Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions
Top Cited Papers
Open Access
- 2 June 2017
- journal article
- research article
- Published by Springer Science and Business Media LLC in Journal of Digital Imaging
- Vol. 30 (4), 449-459
- https://doi.org/10.1007/s10278-017-9983-4
Abstract
Quantitative analysis of brain MRI is routine for many neurological diseases and conditions and relies on accurate segmentation of structures of interest. Deep learning-based segmentation approaches for brain MRI are gaining interest due to their self-learning and generalization ability over large amounts of data. As the deep learning architectures are becoming more mature, they gradually outperform previous state-of-the-art classical machine learning algorithms. This review aims to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First we review the current deep learning architectures used for segmentation of anatomical brain structures and brain lesions. Next, the performance, speed, and properties of deep learning approaches are summarized and discussed. Finally, we provide a critical assessment of the current state and identify likely future developments and trends.Keywords
Funding Information
- National Cancer Institute (U01CA160045, U01CA142555)
This publication has 59 references indexed in Scilit:
- A survey of MRI-based medical image analysis for brain tumor studiesPhysics in Medicine & Biology, 2013
- Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imagingMedical Image Analysis, 2013
- A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesionsNeuroImage, 2010
- Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registrationNeuroImage, 2009
- Construction of a 3D probabilistic atlas of human cortical structuresNeuroImage, 2008
- Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classificationNeuroImage, 2007
- Unified segmentationNeuroImage, 2005
- Simultaneous Truth and Performance Level Estimation (STAPLE): An Algorithm for the Validation of Image SegmentationIEEE Transactions on Medical Imaging, 2004
- Fast robust automated brain extractionHuman Brain Mapping, 2002
- On standardizing the MR image intensity scaleMagnetic Resonance in Medicine, 1999