Stochastic programming for off-line adaptive radiotherapy

Mustafa Sir, Marina A. Epelman, Stephen M. Pollock

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In intensity-modulated radiotherapy (IMRT), a treatment is designed to deliver high radiation doses to tumors, while avoiding the healthy tissue. Optimization-based treatment planning often produces sharp dose gradients between tumors and healthy tissue. Random shifts during treatment can cause significant differences between the dose in the "optimized" plan and the actual dose delivered to a patient. An IMRT treatment plan is delivered as a series of small daily dosages, or fractions, over a period of time (typically 35 days). It has recently become technically possible to measure variations in patient setup and the delivered doses after each fraction. We develop an optimization framework, which exploits the dynamic nature of radiotherapy and information gathering by adapting the treatment plan in response to temporal variations measured during the treatment course of a individual patient. The resulting (suboptimal) control policies, which re-optimize before each fraction, include two approximate dynamic programming schemes: certainty equivalent control (CEC) and open-loop feedback control (OLFC). Computational experiments show that resulting individualized adaptive radiotherapy plans promise to provide a considerable improvement compared to non-adaptive treatment plans, while remaining computationally feasible to implement.

Original languageEnglish (US)
Pages (from-to)767-797
Number of pages31
JournalAnnals of Operations Research
Volume196
Issue number1
DOIs
StatePublished - Jul 1 2012

Fingerprint

Stochastic programming
Tumor
Gradient
Planning
Certainty equivalent
Experiment
Information gathering
Radiation
Feedback control
Approximate dynamic programming

Keywords

  • Adaptive radiotherapy
  • Patient setup error
  • Stochastic programming

ASJC Scopus subject areas

  • Decision Sciences(all)
  • Management Science and Operations Research

Cite this

Stochastic programming for off-line adaptive radiotherapy. / Sir, Mustafa; Epelman, Marina A.; Pollock, Stephen M.

In: Annals of Operations Research, Vol. 196, No. 1, 01.07.2012, p. 767-797.

Research output: Contribution to journalArticle

Sir, Mustafa ; Epelman, Marina A. ; Pollock, Stephen M. / Stochastic programming for off-line adaptive radiotherapy. In: Annals of Operations Research. 2012 ; Vol. 196, No. 1. pp. 767-797.
@article{be57e5caf2804b58abf0db8af7186033,
title = "Stochastic programming for off-line adaptive radiotherapy",
abstract = "In intensity-modulated radiotherapy (IMRT), a treatment is designed to deliver high radiation doses to tumors, while avoiding the healthy tissue. Optimization-based treatment planning often produces sharp dose gradients between tumors and healthy tissue. Random shifts during treatment can cause significant differences between the dose in the {"}optimized{"} plan and the actual dose delivered to a patient. An IMRT treatment plan is delivered as a series of small daily dosages, or fractions, over a period of time (typically 35 days). It has recently become technically possible to measure variations in patient setup and the delivered doses after each fraction. We develop an optimization framework, which exploits the dynamic nature of radiotherapy and information gathering by adapting the treatment plan in response to temporal variations measured during the treatment course of a individual patient. The resulting (suboptimal) control policies, which re-optimize before each fraction, include two approximate dynamic programming schemes: certainty equivalent control (CEC) and open-loop feedback control (OLFC). Computational experiments show that resulting individualized adaptive radiotherapy plans promise to provide a considerable improvement compared to non-adaptive treatment plans, while remaining computationally feasible to implement.",
keywords = "Adaptive radiotherapy, Patient setup error, Stochastic programming",
author = "Mustafa Sir and Epelman, {Marina A.} and Pollock, {Stephen M.}",
year = "2012",
month = "7",
day = "1",
doi = "10.1007/s10479-010-0779-x",
language = "English (US)",
volume = "196",
pages = "767--797",
journal = "Annals of Operations Research",
issn = "0254-5330",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Stochastic programming for off-line adaptive radiotherapy

AU - Sir, Mustafa

AU - Epelman, Marina A.

AU - Pollock, Stephen M.

PY - 2012/7/1

Y1 - 2012/7/1

N2 - In intensity-modulated radiotherapy (IMRT), a treatment is designed to deliver high radiation doses to tumors, while avoiding the healthy tissue. Optimization-based treatment planning often produces sharp dose gradients between tumors and healthy tissue. Random shifts during treatment can cause significant differences between the dose in the "optimized" plan and the actual dose delivered to a patient. An IMRT treatment plan is delivered as a series of small daily dosages, or fractions, over a period of time (typically 35 days). It has recently become technically possible to measure variations in patient setup and the delivered doses after each fraction. We develop an optimization framework, which exploits the dynamic nature of radiotherapy and information gathering by adapting the treatment plan in response to temporal variations measured during the treatment course of a individual patient. The resulting (suboptimal) control policies, which re-optimize before each fraction, include two approximate dynamic programming schemes: certainty equivalent control (CEC) and open-loop feedback control (OLFC). Computational experiments show that resulting individualized adaptive radiotherapy plans promise to provide a considerable improvement compared to non-adaptive treatment plans, while remaining computationally feasible to implement.

AB - In intensity-modulated radiotherapy (IMRT), a treatment is designed to deliver high radiation doses to tumors, while avoiding the healthy tissue. Optimization-based treatment planning often produces sharp dose gradients between tumors and healthy tissue. Random shifts during treatment can cause significant differences between the dose in the "optimized" plan and the actual dose delivered to a patient. An IMRT treatment plan is delivered as a series of small daily dosages, or fractions, over a period of time (typically 35 days). It has recently become technically possible to measure variations in patient setup and the delivered doses after each fraction. We develop an optimization framework, which exploits the dynamic nature of radiotherapy and information gathering by adapting the treatment plan in response to temporal variations measured during the treatment course of a individual patient. The resulting (suboptimal) control policies, which re-optimize before each fraction, include two approximate dynamic programming schemes: certainty equivalent control (CEC) and open-loop feedback control (OLFC). Computational experiments show that resulting individualized adaptive radiotherapy plans promise to provide a considerable improvement compared to non-adaptive treatment plans, while remaining computationally feasible to implement.

KW - Adaptive radiotherapy

KW - Patient setup error

KW - Stochastic programming

UR - http://www.scopus.com/inward/record.url?scp=84863205540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863205540&partnerID=8YFLogxK

U2 - 10.1007/s10479-010-0779-x

DO - 10.1007/s10479-010-0779-x

M3 - Article

AN - SCOPUS:84863205540

VL - 196

SP - 767

EP - 797

JO - Annals of Operations Research

JF - Annals of Operations Research

SN - 0254-5330

IS - 1

ER -