Next Article in Journal
Intraobserver Variability in Bladder Cancer Treatment Response Assessment With and Without Computerized Decision Support
Previous Article in Journal
Repeatability and Reproducibility of ADC Histogram Metrics from the ACRIN 6698 Breast Cancer Therapy Response Trial
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Tomography
Volume 6
Issue 2
10.18383/j.tom.2019.00026
tomography-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
Tomography is published by MDPI from Volume 7 Issue 1 (2021). Previous articles were published by another publisher in Open Access under a CC-BY (or CC-BY-NC-ND) licence, and they are hosted by MDPI on mdpi.com as a courtesy and upon agreement with Grapho, LLC.
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Fully Automated Deep Learning Network for Brain Tumor Segmentation

by
Chandan Ganesh Bangalore Yogananda
1,
Bhavya R. Shah
1,
Maryam Vejdani-Jahromi
1,
Sahil S. Nalawade
1,
Gowtham K. Murugesan
1,
Frank F. Yu
1,
Marco C. Pinho
1,
Benjamin C. Wagner
1,
Kyrre E. Emblem
2,
Atle Bjørnerud
3,
Baowei Fei
4,
Ananth J. Madhuranthakam
1 and
Joseph A. Maldjian
1,*
1
Department of Radiology, UT Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9178, USA
2
Department of Diagnostic Physics, Division of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway
3
Computational Radiology and Artificial Intelligence (CRAI), Division of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway
4
Department of Bioengineering, The University of Texas at Dallas, Richardson, TX, USA
*
Author to whom correspondence should be addressed.
Tomography 2020, 6(2), 186-193; https://doi.org/10.18383/j.tom.2019.00026
Submission received: 11 March 2020 / Revised: 12 April 2020 / Accepted: 10 May 2020 / Published: 1 June 2020
Versions Notes

Abstract

We developed a fully automated method for brain tumor segmentation using deep learning; 285 brain tumor cases with multiparametric magnetic resonance images from the BraTS2018 data set were used. We designed 3 separate 3D-Dense-UNets to simplify the complex multiclass segmentation problem into individual binary-segmentation problems for each subcomponent. We implemented a 3-fold cross-validation to generalize the network's performance. The mean cross-validation Dice-scores for whole tumor (WT), tumor core (TC), and enhancing tumor (ET) segmentations were 0.92, 0.84, and 0.80, respectively. We then retrained the individual binary-segmentation networks using 265 of the 285 cases, with 20 cases held-out for testing. We also tested the network on 46 cases from the BraTS2017 validation data set, 66 cases from the BraTS2018 validation data set, and 52 cases from an independent clinical data set. The average Dice-scores for WT, TC, and ET were 0.90, 0.84, and 0.80, respectively, on the 20 held-out testing cases. The average Dice-scores for WT, TC, and ET on the BraTS2017 validation data set, the BraTS2018 validation data set, and the clinical data set were as follows: 0.90, 0.80, and 0.78; 0.90, 0.82, and 0.80; and 0.85, 0.80, and 0.77, respectively. A fully automated deep learning method was developed to segment brain tumors into their subcomponents, which achieved high prediction accuracy on the BraTS data set and on the independent clinical data set. This method is promising for implementation into a clinical workflow.
Keywords: brain tumor segmentation; deep learning; BraTS; machine learning; CNN (convolutional neural networks); MRI; Dense UNet brain tumor segmentation; deep learning; BraTS; machine learning; CNN (convolutional neural networks); MRI; Dense UNet

Share and Cite

MDPI and ACS Style

Yogananda, C.G.B.; Shah, B.R.; Vejdani-Jahromi, M.; Nalawade, S.S.; Murugesan, G.K.; Yu, F.F.; Pinho, M.C.; Wagner, B.C.; Emblem, K.E.; Bjørnerud, A.; et al. A Fully Automated Deep Learning Network for Brain Tumor Segmentation. Tomography 2020, 6, 186-193. https://doi.org/10.18383/j.tom.2019.00026

AMA Style

Yogananda CGB, Shah BR, Vejdani-Jahromi M, Nalawade SS, Murugesan GK, Yu FF, Pinho MC, Wagner BC, Emblem KE, Bjørnerud A, et al. A Fully Automated Deep Learning Network for Brain Tumor Segmentation. Tomography. 2020; 6(2):186-193. https://doi.org/10.18383/j.tom.2019.00026

Chicago/Turabian Style

Yogananda, Chandan Ganesh Bangalore, Bhavya R. Shah, Maryam Vejdani-Jahromi, Sahil S. Nalawade, Gowtham K. Murugesan, Frank F. Yu, Marco C. Pinho, Benjamin C. Wagner, Kyrre E. Emblem, Atle Bjørnerud, and et al. 2020. "A Fully Automated Deep Learning Network for Brain Tumor Segmentation" Tomography 6, no. 2: 186-193. https://doi.org/10.18383/j.tom.2019.00026

APA Style

Yogananda, C. G. B., Shah, B. R., Vejdani-Jahromi, M., Nalawade, S. S., Murugesan, G. K., Yu, F. F., Pinho, M. C., Wagner, B. C., Emblem, K. E., Bjørnerud, A., Fei, B., Madhuranthakam, A. J., & Maldjian, J. A. (2020). A Fully Automated Deep Learning Network for Brain Tumor Segmentation. Tomography, 6(2), 186-193. https://doi.org/10.18383/j.tom.2019.00026

Article Metrics

Back to TopTop