Dose distribution as outcome predictor for Gamma Knife radiosurgery on vestibular schwannoma

Patrick Langenhuizen, Hans van Gorp, Sveta Zinger, H.B. Verheul, Sieger Leenstra, Peter de With

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Vestibular schwannomas are benign brain tumors that can be treated radiosurgically with the Gamma Knife in order to stop tumor progression. However, in some cases tumor progression is not stopped and treatment is deemed a failure. At present, the reason for these failed treatments is unknown. Clinical factors and MRI characteristics have been considered as prognostic factors. Another confounder in the success of treatment is the treatment planning itself. It is thought to be very uniformly planned, even though dose distributions among treatment plans are highly inhomogeneous. This paper explores the predictive value of these dose distributions for the treatment outcome. We compute homogeneity indices (HI) and three-dimensional histogram-of-oriented gradients (3D-HOG) and employ support vector machine (SVM) paired with principal component analysis (PCA) for classification. In a clinical dataset, consisting of 20 tumors that showed treatment failure and 20 tumors showing treatment success, we discover that the correlation of the HI values with the treatment outcome presents no statistical evidence of an association (52:5% accuracy employing linear SVM and no statistical significant difference with t-tests), whereas the 3D-HOG features concerning the dose distribution do present correlations to the treatment outcome, suggesting the influence of the treatment on the outcome itself (77:5% accuracy employing linear SVM and PCA). These findings can provide a basis for refining towards personalized treatments and prediction of treatment efficiency. However, larger datasets are needed for more extensive analysis.
Original languageEnglish
Title of host publicationMedical Imaging 2019: Computer-Aided Diagnosis
EditorsKensaku Mori, Horst K. Hahn
Place of PublicationHoboken
PublisherSPIE
Number of pages9
ISBN (Electronic)9781510625471
DOIs
Publication statusPublished - 13 Mar 2019
EventSPIE Medical Imaging 2019 - San Diego, United States
Duration: 16 Feb 201921 Feb 2019
http://spie.org/MI/entireprogram/2019-2-20?print=2&SSO=1

Publication series

NameProceedings of SPIE
PublisherSPIE
Volume10950
ISSN (Print)1605-7422

Conference

ConferenceSPIE Medical Imaging 2019
CountryUnited States
CitySan Diego
Period16/02/1921/02/19
Internet address

Fingerprint

Acoustic Neuroma
Radiosurgery
Therapeutics
Principal Component Analysis
Neoplasms
Treatment Failure
Brain Neoplasms

Keywords

  • Classification
  • Dose distribution
  • Gamma Knife radiosurgery
  • Homogeneity index
  • Outcome prediction
  • PCA
  • SVM
  • Threedimensional histogram of oriented gradients
  • Vestibular schwannoma
  • homogeneity index
  • three-dimensional histogram of oriented gradients
  • classification
  • outcome prediction
  • dose distribution
  • vestibular schwannoma

Cite this

Langenhuizen, P., van Gorp, H., Zinger, S., Verheul, H. B., Leenstra, S., & de With, P. (2019). Dose distribution as outcome predictor for Gamma Knife radiosurgery on vestibular schwannoma. In K. Mori, & H. K. Hahn (Eds.), Medical Imaging 2019: Computer-Aided Diagnosis [109504C] (Proceedings of SPIE; Vol. 10950). Hoboken: SPIE. https://doi.org/10.1117/12.2512472
Langenhuizen, Patrick ; van Gorp, Hans ; Zinger, Sveta ; Verheul, H.B. ; Leenstra, Sieger ; de With, Peter. / Dose distribution as outcome predictor for Gamma Knife radiosurgery on vestibular schwannoma. Medical Imaging 2019: Computer-Aided Diagnosis. editor / Kensaku Mori ; Horst K. Hahn. Hoboken : SPIE, 2019. (Proceedings of SPIE).
@inproceedings{38e24d66909d47b59c46135611582357,
title = "Dose distribution as outcome predictor for Gamma Knife radiosurgery on vestibular schwannoma",
abstract = "Vestibular schwannomas are benign brain tumors that can be treated radiosurgically with the Gamma Knife in order to stop tumor progression. However, in some cases tumor progression is not stopped and treatment is deemed a failure. At present, the reason for these failed treatments is unknown. Clinical factors and MRI characteristics have been considered as prognostic factors. Another confounder in the success of treatment is the treatment planning itself. It is thought to be very uniformly planned, even though dose distributions among treatment plans are highly inhomogeneous. This paper explores the predictive value of these dose distributions for the treatment outcome. We compute homogeneity indices (HI) and three-dimensional histogram-of-oriented gradients (3D-HOG) and employ support vector machine (SVM) paired with principal component analysis (PCA) for classification. In a clinical dataset, consisting of 20 tumors that showed treatment failure and 20 tumors showing treatment success, we discover that the correlation of the HI values with the treatment outcome presents no statistical evidence of an association (52:5{\%} accuracy employing linear SVM and no statistical significant difference with t-tests), whereas the 3D-HOG features concerning the dose distribution do present correlations to the treatment outcome, suggesting the influence of the treatment on the outcome itself (77:5{\%} accuracy employing linear SVM and PCA). These findings can provide a basis for refining towards personalized treatments and prediction of treatment efficiency. However, larger datasets are needed for more extensive analysis.",
keywords = "Classification, Dose distribution, Gamma Knife radiosurgery, Homogeneity index, Outcome prediction, PCA, SVM, Threedimensional histogram of oriented gradients, Vestibular schwannoma, homogeneity index, three-dimensional histogram of oriented gradients, classification, outcome prediction, dose distribution, vestibular schwannoma",
author = "Patrick Langenhuizen and {van Gorp}, Hans and Sveta Zinger and H.B. Verheul and Sieger Leenstra and {de With}, Peter",
year = "2019",
month = "3",
day = "13",
doi = "10.1117/12.2512472",
language = "English",
series = "Proceedings of SPIE",
publisher = "SPIE",
editor = "Kensaku Mori and Hahn, {Horst K.}",
booktitle = "Medical Imaging 2019: Computer-Aided Diagnosis",
address = "United States",

}

Langenhuizen, P, van Gorp, H, Zinger, S, Verheul, HB, Leenstra, S & de With, P 2019, Dose distribution as outcome predictor for Gamma Knife radiosurgery on vestibular schwannoma. in K Mori & HK Hahn (eds), Medical Imaging 2019: Computer-Aided Diagnosis., 109504C, Proceedings of SPIE, vol. 10950, SPIE, Hoboken, SPIE Medical Imaging 2019, San Diego, United States, 16/02/19. https://doi.org/10.1117/12.2512472

Dose distribution as outcome predictor for Gamma Knife radiosurgery on vestibular schwannoma. / Langenhuizen, Patrick; van Gorp, Hans; Zinger, Sveta; Verheul, H.B.; Leenstra, Sieger; de With, Peter.

Medical Imaging 2019: Computer-Aided Diagnosis. ed. / Kensaku Mori; Horst K. Hahn. Hoboken : SPIE, 2019. 109504C (Proceedings of SPIE; Vol. 10950).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Dose distribution as outcome predictor for Gamma Knife radiosurgery on vestibular schwannoma

AU - Langenhuizen, Patrick

AU - van Gorp, Hans

AU - Zinger, Sveta

AU - Verheul, H.B.

AU - Leenstra, Sieger

AU - de With, Peter

PY - 2019/3/13

Y1 - 2019/3/13

N2 - Vestibular schwannomas are benign brain tumors that can be treated radiosurgically with the Gamma Knife in order to stop tumor progression. However, in some cases tumor progression is not stopped and treatment is deemed a failure. At present, the reason for these failed treatments is unknown. Clinical factors and MRI characteristics have been considered as prognostic factors. Another confounder in the success of treatment is the treatment planning itself. It is thought to be very uniformly planned, even though dose distributions among treatment plans are highly inhomogeneous. This paper explores the predictive value of these dose distributions for the treatment outcome. We compute homogeneity indices (HI) and three-dimensional histogram-of-oriented gradients (3D-HOG) and employ support vector machine (SVM) paired with principal component analysis (PCA) for classification. In a clinical dataset, consisting of 20 tumors that showed treatment failure and 20 tumors showing treatment success, we discover that the correlation of the HI values with the treatment outcome presents no statistical evidence of an association (52:5% accuracy employing linear SVM and no statistical significant difference with t-tests), whereas the 3D-HOG features concerning the dose distribution do present correlations to the treatment outcome, suggesting the influence of the treatment on the outcome itself (77:5% accuracy employing linear SVM and PCA). These findings can provide a basis for refining towards personalized treatments and prediction of treatment efficiency. However, larger datasets are needed for more extensive analysis.

AB - Vestibular schwannomas are benign brain tumors that can be treated radiosurgically with the Gamma Knife in order to stop tumor progression. However, in some cases tumor progression is not stopped and treatment is deemed a failure. At present, the reason for these failed treatments is unknown. Clinical factors and MRI characteristics have been considered as prognostic factors. Another confounder in the success of treatment is the treatment planning itself. It is thought to be very uniformly planned, even though dose distributions among treatment plans are highly inhomogeneous. This paper explores the predictive value of these dose distributions for the treatment outcome. We compute homogeneity indices (HI) and three-dimensional histogram-of-oriented gradients (3D-HOG) and employ support vector machine (SVM) paired with principal component analysis (PCA) for classification. In a clinical dataset, consisting of 20 tumors that showed treatment failure and 20 tumors showing treatment success, we discover that the correlation of the HI values with the treatment outcome presents no statistical evidence of an association (52:5% accuracy employing linear SVM and no statistical significant difference with t-tests), whereas the 3D-HOG features concerning the dose distribution do present correlations to the treatment outcome, suggesting the influence of the treatment on the outcome itself (77:5% accuracy employing linear SVM and PCA). These findings can provide a basis for refining towards personalized treatments and prediction of treatment efficiency. However, larger datasets are needed for more extensive analysis.

KW - Classification

KW - Dose distribution

KW - Gamma Knife radiosurgery

KW - Homogeneity index

KW - Outcome prediction

KW - PCA

KW - SVM

KW - Threedimensional histogram of oriented gradients

KW - Vestibular schwannoma

KW - homogeneity index

KW - three-dimensional histogram of oriented gradients

KW - classification

KW - outcome prediction

KW - dose distribution

KW - vestibular schwannoma

UR - http://www.scopus.com/inward/record.url?scp=85068131642&partnerID=8YFLogxK

U2 - 10.1117/12.2512472

DO - 10.1117/12.2512472

M3 - Conference contribution

T3 - Proceedings of SPIE

BT - Medical Imaging 2019: Computer-Aided Diagnosis

A2 - Mori, Kensaku

A2 - Hahn, Horst K.

PB - SPIE

CY - Hoboken

ER -

Langenhuizen P, van Gorp H, Zinger S, Verheul HB, Leenstra S, de With P. Dose distribution as outcome predictor for Gamma Knife radiosurgery on vestibular schwannoma. In Mori K, Hahn HK, editors, Medical Imaging 2019: Computer-Aided Diagnosis. Hoboken: SPIE. 2019. 109504C. (Proceedings of SPIE). https://doi.org/10.1117/12.2512472