IMRT QA using machine learning: A multi-institutional validation

Gilmer Valdes, Maria F. Chan, Seng Boh Lim, Ryan Scheuermann, Joseph O. Deasy, Timothy D. Solberg

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Purpose: To validate a machine learning approach to Virtual intensity-modulated radiation therapy (IMRT) quality assurance (QA) for accurately predicting gamma passing rates using different measurement approaches at different institutions. Methods: A Virtual IMRT QA framework was previously developed using a machine learning algorithm based on 498 IMRT plans, in which QA measurements were performed using diode-array detectors and a 3%local/3 mm with 10% threshold at Institution 1. An independent set of 139 IMRT measurements from a different institution, Institution 2, with QA data based on portal dosimetry using the same gamma index, was used to test the mathematical framework. Only pixels with ≥10% of the maximum calibrated units (CU) or dose were included in the comparison. Plans were characterized by 90 different complexity metrics. A weighted poison regression with Lasso regularization was trained to predict passing rates using the complexity metrics as input. Results: The methodology predicted passing rates within 3% accuracy for all composite plans measured using diode-array detectors at Institution 1, and within 3.5% for 120 of 139 plans using portal dosimetry measurements performed on a per-beam basis at Institution 2. The remaining measurements (19) had large areas of low CU, where portal dosimetry has a larger disagreement with the calculated dose and as such, the failure was expected. These beams need further modeling in the treatment planning system to correct the under-response in low-dose regions. Important features selected by Lasso to predict gamma passing rates were as follows: complete irradiated area outline (CIAO), jaw position, fraction of MLC leafs with gaps smaller than 20 or 5 mm, fraction of area receiving less than 50% of the total CU, fraction of the area receiving dose from penumbra, weighted average irregularity factor, and duty cycle. Conclusions: We have demonstrated that Virtual IMRT QA can predict passing rates using different measurement techniques and across multiple institutions. Prediction of QA passing rates can have profound implications on the current IMRT process.

Original languageEnglish (US)
JournalJournal of Applied Clinical Medical Physics
DOIs
StateAccepted/In press - 2017

Fingerprint

machine learning
Radiotherapy
assurance
Quality assurance
Learning systems
radiation therapy
Dosimetry
dosimeters
dosage
Diodes
diodes
Detectors
Poisons
penumbras
poisons
Jaw
detectors
Machine Learning
irregularities
leaves

Keywords

  • IMRT QA
  • Machine learning
  • Poisson regression
  • Radiotherapy

ASJC Scopus subject areas

  • Radiation
  • Instrumentation
  • Radiology Nuclear Medicine and imaging

Cite this

Valdes, G., Chan, M. F., Lim, S. B., Scheuermann, R., Deasy, J. O., & Solberg, T. D. (Accepted/In press). IMRT QA using machine learning: A multi-institutional validation. Journal of Applied Clinical Medical Physics. https://doi.org/10.1002/acm2.12161

IMRT QA using machine learning : A multi-institutional validation. / Valdes, Gilmer; Chan, Maria F.; Lim, Seng Boh; Scheuermann, Ryan; Deasy, Joseph O.; Solberg, Timothy D.

In: Journal of Applied Clinical Medical Physics, 2017.

Research output: Contribution to journalArticle

Valdes, Gilmer ; Chan, Maria F. ; Lim, Seng Boh ; Scheuermann, Ryan ; Deasy, Joseph O. ; Solberg, Timothy D. / IMRT QA using machine learning : A multi-institutional validation. In: Journal of Applied Clinical Medical Physics. 2017.
@article{70e5b647253042da91ea2e9fb574ea34,
title = "IMRT QA using machine learning: A multi-institutional validation",
abstract = "Purpose: To validate a machine learning approach to Virtual intensity-modulated radiation therapy (IMRT) quality assurance (QA) for accurately predicting gamma passing rates using different measurement approaches at different institutions. Methods: A Virtual IMRT QA framework was previously developed using a machine learning algorithm based on 498 IMRT plans, in which QA measurements were performed using diode-array detectors and a 3{\%}local/3 mm with 10{\%} threshold at Institution 1. An independent set of 139 IMRT measurements from a different institution, Institution 2, with QA data based on portal dosimetry using the same gamma index, was used to test the mathematical framework. Only pixels with ≥10{\%} of the maximum calibrated units (CU) or dose were included in the comparison. Plans were characterized by 90 different complexity metrics. A weighted poison regression with Lasso regularization was trained to predict passing rates using the complexity metrics as input. Results: The methodology predicted passing rates within 3{\%} accuracy for all composite plans measured using diode-array detectors at Institution 1, and within 3.5{\%} for 120 of 139 plans using portal dosimetry measurements performed on a per-beam basis at Institution 2. The remaining measurements (19) had large areas of low CU, where portal dosimetry has a larger disagreement with the calculated dose and as such, the failure was expected. These beams need further modeling in the treatment planning system to correct the under-response in low-dose regions. Important features selected by Lasso to predict gamma passing rates were as follows: complete irradiated area outline (CIAO), jaw position, fraction of MLC leafs with gaps smaller than 20 or 5 mm, fraction of area receiving less than 50{\%} of the total CU, fraction of the area receiving dose from penumbra, weighted average irregularity factor, and duty cycle. Conclusions: We have demonstrated that Virtual IMRT QA can predict passing rates using different measurement techniques and across multiple institutions. Prediction of QA passing rates can have profound implications on the current IMRT process.",
keywords = "IMRT QA, Machine learning, Poisson regression, Radiotherapy",
author = "Gilmer Valdes and Chan, {Maria F.} and Lim, {Seng Boh} and Ryan Scheuermann and Deasy, {Joseph O.} and Solberg, {Timothy D.}",
year = "2017",
doi = "10.1002/acm2.12161",
language = "English (US)",
journal = "Journal of Applied Clinical Medical Physics",
issn = "1526-9914",
publisher = "American Institute of Physics Publising LLC",

}

TY - JOUR

T1 - IMRT QA using machine learning

T2 - A multi-institutional validation

AU - Valdes, Gilmer

AU - Chan, Maria F.

AU - Lim, Seng Boh

AU - Scheuermann, Ryan

AU - Deasy, Joseph O.

AU - Solberg, Timothy D.

PY - 2017

Y1 - 2017

N2 - Purpose: To validate a machine learning approach to Virtual intensity-modulated radiation therapy (IMRT) quality assurance (QA) for accurately predicting gamma passing rates using different measurement approaches at different institutions. Methods: A Virtual IMRT QA framework was previously developed using a machine learning algorithm based on 498 IMRT plans, in which QA measurements were performed using diode-array detectors and a 3%local/3 mm with 10% threshold at Institution 1. An independent set of 139 IMRT measurements from a different institution, Institution 2, with QA data based on portal dosimetry using the same gamma index, was used to test the mathematical framework. Only pixels with ≥10% of the maximum calibrated units (CU) or dose were included in the comparison. Plans were characterized by 90 different complexity metrics. A weighted poison regression with Lasso regularization was trained to predict passing rates using the complexity metrics as input. Results: The methodology predicted passing rates within 3% accuracy for all composite plans measured using diode-array detectors at Institution 1, and within 3.5% for 120 of 139 plans using portal dosimetry measurements performed on a per-beam basis at Institution 2. The remaining measurements (19) had large areas of low CU, where portal dosimetry has a larger disagreement with the calculated dose and as such, the failure was expected. These beams need further modeling in the treatment planning system to correct the under-response in low-dose regions. Important features selected by Lasso to predict gamma passing rates were as follows: complete irradiated area outline (CIAO), jaw position, fraction of MLC leafs with gaps smaller than 20 or 5 mm, fraction of area receiving less than 50% of the total CU, fraction of the area receiving dose from penumbra, weighted average irregularity factor, and duty cycle. Conclusions: We have demonstrated that Virtual IMRT QA can predict passing rates using different measurement techniques and across multiple institutions. Prediction of QA passing rates can have profound implications on the current IMRT process.

AB - Purpose: To validate a machine learning approach to Virtual intensity-modulated radiation therapy (IMRT) quality assurance (QA) for accurately predicting gamma passing rates using different measurement approaches at different institutions. Methods: A Virtual IMRT QA framework was previously developed using a machine learning algorithm based on 498 IMRT plans, in which QA measurements were performed using diode-array detectors and a 3%local/3 mm with 10% threshold at Institution 1. An independent set of 139 IMRT measurements from a different institution, Institution 2, with QA data based on portal dosimetry using the same gamma index, was used to test the mathematical framework. Only pixels with ≥10% of the maximum calibrated units (CU) or dose were included in the comparison. Plans were characterized by 90 different complexity metrics. A weighted poison regression with Lasso regularization was trained to predict passing rates using the complexity metrics as input. Results: The methodology predicted passing rates within 3% accuracy for all composite plans measured using diode-array detectors at Institution 1, and within 3.5% for 120 of 139 plans using portal dosimetry measurements performed on a per-beam basis at Institution 2. The remaining measurements (19) had large areas of low CU, where portal dosimetry has a larger disagreement with the calculated dose and as such, the failure was expected. These beams need further modeling in the treatment planning system to correct the under-response in low-dose regions. Important features selected by Lasso to predict gamma passing rates were as follows: complete irradiated area outline (CIAO), jaw position, fraction of MLC leafs with gaps smaller than 20 or 5 mm, fraction of area receiving less than 50% of the total CU, fraction of the area receiving dose from penumbra, weighted average irregularity factor, and duty cycle. Conclusions: We have demonstrated that Virtual IMRT QA can predict passing rates using different measurement techniques and across multiple institutions. Prediction of QA passing rates can have profound implications on the current IMRT process.

KW - IMRT QA

KW - Machine learning

KW - Poisson regression

KW - Radiotherapy

UR - http://www.scopus.com/inward/record.url?scp=85027501141&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027501141&partnerID=8YFLogxK

U2 - 10.1002/acm2.12161

DO - 10.1002/acm2.12161

M3 - Article

C2 - 28815994

AN - SCOPUS:85027501141

JO - Journal of Applied Clinical Medical Physics

JF - Journal of Applied Clinical Medical Physics

SN - 1526-9914

ER -