Investigating particle track topology for range telescopes in particle radiography using convolutional neural networks.
Monte Carlo simulation
Proton computed tomography
convolutional neural network
machine learning
secondary particles
track reconstruction
Journal
Acta oncologica (Stockholm, Sweden)
ISSN: 1651-226X
Titre abrégé: Acta Oncol
Pays: England
ID NLM: 8709065
Informations de publication
Date de publication:
Nov 2021
Nov 2021
Historique:
pubmed:
15
7
2021
medline:
15
10
2021
entrez:
14
7
2021
Statut:
ppublish
Résumé
Proton computed tomography (pCT) and radiography (pRad) are proposed modalities for improved treatment plan accuracy and The CNN was trained by simulation and reconstruction of tens of millions of proton and helium tracks. The CNN filter was then compared to simple energy loss threshold methods using the Area Under the Receiver Operating Characteristics curve (AUROC), and by comparing the image quality and Water Equivalent Path Length (WEPL) error of proton and helium radiographs filtered with the same methods. The CNN method led to a considerable improvement of the AUROC, from 74.3% to 97.5% with protons and from 94.2% to 99.5% with helium. The CNN filtering reduced the WEPL error in the helium radiograph from 1.03 mm to 0.93 mm while no improvement was seen in the CNN filtered pRads. The CNN improved the filtering of proton and helium tracks. Only in the helium radiograph did this lead to improved image quality.
Sections du résumé
BACKGROUND
BACKGROUND
Proton computed tomography (pCT) and radiography (pRad) are proposed modalities for improved treatment plan accuracy and
MATERIAL AND METHODS
METHODS
The CNN was trained by simulation and reconstruction of tens of millions of proton and helium tracks. The CNN filter was then compared to simple energy loss threshold methods using the Area Under the Receiver Operating Characteristics curve (AUROC), and by comparing the image quality and Water Equivalent Path Length (WEPL) error of proton and helium radiographs filtered with the same methods.
RESULTS
RESULTS
The CNN method led to a considerable improvement of the AUROC, from 74.3% to 97.5% with protons and from 94.2% to 99.5% with helium. The CNN filtering reduced the WEPL error in the helium radiograph from 1.03 mm to 0.93 mm while no improvement was seen in the CNN filtered pRads.
CONCLUSION
CONCLUSIONS
The CNN improved the filtering of proton and helium tracks. Only in the helium radiograph did this lead to improved image quality.
Identifiants
pubmed: 34259117
doi: 10.1080/0284186X.2021.1949037
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM