Brain Tumor Segmentation and Survival Prediction Using Multimodal MRI Scans With Deep Learning

Gliomas are the most common primary brain malignancies. Accurate and robust tumor segmentation and prediction of patients' overall survival are important for diagnosis, treatment planning and risk factor identification. Here we present a deep learning-based framework for brain tumor segmentatio...

Full description

Saved in:
Bibliographic Details
Published inFrontiers in neuroscience Vol. 13; p. 810
Main Authors Sun, Li, Zhang, Songtao, Chen, Hang, Luo, Lin
Format Journal Article
LanguageEnglish
Published Switzerland Frontiers Research Foundation 16.08.2019
Frontiers Media S.A
Subjects
3D CNN
Automation
Brain cancer
brain tumor segmentation
Brain tumors
Decision making
Deep learning
Diabetic retinopathy
Edema
Genotype & phenotype
Glioma
Image processing
International conferences
Magnetic resonance imaging
Medical imaging
multimodal MRI
Neural networks
Neuroscience
NMR
Nuclear magnetic resonance
Patients
Performance evaluation
Radiomics
Risk factors
Segmentation
Survival
survival prediction
Tumors
Beijing China
China
3D CNN
deep learning
survival prediction
brain tumor segmentation
multimodal MRI
Online AccessGet full text

Cover

More Information
Summary:Gliomas are the most common primary brain malignancies. Accurate and robust tumor segmentation and prediction of patients' overall survival are important for diagnosis, treatment planning and risk factor identification. Here we present a deep learning-based framework for brain tumor segmentation and survival prediction in glioma, using multimodal MRI scans. For tumor segmentation, we use ensembles of three different 3D CNN architectures for robust performance through a majority rule. This approach can effectively reduce model bias and boost performance. For survival prediction, we extract 4,524 radiomic features from segmented tumor regions, then, a decision tree and cross validation are used to select potent features. Finally, a random forest model is trained to predict the overall survival of patients. The 2018 MICCAI Multimodal Brain Tumor Segmentation Challenge (BraTS), ranks our method at 2nd and 5th place out of 60+ participating teams for survival prediction tasks and segmentation tasks respectively, achieving a promising 61.0% accuracy on the classification of short-survivors, mid-survivors and long-survivors.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Reviewed by: Adriano Pinto, University of Minho, Portugal; Dong-Hoon Lee, University of Sydney, Australia
Edited by: Spyridon Bakas, University of Pennsylvania, United States
This article was submitted to Brain Imaging Methods, a section of the journal Frontiers in Neuroscience
ISSN:1662-453X
1662-4548
1662-453X
DOI:10.3389/fnins.2019.00810