Result: Prediction of the output factor using machine and deep learning approach in uniform scanning proton therapy.

Title:
Prediction of the output factor using machine and deep learning approach in uniform scanning proton therapy.
Authors:
Grewal HS; Oklahoma Proton Center, Oklahoma City, OK, USA.; Department of Radiation Oncology, University of Oklahoma Health Sciences Center, Oklahoma City, OK, USA., Chacko MS; Oklahoma Proton Center, Oklahoma City, OK, USA., Ahmad S; Department of Radiation Oncology, University of Oklahoma Health Sciences Center, Oklahoma City, OK, USA., Jin H; Department of Radiation Oncology, University of Oklahoma Health Sciences Center, Oklahoma City, OK, USA.
Source:
Journal of applied clinical medical physics [J Appl Clin Med Phys] 2020 Jul; Vol. 21 (7), pp. 128-134. Date of Electronic Publication: 2020 May 17.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Wiley on behalf of American Association of Physicists in Medicine Country of Publication: United States NLM ID: 101089176 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1526-9914 (Electronic) Linking ISSN: 15269914 NLM ISO Abbreviation: J Appl Clin Med Phys Subsets: MEDLINE
Imprint Name(s):
Publication: 2017- : Malden, MA : Wiley on behalf of American Association of Physicists in Medicine
Original Publication: Reston, VA : American College of Medical Physics, c2000-
MeSH Terms:
Deep Learning* , Proton Therapy*, Algorithms ; Humans ; Neural Networks, Computer ; Normal Distribution
References:
Phys Med Biol. 2005 Dec 21;50(24):5847-56. (PMID: 16333159)
Med Phys. 2018 May;45(5):2243-2251. (PMID: 29500818)
Front Oncol. 2018 Apr 17;8:110. (PMID: 29719815)
Phys Med Biol. 2013 Jul 7;58(13):4563-77. (PMID: 23771015)
Med Phys. 2016 Jul;43(7):4323. (PMID: 27370147)
Phys Med Biol. 2010 Feb 7;55(3):N87-95. (PMID: 20057011)
Strahlenther Onkol. 2016 Nov;192(11):759-769. (PMID: 27363701)
IEEE Trans Neural Netw. 1994;5(6):989-93. (PMID: 18267874)
J Appl Clin Med Phys. 2017 May;18(3):108-117. (PMID: 28422406)
Phys Med Biol. 2003 Sep 7;48(17):2797-808. (PMID: 14516102)
J Appl Clin Med Phys. 2017 Sep;18(5):279-284. (PMID: 28815994)
Med Phys. 2008 Nov;35(11):5088-97. (PMID: 19070243)
Med Phys. 2013 Sep;40(9):091708. (PMID: 24007141)
Med Dosim. 2011 Summer;36(2):145-52. (PMID: 20599372)
Med Phys. 2011 Apr;38(4):2299-306. (PMID: 21626965)
Contributed Indexing:
Keywords: gaussian process regression; machine and deep learning; proton therapy; shallow neural network
Entry Date(s):
Date Created: 20200519 Date Completed: 20210621 Latest Revision: 20210621
Update Code:
20250114
PubMed Central ID:
PMC7386178
DOI:
10.1002/acm2.12899
PMID:
32419245
Database:
MEDLINE

Further Information

Purpose: The purpose of this work is to develop machine and deep learning-based models to predict output and MU based on measured patient quality assurance (QA) data in uniform scanning proton therapy (USPT).
Methods: This study involves 4,231 patient QA measurements conducted over the last 6 years. In the current approach, output and MU are predicted by an empirical model (EM) based on patient treatment plan parameters. In this study, two MATLAB-based machine and deep learning algorithms - Gaussian process regression (GPR) and shallow neural network (SNN) - were developed. The four parameters from patient QA (range, modulation, field size, and measured output factor) were used to train these algorithms. The data were randomized with a training set containing 90% and a testing set containing remaining 10% of the data. The model performance during training was accessed using root mean square error (RMSE) and R-squared values. The trained model was used to predict output based on the three input parameters: range, modulation, and field size. The percent difference was calculated between the predicted and measured output factors. The number of data sets required to make prediction accuracy of GPR and SNN models' invariable was also evaluated.
Results: The prediction accuracy of machine and deep learning algorithms is higher than the EM. The output predictions with [GPR, SNN, and EM] within ± 2% and ± 3% difference were [97.16%, 97.64%, and 92.95%] and [99.76%, 99.29%, and 97.18%], respectively. The GPR model outperformed the SNN with a smaller number of training data sets.
Conclusion: The GPR and SNN models outperformed the EM in terms of prediction accuracy. Machine and deep learning algorithms predicted the output factor and MU for USPT with higher predictive accuracy than EM. In our clinic, these models have been adopted as a secondary check of MU or output factors.
(© 2020 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.)