlocalisationandclassificationofgammaphotoninteractionsinthicknanocompositeandceramicmonolithicscintillators
AT mitrasafavinaeini deeplearningbasedlocalisationandclassificationofgammaphotoninteractionsinthicknanocompositeandceramicmonolithicscintillators
AT danielfranklin deeplearningbasedlocalisationandclassificationofgammaphotoninteractionsinthicknanocompositeandceramicmonolithicscintillators