Partial Differential Equations-Based Segmentation for Radiotherapy Treatment Planning

The purpose of this study is to develop automatic algorithms for the segmentation phase of radiotherapy treatmentplanning. We develop new image processing techniques that are based on solving a partial differential equation for theevolution of the curve that identifies the segmented organ. The vel...

Full description

Saved in:
Bibliographic Details
Main Authors: Frédéric Gibou, Doron Levy, Carlos Cárdenas, Pingyu Liu, Arthur Boyer
Format: Article
Language:English
Published: AIMS Press 2005-02-01
Series:Mathematical Biosciences and Engineering
Subjects:
Online Access:https://www.aimspress.com/article/doi/10.3934/mbe.2005.2.209
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832590273315602432
author Frédéric Gibou
Doron Levy
Carlos Cárdenas
Pingyu Liu
Arthur Boyer
author_facet Frédéric Gibou
Doron Levy
Carlos Cárdenas
Pingyu Liu
Arthur Boyer
author_sort Frédéric Gibou
collection DOAJ
description The purpose of this study is to develop automatic algorithms for the segmentation phase of radiotherapy treatmentplanning. We develop new image processing techniques that are based on solving a partial differential equation for theevolution of the curve that identifies the segmented organ. The velocity function is based on the piecewiseMumford-Shah functional. Our method incorporates information about the target organ into classical segmentationalgorithms. This information, which is given in terms of a three-dimensional wireframe representation of the organ,serves as an initial guess for the segmentation algorithm. We check the performance of the new algorithm on eight datasets of three different organs: rectum, bladder, and kidney. The results of the automatic segmentation were comparedwith a manual segmentation of each data set by radiation oncology faculty and residents. The quality of the automaticsegmentation was measured with the ''$\kappa$-statistics'', and with a count of over- and undersegmented frames, andwas shown in most cases to be very close to the manual segmentation of the same data. A typical segmentation of anorgan with sixty slices takes less than ten seconds on a Pentium IV laptop.
format Article
id doaj-art-9c5889bb2e474800a8562080908e1eca
institution Kabale University
issn 1551-0018
language English
publishDate 2005-02-01
publisher AIMS Press
record_format Article
series Mathematical Biosciences and Engineering
spelling doaj-art-9c5889bb2e474800a8562080908e1eca2025-01-24T01:48:05ZengAIMS PressMathematical Biosciences and Engineering1551-00182005-02-012220922610.3934/mbe.2005.2.209Partial Differential Equations-Based Segmentation for Radiotherapy Treatment PlanningFrédéric Gibou0Doron Levy1Carlos Cárdenas2Pingyu Liu3Arthur Boyer4Department of Computer Science and Department of Mechanical Engineering, University of California at Santa Barbara, CA 93106-5070Department of Mathematics, Stanford University, Stanford, CA 94305-2125Siemens Medical Solutions, Med SW West, 755 College Road East, Princeton, NJ 08540Department of Radiation Oncology, Stanford University, Stanford, CA 94305Department of Radiation Oncology, Stanford University, Stanford, CA 94305The purpose of this study is to develop automatic algorithms for the segmentation phase of radiotherapy treatmentplanning. We develop new image processing techniques that are based on solving a partial differential equation for theevolution of the curve that identifies the segmented organ. The velocity function is based on the piecewiseMumford-Shah functional. Our method incorporates information about the target organ into classical segmentationalgorithms. This information, which is given in terms of a three-dimensional wireframe representation of the organ,serves as an initial guess for the segmentation algorithm. We check the performance of the new algorithm on eight datasets of three different organs: rectum, bladder, and kidney. The results of the automatic segmentation were comparedwith a manual segmentation of each data set by radiation oncology faculty and residents. The quality of the automaticsegmentation was measured with the ''$\kappa$-statistics'', and with a count of over- and undersegmented frames, andwas shown in most cases to be very close to the manual segmentation of the same data. A typical segmentation of anorgan with sixty slices takes less than ten seconds on a Pentium IV laptop.https://www.aimspress.com/article/doi/10.3934/mbe.2005.2.209segmentationradiotherapy treatmentlevel-set methodsmumford-shah.
spellingShingle Frédéric Gibou
Doron Levy
Carlos Cárdenas
Pingyu Liu
Arthur Boyer
Partial Differential Equations-Based Segmentation for Radiotherapy Treatment Planning
Mathematical Biosciences and Engineering
segmentation
radiotherapy treatment
level-set methods
mumford-shah.
title Partial Differential Equations-Based Segmentation for Radiotherapy Treatment Planning
title_full Partial Differential Equations-Based Segmentation for Radiotherapy Treatment Planning
title_fullStr Partial Differential Equations-Based Segmentation for Radiotherapy Treatment Planning
title_full_unstemmed Partial Differential Equations-Based Segmentation for Radiotherapy Treatment Planning
title_short Partial Differential Equations-Based Segmentation for Radiotherapy Treatment Planning
title_sort partial differential equations based segmentation for radiotherapy treatment planning
topic segmentation
radiotherapy treatment
level-set methods
mumford-shah.
url https://www.aimspress.com/article/doi/10.3934/mbe.2005.2.209
work_keys_str_mv AT fredericgibou partialdifferentialequationsbasedsegmentationforradiotherapytreatmentplanning
AT doronlevy partialdifferentialequationsbasedsegmentationforradiotherapytreatmentplanning
AT carloscardenas partialdifferentialequationsbasedsegmentationforradiotherapytreatmentplanning
AT pingyuliu partialdifferentialequationsbasedsegmentationforradiotherapytreatmentplanning
AT arthurboyer partialdifferentialequationsbasedsegmentationforradiotherapytreatmentplanning