Enhanced Proton Tracking with ASTRA Using Calorimetry and Deep Learning

César Jesús-Valls; Marc Granado-González; Thorsten Lux; Tony Price; Federico Sánchez

doi:10.3390/instruments6040058

Enhanced Proton Tracking with ASTRA Using Calorimetry and Deep Learning

César Jesús-Valls^*, Marc Granado-González, Thorsten Lux, Tony Price, Federico Sánchez

^*Corresponding author for this work

Physics and Astronomy

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

54 Downloads (Pure)

Abstract

Recently, we proposed a novel range detector concept named ASTRA. ASTRA is optimized to accurately measure (better than 1%) the residual energy of protons with kinetic energies in the range from tens to a few hundred MeVs at a very high rate of (Formula presented.) 100 MHz). These combined performances are aimed at achieving fast and high-quality proton Computerized Tomography (pCT), which is crucial to correctly assessing treatment planning in proton beam therapy. Despite being a range telescope, ASTRA is also a calorimeter, opening the door to enhanced tracking possibilities based on deep learning. Here, we review the ASTRA concept, and we study an alternative tracking method that exploits calorimetry. In particular, we study the potential of ASTRA to deal with pile-up protons by means of a novel tracking method based on semantic segmentation, a deep learning network architecture that performs classification at the pixel level.

Original language	English
Article number	58
Number of pages	6
Journal	Instruments
Volume	6
Issue number	4
DOIs	https://doi.org/10.3390/instruments6040058
Publication status	Published - 8 Oct 2022

Bibliographical note

Funding Information:
This research was funded by SEIDI-MINECO grants number PID2019-107564GB-I00 and SEV-2016-0588, the SNF grant number 200021_85012 and the EPSRC grant number EP/R023220/1.

Publisher Copyright:
© 2022 by the authors.

Keywords

deep learning
image reconstruction
proton CT
proton tracking

ASJC Scopus subject areas

Instrumentation

Access to Document

10.3390/instruments6040058Licence: Creative Commons: Attribution (CC BY)

JesúsVallsC2022EnhancedFinal published version, 1.05 MBLicence: Creative Commons: Attribution (CC BY)

OPTIMA: Optimising proton therapy through imaging
Allport, P. & Price, T.
Engineering & Physical Science Research Council
1/05/18 → 30/11/24
Project: Research Councils

Cite this

@article{7aa01fadd27148d384e5973be1eab495,

title = "Enhanced Proton Tracking with ASTRA Using Calorimetry and Deep Learning",

abstract = "Recently, we proposed a novel range detector concept named ASTRA. ASTRA is optimized to accurately measure (better than 1%) the residual energy of protons with kinetic energies in the range from tens to a few hundred MeVs at a very high rate of (Formula presented.) 100 MHz). These combined performances are aimed at achieving fast and high-quality proton Computerized Tomography (pCT), which is crucial to correctly assessing treatment planning in proton beam therapy. Despite being a range telescope, ASTRA is also a calorimeter, opening the door to enhanced tracking possibilities based on deep learning. Here, we review the ASTRA concept, and we study an alternative tracking method that exploits calorimetry. In particular, we study the potential of ASTRA to deal with pile-up protons by means of a novel tracking method based on semantic segmentation, a deep learning network architecture that performs classification at the pixel level.",

keywords = "deep learning, image reconstruction, proton CT, proton tracking",

author = "C{\'e}sar Jes{\'u}s-Valls and Marc Granado-Gonz{\'a}lez and Thorsten Lux and Tony Price and Federico S{\'a}nchez",

note = "Funding Information: This research was funded by SEIDI-MINECO grants number PID2019-107564GB-I00 and SEV-2016-0588, the SNF grant number 200021_85012 and the EPSRC grant number EP/R023220/1. Publisher Copyright: {\textcopyright} 2022 by the authors.",

year = "2022",

month = oct,

day = "8",

doi = "10.3390/instruments6040058",

language = "English",

volume = "6",

journal = "Instruments",

issn = "2410-390X",

publisher = "MDPI",

number = "4",

}

TY - JOUR

T1 - Enhanced Proton Tracking with ASTRA Using Calorimetry and Deep Learning

AU - Jesús-Valls, César

AU - Granado-González, Marc

AU - Lux, Thorsten

AU - Price, Tony

AU - Sánchez, Federico

N1 - Funding Information: This research was funded by SEIDI-MINECO grants number PID2019-107564GB-I00 and SEV-2016-0588, the SNF grant number 200021_85012 and the EPSRC grant number EP/R023220/1. Publisher Copyright: © 2022 by the authors.

PY - 2022/10/8

Y1 - 2022/10/8

N2 - Recently, we proposed a novel range detector concept named ASTRA. ASTRA is optimized to accurately measure (better than 1%) the residual energy of protons with kinetic energies in the range from tens to a few hundred MeVs at a very high rate of (Formula presented.) 100 MHz). These combined performances are aimed at achieving fast and high-quality proton Computerized Tomography (pCT), which is crucial to correctly assessing treatment planning in proton beam therapy. Despite being a range telescope, ASTRA is also a calorimeter, opening the door to enhanced tracking possibilities based on deep learning. Here, we review the ASTRA concept, and we study an alternative tracking method that exploits calorimetry. In particular, we study the potential of ASTRA to deal with pile-up protons by means of a novel tracking method based on semantic segmentation, a deep learning network architecture that performs classification at the pixel level.

AB - Recently, we proposed a novel range detector concept named ASTRA. ASTRA is optimized to accurately measure (better than 1%) the residual energy of protons with kinetic energies in the range from tens to a few hundred MeVs at a very high rate of (Formula presented.) 100 MHz). These combined performances are aimed at achieving fast and high-quality proton Computerized Tomography (pCT), which is crucial to correctly assessing treatment planning in proton beam therapy. Despite being a range telescope, ASTRA is also a calorimeter, opening the door to enhanced tracking possibilities based on deep learning. Here, we review the ASTRA concept, and we study an alternative tracking method that exploits calorimetry. In particular, we study the potential of ASTRA to deal with pile-up protons by means of a novel tracking method based on semantic segmentation, a deep learning network architecture that performs classification at the pixel level.

KW - deep learning

KW - image reconstruction

KW - proton CT

KW - proton tracking

UR - http://www.scopus.com/inward/record.url?scp=85144687303&partnerID=8YFLogxK

U2 - 10.3390/instruments6040058

DO - 10.3390/instruments6040058

M3 - Article

AN - SCOPUS:85144687303

SN - 2410-390X

VL - 6

JO - Instruments

JF - Instruments

IS - 4

M1 - 58

ER -

Enhanced Proton Tracking with ASTRA Using Calorimetry and Deep Learning

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Projects

OPTIMA: Optimising proton therapy through imaging

Cite this