Using Synthetic Training Data for Deep Learning-Based GBM Segmentation

Lydia Lindner; Dominik Narnhofer; Maximilian Weber; Christina Gsaxner; Jan Egger; Malgorzata Kolodziej

doi:10.1109/EMBC.2019.8856297

Using Synthetic Training Data for Deep Learning-Based GBM Segmentation

Lydia Lindner, Dominik Narnhofer, Maximilian Weber, Christina Gsaxner, Jan Egger, Malgorzata Kolodziej

Institute of Computer Graphics and Vision (7100)

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

Abstract

In this work, fully automatic binary segmentation of GBMs (glioblastoma multiforme) in 2D magnetic resonance images is presented using a convolutional neural network trained exclusively on synthetic data. The precise segmentation of brain tumors is one of the most complex and challenging tasks in clinical practice and is usually done manually by radiologists or physicians. However, manual delineations are time-consuming, subjective and in general not reproducible. Hence, more advanced automated segmentation techniques are in great demand. After deep learning methods already successfully demonstrated their practical usefulness in other domains, they are now also attracting increasing interest in the field of medical image processing. Using fully convolutional neural networks for medical image segmentation provides considerable advantages, as it is a reliable, fast and objective technique. In the medical …

Original language	English
Title of host publication	2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Publisher	Institute of Electrical and Electronics Engineers
Pages	6724-6729
Number of pages	6
ISBN (Electronic)	978-1-5386-1311-5
DOIs	https://doi.org/10.1109/EMBC.2019.8856297
Publication status	Published - 2019
Event	41st Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: EMBC 2019 - CityCube, Berlin, Germany Duration: 23 Jul 2019 → 27 Jul 2019 Conference number: 41 https://embc.embs.org/2019/

Conference

Conference	41st Annual International Conferences of the IEEE Engineering in Medicine and Biology Society
Abbreviated title	IEEE EMBC 2019
Country/Territory	Germany
City	Berlin
Period	23/07/19 → 27/07/19
Internet address	https://embc.embs.org/2019/

Access to Document

10.1109/EMBC.2019.8856297

Cite this

Lindner, L., Narnhofer, D., Weber, M., Gsaxner, C., Egger, J., & Kolodziej, M. (2019). Using Synthetic Training Data for Deep Learning-Based GBM Segmentation. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 6724-6729). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/EMBC.2019.8856297

Using Synthetic Training Data for Deep Learning-Based GBM Segmentation. / Lindner, Lydia; Narnhofer, Dominik; Weber, Maximilian et al.
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Institute of Electrical and Electronics Engineers, 2019. p. 6724-6729.

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

Lindner, L, Narnhofer, D, Weber, M, Gsaxner, C , Egger, J & Kolodziej, M 2019, Using Synthetic Training Data for Deep Learning-Based GBM Segmentation. in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Institute of Electrical and Electronics Engineers, pp. 6724-6729, 41st Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, Berlin, Berlin, Germany, 23/07/19. https://doi.org/10.1109/EMBC.2019.8856297

@inproceedings{398767a3eb4f4440a81e4a0535860af7,

title = "Using Synthetic Training Data for Deep Learning-Based GBM Segmentation",

abstract = "In this work, fully automatic binary segmentation of GBMs (glioblastoma multiforme) in 2D magnetic resonance images is presented using a convolutional neural network trained exclusively on synthetic data. The precise segmentation of brain tumors is one of the most complex and challenging tasks in clinical practice and is usually done manually by radiologists or physicians. However, manual delineations are time-consuming, subjective and in general not reproducible. Hence, more advanced automated segmentation techniques are in great demand. After deep learning methods already successfully demonstrated their practical usefulness in other domains, they are now also attracting increasing interest in the field of medical image processing. Using fully convolutional neural networks for medical image segmentation provides considerable advantages, as it is a reliable, fast and objective technique. In the medical …",

author = "Lydia Lindner and Dominik Narnhofer and Maximilian Weber and Christina Gsaxner and Jan Egger and Malgorzata Kolodziej",

year = "2019",

doi = "10.1109/EMBC.2019.8856297",

language = "English",

pages = "6724--6729",

booktitle = "2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "41st Annual International Conferences of the IEEE Engineering in Medicine and Biology Society : EMBC 2019, IEEE EMBC 2019 ; Conference date: 23-07-2019 Through 27-07-2019",

url = "https://embc.embs.org/2019/",

}

TY - GEN

T1 - Using Synthetic Training Data for Deep Learning-Based GBM Segmentation

AU - Lindner, Lydia

AU - Narnhofer, Dominik

AU - Weber, Maximilian

AU - Gsaxner, Christina

AU - Egger, Jan

AU - Kolodziej, Malgorzata

N1 - Conference code: 41

PY - 2019

Y1 - 2019

N2 - In this work, fully automatic binary segmentation of GBMs (glioblastoma multiforme) in 2D magnetic resonance images is presented using a convolutional neural network trained exclusively on synthetic data. The precise segmentation of brain tumors is one of the most complex and challenging tasks in clinical practice and is usually done manually by radiologists or physicians. However, manual delineations are time-consuming, subjective and in general not reproducible. Hence, more advanced automated segmentation techniques are in great demand. After deep learning methods already successfully demonstrated their practical usefulness in other domains, they are now also attracting increasing interest in the field of medical image processing. Using fully convolutional neural networks for medical image segmentation provides considerable advantages, as it is a reliable, fast and objective technique. In the medical …

AB - In this work, fully automatic binary segmentation of GBMs (glioblastoma multiforme) in 2D magnetic resonance images is presented using a convolutional neural network trained exclusively on synthetic data. The precise segmentation of brain tumors is one of the most complex and challenging tasks in clinical practice and is usually done manually by radiologists or physicians. However, manual delineations are time-consuming, subjective and in general not reproducible. Hence, more advanced automated segmentation techniques are in great demand. After deep learning methods already successfully demonstrated their practical usefulness in other domains, they are now also attracting increasing interest in the field of medical image processing. Using fully convolutional neural networks for medical image segmentation provides considerable advantages, as it is a reliable, fast and objective technique. In the medical …

U2 - 10.1109/EMBC.2019.8856297

DO - 10.1109/EMBC.2019.8856297

M3 - Conference paper

SP - 6724

EP - 6729

BT - 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

PB - Institute of Electrical and Electronics Engineers

T2 - 41st Annual International Conferences of the IEEE Engineering in Medicine and Biology Society

Y2 - 23 July 2019 through 27 July 2019

ER -

Using Synthetic Training Data for Deep Learning-Based GBM Segmentation

Abstract

Conference

Access to Document

Fingerprint

Cite this