AI-guided parameter optimization in inverse treatment planning.

Journal Article (Journal Article)

An artificial intelligence (AI)-guided inverse planning system was developed to optimize the combination of parameters in the objective function for intensity-modulated radiation therapy (IMRT). In this system, the empirical knowledge of inverse planning was formulated with fuzzy if-then rules, which then guide the parameter modification based on the on-line calculated dose. Three kinds of parameters (weighting factor, dose specification, and dose prescription) were automatically modified using the fuzzy inference system (FIS). The performance of the AI-guided inverse planning system (AIGIPS) was examined using the simulated and clinical examples. Preliminary results indicate that the expected dose distribution was automatically achieved using the AI-guided inverse planning system, with the complicated compromising between different parameters accomplished by the fuzzy inference technique. The AIGIPS provides a highly promising method to replace the current trial-and-error approach.

Full Text

Duke Authors

Cited Authors

  • Yan, H; Yin, F-F; Guan, H-Q; Kim, JH

Published Date

  • November 7, 2003

Published In

Volume / Issue

  • 48 / 21

Start / End Page

  • 3565 - 3580

PubMed ID

  • 14653563

International Standard Serial Number (ISSN)

  • 0031-9155

Digital Object Identifier (DOI)

  • 10.1088/0031-9155/48/21/008


  • eng

Conference Location

  • England