Treatment planning optimization based on response-surface modeling of cost function versus multiple constraints

H. H. Liu, Rosen, N. A. Janjan, Alan Pollack

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In treatment planning optimization and inverse planning, a solution is governed by operator-specified objectives and constraints, which are usually in conflict with each other. Currently, the planning process involves manual iterations of testing different combinations of constraints and/or objectives, and evaluating the resulting solutions. In this we are developing a more efficient paradigm to automate this process. The key component of our approach is to model the cost to be optimized as a function of all the competing constraints. Initially we evaluated this technique for optimizing angles and weights of coplanar beams in conformal therapy of pancreas prostate cancer. The minimum tumor dose was maximized with multiple dose-volume constraints for other critical structures. An initial set of constraints was established such that the tumor dose fell within desired limits. Subsequently, each active constraint was changed by a small step and the optimization was rerun to obtain a new solution. Effectively, we sampled the solution space and obtained a database of the optimized solutions for a variety of different constraint values. We then modeled the tumor dose as a multi-variable function of doses to critical structures using a response-surface method. This allowed us to visualize how the constraints competed and affected the tumor dose. Using this information, one can interactively navigate through the solution space and quickly balance among the tumor dose and doses to other structures. This new paradigm focuses on clinical considerations during optimization and improves the efficiency of the treatment planning process.

Original languageEnglish (US)
Title of host publicationAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
EditorsJ.D. Enderle
Pages119-122
Number of pages4
Volume1
StatePublished - 2000
Externally publishedYes
Event22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Chicago, IL, United States
Duration: Jul 23 2000Jul 28 2000

Other

Other22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CountryUnited States
CityChicago, IL
Period7/23/007/28/00

Fingerprint

Cost functions
Tumors
Planning
Testing
Costs

Keywords

  • Inverse planning
  • Response-surface method
  • Treatment plan optimization

ASJC Scopus subject areas

  • Bioengineering

Cite this

Liu, H. H., Rosen, Janjan, N. A., & Pollack, A. (2000). Treatment planning optimization based on response-surface modeling of cost function versus multiple constraints. In J. D. Enderle (Ed.), Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings (Vol. 1, pp. 119-122)

Treatment planning optimization based on response-surface modeling of cost function versus multiple constraints. / Liu, H. H.; Rosen; Janjan, N. A.; Pollack, Alan.

Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. ed. / J.D. Enderle. Vol. 1 2000. p. 119-122.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, HH, Rosen, Janjan, NA & Pollack, A 2000, Treatment planning optimization based on response-surface modeling of cost function versus multiple constraints. in JD Enderle (ed.), Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. vol. 1, pp. 119-122, 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, United States, 7/23/00.
Liu HH, Rosen, Janjan NA, Pollack A. Treatment planning optimization based on response-surface modeling of cost function versus multiple constraints. In Enderle JD, editor, Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 1. 2000. p. 119-122
Liu, H. H. ; Rosen ; Janjan, N. A. ; Pollack, Alan. / Treatment planning optimization based on response-surface modeling of cost function versus multiple constraints. Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. editor / J.D. Enderle. Vol. 1 2000. pp. 119-122
@inproceedings{6d799533d972432b8ab65dcf2d408905,
title = "Treatment planning optimization based on response-surface modeling of cost function versus multiple constraints",
abstract = "In treatment planning optimization and inverse planning, a solution is governed by operator-specified objectives and constraints, which are usually in conflict with each other. Currently, the planning process involves manual iterations of testing different combinations of constraints and/or objectives, and evaluating the resulting solutions. In this we are developing a more efficient paradigm to automate this process. The key component of our approach is to model the cost to be optimized as a function of all the competing constraints. Initially we evaluated this technique for optimizing angles and weights of coplanar beams in conformal therapy of pancreas prostate cancer. The minimum tumor dose was maximized with multiple dose-volume constraints for other critical structures. An initial set of constraints was established such that the tumor dose fell within desired limits. Subsequently, each active constraint was changed by a small step and the optimization was rerun to obtain a new solution. Effectively, we sampled the solution space and obtained a database of the optimized solutions for a variety of different constraint values. We then modeled the tumor dose as a multi-variable function of doses to critical structures using a response-surface method. This allowed us to visualize how the constraints competed and affected the tumor dose. Using this information, one can interactively navigate through the solution space and quickly balance among the tumor dose and doses to other structures. This new paradigm focuses on clinical considerations during optimization and improves the efficiency of the treatment planning process.",
keywords = "Inverse planning, Response-surface method, Treatment plan optimization",
author = "Liu, {H. H.} and Rosen and Janjan, {N. A.} and Alan Pollack",
year = "2000",
language = "English (US)",
volume = "1",
pages = "119--122",
editor = "J.D. Enderle",
booktitle = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",

}

TY - GEN

T1 - Treatment planning optimization based on response-surface modeling of cost function versus multiple constraints

AU - Liu, H. H.

AU - Rosen,

AU - Janjan, N. A.

AU - Pollack, Alan

PY - 2000

Y1 - 2000

N2 - In treatment planning optimization and inverse planning, a solution is governed by operator-specified objectives and constraints, which are usually in conflict with each other. Currently, the planning process involves manual iterations of testing different combinations of constraints and/or objectives, and evaluating the resulting solutions. In this we are developing a more efficient paradigm to automate this process. The key component of our approach is to model the cost to be optimized as a function of all the competing constraints. Initially we evaluated this technique for optimizing angles and weights of coplanar beams in conformal therapy of pancreas prostate cancer. The minimum tumor dose was maximized with multiple dose-volume constraints for other critical structures. An initial set of constraints was established such that the tumor dose fell within desired limits. Subsequently, each active constraint was changed by a small step and the optimization was rerun to obtain a new solution. Effectively, we sampled the solution space and obtained a database of the optimized solutions for a variety of different constraint values. We then modeled the tumor dose as a multi-variable function of doses to critical structures using a response-surface method. This allowed us to visualize how the constraints competed and affected the tumor dose. Using this information, one can interactively navigate through the solution space and quickly balance among the tumor dose and doses to other structures. This new paradigm focuses on clinical considerations during optimization and improves the efficiency of the treatment planning process.

AB - In treatment planning optimization and inverse planning, a solution is governed by operator-specified objectives and constraints, which are usually in conflict with each other. Currently, the planning process involves manual iterations of testing different combinations of constraints and/or objectives, and evaluating the resulting solutions. In this we are developing a more efficient paradigm to automate this process. The key component of our approach is to model the cost to be optimized as a function of all the competing constraints. Initially we evaluated this technique for optimizing angles and weights of coplanar beams in conformal therapy of pancreas prostate cancer. The minimum tumor dose was maximized with multiple dose-volume constraints for other critical structures. An initial set of constraints was established such that the tumor dose fell within desired limits. Subsequently, each active constraint was changed by a small step and the optimization was rerun to obtain a new solution. Effectively, we sampled the solution space and obtained a database of the optimized solutions for a variety of different constraint values. We then modeled the tumor dose as a multi-variable function of doses to critical structures using a response-surface method. This allowed us to visualize how the constraints competed and affected the tumor dose. Using this information, one can interactively navigate through the solution space and quickly balance among the tumor dose and doses to other structures. This new paradigm focuses on clinical considerations during optimization and improves the efficiency of the treatment planning process.

KW - Inverse planning

KW - Response-surface method

KW - Treatment plan optimization

UR - http://www.scopus.com/inward/record.url?scp=0034441042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034441042&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1

SP - 119

EP - 122

BT - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

A2 - Enderle, J.D.

ER -