A modality-adaptive method for segmenting brain tumors and organs-at-risk in radiation therapy planning

Mikael Agn*, Per Munck af Rosenschöld, Oula Puonti, Michael J. Lundemann, Laura Mancini, Anastasia Papadaki, Steffi Thust, John Ashburner, Ian Law, Koen Van Leemput

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

187 Downloads (Pure)

Abstract

In this paper we present a method for simultaneously segmenting brain tumors and an extensive set of organs-at-risk for radiation therapy planning of glioblastomas. The method combines a contrast-adaptive generative model for whole-brain segmentation with a new spatial regularization model of tumor shape using convolutional restricted Boltzmann machines. We demonstrate experimentally that the method is able to adapt to image acquisitions that differ substantially from any available training data, ensuring its applicability across treatment sites; that its tumor segmentation accuracy is comparable to that of the current state of the art; and that it captures most organs-at-risk sufficiently well for radiation therapy planning purposes. The proposed method may be a valuable step towards automating the delineation of brain tumors and organs-at-risk in glioblastoma patients undergoing radiation therapy.

Original languageEnglish
JournalMedical Image Analysis
Volume54
Pages (from-to)220-237
ISSN1361-8415
DOIs
Publication statusPublished - 1 May 2019

Keywords

  • Generative probabilistic model
  • Glioma
  • Restricted Boltzmann machine
  • Whole-brain segmentation

Cite this

Agn, Mikael ; Munck af Rosenschöld, Per ; Puonti, Oula ; Lundemann, Michael J. ; Mancini, Laura ; Papadaki, Anastasia ; Thust, Steffi ; Ashburner, John ; Law, Ian ; Van Leemput, Koen. / A modality-adaptive method for segmenting brain tumors and organs-at-risk in radiation therapy planning. In: Medical Image Analysis. 2019 ; Vol. 54. pp. 220-237.
@article{b5c2eb23e5b74bc5be76d0895bddbfe3,
title = "A modality-adaptive method for segmenting brain tumors and organs-at-risk in radiation therapy planning",
abstract = "In this paper we present a method for simultaneously segmenting brain tumors and an extensive set of organs-at-risk for radiation therapy planning of glioblastomas. The method combines a contrast-adaptive generative model for whole-brain segmentation with a new spatial regularization model of tumor shape using convolutional restricted Boltzmann machines. We demonstrate experimentally that the method is able to adapt to image acquisitions that differ substantially from any available training data, ensuring its applicability across treatment sites; that its tumor segmentation accuracy is comparable to that of the current state of the art; and that it captures most organs-at-risk sufficiently well for radiation therapy planning purposes. The proposed method may be a valuable step towards automating the delineation of brain tumors and organs-at-risk in glioblastoma patients undergoing radiation therapy.",
keywords = "Generative probabilistic model, Glioma, Restricted Boltzmann machine, Whole-brain segmentation",
author = "Mikael Agn and {Munck af Rosensch{\"o}ld}, Per and Oula Puonti and Lundemann, {Michael J.} and Laura Mancini and Anastasia Papadaki and Steffi Thust and John Ashburner and Ian Law and {Van Leemput}, Koen",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.media.2019.03.005",
language = "English",
volume = "54",
pages = "220--237",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

Agn, M, Munck af Rosenschöld, P, Puonti, O, Lundemann, MJ, Mancini, L, Papadaki, A, Thust, S, Ashburner, J, Law, I & Van Leemput, K 2019, 'A modality-adaptive method for segmenting brain tumors and organs-at-risk in radiation therapy planning', Medical Image Analysis, vol. 54, pp. 220-237. https://doi.org/10.1016/j.media.2019.03.005

A modality-adaptive method for segmenting brain tumors and organs-at-risk in radiation therapy planning. / Agn, Mikael; Munck af Rosenschöld, Per; Puonti, Oula; Lundemann, Michael J.; Mancini, Laura; Papadaki, Anastasia; Thust, Steffi; Ashburner, John; Law, Ian; Van Leemput, Koen.

In: Medical Image Analysis, Vol. 54, 01.05.2019, p. 220-237.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - A modality-adaptive method for segmenting brain tumors and organs-at-risk in radiation therapy planning

AU - Agn, Mikael

AU - Munck af Rosenschöld, Per

AU - Puonti, Oula

AU - Lundemann, Michael J.

AU - Mancini, Laura

AU - Papadaki, Anastasia

AU - Thust, Steffi

AU - Ashburner, John

AU - Law, Ian

AU - Van Leemput, Koen

PY - 2019/5/1

Y1 - 2019/5/1

N2 - In this paper we present a method for simultaneously segmenting brain tumors and an extensive set of organs-at-risk for radiation therapy planning of glioblastomas. The method combines a contrast-adaptive generative model for whole-brain segmentation with a new spatial regularization model of tumor shape using convolutional restricted Boltzmann machines. We demonstrate experimentally that the method is able to adapt to image acquisitions that differ substantially from any available training data, ensuring its applicability across treatment sites; that its tumor segmentation accuracy is comparable to that of the current state of the art; and that it captures most organs-at-risk sufficiently well for radiation therapy planning purposes. The proposed method may be a valuable step towards automating the delineation of brain tumors and organs-at-risk in glioblastoma patients undergoing radiation therapy.

AB - In this paper we present a method for simultaneously segmenting brain tumors and an extensive set of organs-at-risk for radiation therapy planning of glioblastomas. The method combines a contrast-adaptive generative model for whole-brain segmentation with a new spatial regularization model of tumor shape using convolutional restricted Boltzmann machines. We demonstrate experimentally that the method is able to adapt to image acquisitions that differ substantially from any available training data, ensuring its applicability across treatment sites; that its tumor segmentation accuracy is comparable to that of the current state of the art; and that it captures most organs-at-risk sufficiently well for radiation therapy planning purposes. The proposed method may be a valuable step towards automating the delineation of brain tumors and organs-at-risk in glioblastoma patients undergoing radiation therapy.

KW - Generative probabilistic model

KW - Glioma

KW - Restricted Boltzmann machine

KW - Whole-brain segmentation

U2 - 10.1016/j.media.2019.03.005

DO - 10.1016/j.media.2019.03.005

M3 - Journal article

VL - 54

SP - 220

EP - 237

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -

Agn M, Munck af Rosenschöld P, Puonti O, Lundemann MJ, Mancini L, Papadaki A et al. A modality-adaptive method for segmenting brain tumors and organs-at-risk in radiation therapy planning. Medical Image Analysis. 2019 May 1;54:220-237. https://doi.org/10.1016/j.media.2019.03.005