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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |