Prediction of MGMT Methylation Status of Glioblastoma Using Radiomics and Latent Space Shape Features

Sveinn Pálsson; Stefano Cerri; Koen Van Leemput

doi:10.1007/978-3-031-09002-8_20

Prediction of MGMT Methylation Status of Glioblastoma Using Radiomics and Latent Space Shape Features

Sveinn Pálsson^*, Stefano Cerri, Koen Van Leemput

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

In this paper we propose a method for predicting the status of MGMT promoter methylation in high-grade gliomas. From the available MR images, we segment the tumor using deep convolutional neural networks and extract both radiomic features and shape features learned by a variational autoencoder. We implemented a standard machine learning workflow to obtain predictions, consisting of feature selection followed by training of a random forest classification model. We trained and evaluated our method on the RSNA-ASNR-MICCAI BraTS 2021 challenge dataset and submitted our predictions to the challenge.

Original language	English
Title of host publication	Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries - 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Revised Selected Papers : 7th International Workshop, BrainLes 2021 Held in Conjunction with MICCAI 2021 Virtual Event, September 27, 2021 Revised Selected Papers, Part II
Publisher	Springer
Publication date	2022
Pages	222-231
ISBN (Print)	978-3-031-09001-1
ISBN (Electronic)	978-3-031-09002-8
DOIs	https://doi.org/10.1007/978-3-031-09002-8_20
Publication status	Published - 2022
Event	7th International Brain Lesion Workshop - Virtual, Online Duration: 27 Sept 2021 → …

Workshop

Workshop	7th International Brain Lesion Workshop
City	Virtual, Online
Period	27/09/2021 → …

Keywords

Deep learning
Glioblastoma
MGMT prediction
Radiomics
Variational autoencoder

Access to Document

10.1007/978-3-031-09002-8_20

OpenUrl availability

Full text

Cite this

Pálsson, S., Cerri, S., & Van Leemput, K. (2022). Prediction of MGMT Methylation Status of Glioblastoma Using Radiomics and Latent Space Shape Features. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries - 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Revised Selected Papers: 7th International Workshop, BrainLes 2021 Held in Conjunction with MICCAI 2021 Virtual Event, September 27, 2021 Revised Selected Papers, Part II (pp. 222-231). Springer. https://doi.org/10.1007/978-3-031-09002-8_20

Pálsson, Sveinn ; Cerri, Stefano ; Van Leemput, Koen. / Prediction of MGMT Methylation Status of Glioblastoma Using Radiomics and Latent Space Shape Features. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries - 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Revised Selected Papers: 7th International Workshop, BrainLes 2021 Held in Conjunction with MICCAI 2021 Virtual Event, September 27, 2021 Revised Selected Papers, Part II. Springer, 2022. pp. 222-231

@inproceedings{0c3e4b70862c4c3a887e7f9c1b8839c5,

title = "Prediction of MGMT Methylation Status of Glioblastoma Using Radiomics and Latent Space Shape Features",

abstract = "In this paper we propose a method for predicting the status of MGMT promoter methylation in high-grade gliomas. From the available MR images, we segment the tumor using deep convolutional neural networks and extract both radiomic features and shape features learned by a variational autoencoder. We implemented a standard machine learning workflow to obtain predictions, consisting of feature selection followed by training of a random forest classification model. We trained and evaluated our method on the RSNA-ASNR-MICCAI BraTS 2021 challenge dataset and submitted our predictions to the challenge.",

keywords = "Deep learning, Glioblastoma, MGMT prediction, Radiomics, Variational autoencoder",

author = "Sveinn P{\'a}lsson and Stefano Cerri and {Van Leemput}, Koen",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 7th International Brain Lesion Workshop, BrainLes ; Conference date: 27-09-2021",

year = "2022",

doi = "10.1007/978-3-031-09002-8_20",

language = "English",

isbn = "978-3-031-09001-1",

pages = "222--231",

booktitle = "Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries - 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Revised Selected Papers",

publisher = "Springer",

}

Pálsson, S, Cerri, S & Van Leemput, K 2022, Prediction of MGMT Methylation Status of Glioblastoma Using Radiomics and Latent Space Shape Features. in Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries - 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Revised Selected Papers: 7th International Workshop, BrainLes 2021 Held in Conjunction with MICCAI 2021 Virtual Event, September 27, 2021 Revised Selected Papers, Part II. Springer, pp. 222-231, 7th International Brain Lesion Workshop, Virtual, Online, 27/09/2021. https://doi.org/10.1007/978-3-031-09002-8_20

Prediction of MGMT Methylation Status of Glioblastoma Using Radiomics and Latent Space Shape Features. / Pálsson, Sveinn; Cerri, Stefano; Van Leemput, Koen.
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries - 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Revised Selected Papers: 7th International Workshop, BrainLes 2021 Held in Conjunction with MICCAI 2021 Virtual Event, September 27, 2021 Revised Selected Papers, Part II. Springer, 2022. p. 222-231.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Prediction of MGMT Methylation Status of Glioblastoma Using Radiomics and Latent Space Shape Features

AU - Pálsson, Sveinn

AU - Cerri, Stefano

AU - Van Leemput, Koen

PY - 2022

Y1 - 2022

N2 - In this paper we propose a method for predicting the status of MGMT promoter methylation in high-grade gliomas. From the available MR images, we segment the tumor using deep convolutional neural networks and extract both radiomic features and shape features learned by a variational autoencoder. We implemented a standard machine learning workflow to obtain predictions, consisting of feature selection followed by training of a random forest classification model. We trained and evaluated our method on the RSNA-ASNR-MICCAI BraTS 2021 challenge dataset and submitted our predictions to the challenge.

AB - In this paper we propose a method for predicting the status of MGMT promoter methylation in high-grade gliomas. From the available MR images, we segment the tumor using deep convolutional neural networks and extract both radiomic features and shape features learned by a variational autoencoder. We implemented a standard machine learning workflow to obtain predictions, consisting of feature selection followed by training of a random forest classification model. We trained and evaluated our method on the RSNA-ASNR-MICCAI BraTS 2021 challenge dataset and submitted our predictions to the challenge.

KW - Deep learning

KW - Glioblastoma

KW - MGMT prediction

KW - Radiomics

KW - Variational autoencoder

U2 - 10.1007/978-3-031-09002-8_20

DO - 10.1007/978-3-031-09002-8_20

M3 - Article in proceedings

AN - SCOPUS:85135195470

SN - 978-3-031-09001-1

SP - 222

EP - 231

BT - Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries - 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Revised Selected Papers

PB - Springer

T2 - 7th International Brain Lesion Workshop

Y2 - 27 September 2021

ER -

Pálsson S, Cerri S, Van Leemput K. Prediction of MGMT Methylation Status of Glioblastoma Using Radiomics and Latent Space Shape Features. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries - 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Revised Selected Papers: 7th International Workshop, BrainLes 2021 Held in Conjunction with MICCAI 2021 Virtual Event, September 27, 2021 Revised Selected Papers, Part II. Springer. 2022. p. 222-231 doi: 10.1007/978-3-031-09002-8_20