Sequential neural networks for biologically informed glioma segmentation

Andrew Beers, Ken Chang, James Brown, Elizabeth Gerstner, Bruce Rosen, Jayashree Kalpathy-Cramer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In the last five years, advances in processing power and computational efficiency in graphical processing units have catalyzed dozens of deep neural network segmentation algorithms for a variety of target tissues and malignancies. However, few of these algorithms preconfigure any biological context of their chosen segmentation tissues, instead relying on the neural network's optimizer to develop such associations de novo. We present a novel method for applying deep neural networks to the problem of glioma tissue segmentation that takes into account the structured nature of gliomas-edematous tissue surrounding mutually-exclusive regions of enhancing and non-enhancing tumor. We trained separate deep neural networks with a 3D U-Net architecture in a tree structure to create segmentations for edema, non-enhancing tumor, and enhancing tumor regions. Specifically, training was configured such that the whole tumor region including edema was predicted first, and its output segmentation was fed as input into separate models to predict enhancing and non-enhancing tumor. We trained our model on publicly available pre- and post-contrast T1 images, T2 images, and FLAIR images, and validated our trained model on patient data from an ongoing clinical trial.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2018
Subtitle of host publicationImage Processing
PublisherSPIE
Volume10574
ISBN (Electronic)9781510616370
DOIs
StatePublished - Jan 1 2018
Externally publishedYes
EventMedical Imaging 2018: Image Processing - Houston, United States
Duration: Feb 11 2018Feb 13 2018

Other

OtherMedical Imaging 2018: Image Processing
CountryUnited States
CityHouston
Period2/11/182/13/18

Fingerprint

Glioma
Tumors
tumors
Neural networks
Tissue
edema
Neoplasms
Edema
image contrast
power efficiency
Processing
Computational efficiency
education
Clinical Trials
output
Deep neural networks

Keywords

  • Deep Learning
  • Glioma
  • Neural Networks
  • Segmentation

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

Beers, A., Chang, K., Brown, J., Gerstner, E., Rosen, B., & Kalpathy-Cramer, J. (2018). Sequential neural networks for biologically informed glioma segmentation. In Medical Imaging 2018: Image Processing (Vol. 10574). [1057433] SPIE. https://doi.org/10.1117/12.2293941

Sequential neural networks for biologically informed glioma segmentation. / Beers, Andrew; Chang, Ken; Brown, James; Gerstner, Elizabeth; Rosen, Bruce; Kalpathy-Cramer, Jayashree.

Medical Imaging 2018: Image Processing. Vol. 10574 SPIE, 2018. 1057433.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Beers, A, Chang, K, Brown, J, Gerstner, E, Rosen, B & Kalpathy-Cramer, J 2018, Sequential neural networks for biologically informed glioma segmentation. in Medical Imaging 2018: Image Processing. vol. 10574, 1057433, SPIE, Medical Imaging 2018: Image Processing, Houston, United States, 2/11/18. https://doi.org/10.1117/12.2293941
Beers A, Chang K, Brown J, Gerstner E, Rosen B, Kalpathy-Cramer J. Sequential neural networks for biologically informed glioma segmentation. In Medical Imaging 2018: Image Processing. Vol. 10574. SPIE. 2018. 1057433 https://doi.org/10.1117/12.2293941
Beers, Andrew ; Chang, Ken ; Brown, James ; Gerstner, Elizabeth ; Rosen, Bruce ; Kalpathy-Cramer, Jayashree. / Sequential neural networks for biologically informed glioma segmentation. Medical Imaging 2018: Image Processing. Vol. 10574 SPIE, 2018.
@inproceedings{f85c34a6dbe94318b77202a48301c684,
title = "Sequential neural networks for biologically informed glioma segmentation",
abstract = "In the last five years, advances in processing power and computational efficiency in graphical processing units have catalyzed dozens of deep neural network segmentation algorithms for a variety of target tissues and malignancies. However, few of these algorithms preconfigure any biological context of their chosen segmentation tissues, instead relying on the neural network's optimizer to develop such associations de novo. We present a novel method for applying deep neural networks to the problem of glioma tissue segmentation that takes into account the structured nature of gliomas-edematous tissue surrounding mutually-exclusive regions of enhancing and non-enhancing tumor. We trained separate deep neural networks with a 3D U-Net architecture in a tree structure to create segmentations for edema, non-enhancing tumor, and enhancing tumor regions. Specifically, training was configured such that the whole tumor region including edema was predicted first, and its output segmentation was fed as input into separate models to predict enhancing and non-enhancing tumor. We trained our model on publicly available pre- and post-contrast T1 images, T2 images, and FLAIR images, and validated our trained model on patient data from an ongoing clinical trial.",
keywords = "Deep Learning, Glioma, Neural Networks, Segmentation",
author = "Andrew Beers and Ken Chang and James Brown and Elizabeth Gerstner and Bruce Rosen and Jayashree Kalpathy-Cramer",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2293941",
language = "English (US)",
volume = "10574",
booktitle = "Medical Imaging 2018",
publisher = "SPIE",

}

TY - GEN

T1 - Sequential neural networks for biologically informed glioma segmentation

AU - Beers, Andrew

AU - Chang, Ken

AU - Brown, James

AU - Gerstner, Elizabeth

AU - Rosen, Bruce

AU - Kalpathy-Cramer, Jayashree

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In the last five years, advances in processing power and computational efficiency in graphical processing units have catalyzed dozens of deep neural network segmentation algorithms for a variety of target tissues and malignancies. However, few of these algorithms preconfigure any biological context of their chosen segmentation tissues, instead relying on the neural network's optimizer to develop such associations de novo. We present a novel method for applying deep neural networks to the problem of glioma tissue segmentation that takes into account the structured nature of gliomas-edematous tissue surrounding mutually-exclusive regions of enhancing and non-enhancing tumor. We trained separate deep neural networks with a 3D U-Net architecture in a tree structure to create segmentations for edema, non-enhancing tumor, and enhancing tumor regions. Specifically, training was configured such that the whole tumor region including edema was predicted first, and its output segmentation was fed as input into separate models to predict enhancing and non-enhancing tumor. We trained our model on publicly available pre- and post-contrast T1 images, T2 images, and FLAIR images, and validated our trained model on patient data from an ongoing clinical trial.

AB - In the last five years, advances in processing power and computational efficiency in graphical processing units have catalyzed dozens of deep neural network segmentation algorithms for a variety of target tissues and malignancies. However, few of these algorithms preconfigure any biological context of their chosen segmentation tissues, instead relying on the neural network's optimizer to develop such associations de novo. We present a novel method for applying deep neural networks to the problem of glioma tissue segmentation that takes into account the structured nature of gliomas-edematous tissue surrounding mutually-exclusive regions of enhancing and non-enhancing tumor. We trained separate deep neural networks with a 3D U-Net architecture in a tree structure to create segmentations for edema, non-enhancing tumor, and enhancing tumor regions. Specifically, training was configured such that the whole tumor region including edema was predicted first, and its output segmentation was fed as input into separate models to predict enhancing and non-enhancing tumor. We trained our model on publicly available pre- and post-contrast T1 images, T2 images, and FLAIR images, and validated our trained model on patient data from an ongoing clinical trial.

KW - Deep Learning

KW - Glioma

KW - Neural Networks

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85047349114&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047349114&partnerID=8YFLogxK

U2 - 10.1117/12.2293941

DO - 10.1117/12.2293941

M3 - Conference contribution

AN - SCOPUS:85047349114

VL - 10574

BT - Medical Imaging 2018

PB - SPIE

ER -