DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy

By Christian Wachinger, Martin Reuter, Tassilo Johannes Klein. NeuroImage, 2017

353 citations recorded by the source corpus.

ABSTRACT We introduce DeepNAT, a 3D Deep convolutional neural network for the automatic segmentation of NeuroAnaTomy in T1‐weighted magnetic resonance images. DeepNAT is an end‐to‐end learning‐based approach to brain segmentation that jointly learns an abstract feature representation and a multi‐class classification. We propose a 3D patch‐based approach, where we do not only predict the center voxel of the patch but also neighbors, which is formulated as multi‐task learning. To address a class imbalance problem, we arrange two networks hierarchically, where the first one separates foreground from background, and the second one identifies 25 brain structures on the foreground. Since patches lack spatial context, we augment them with coordinates. To this end, we introduce a novel intrinsic parameterization of the brain volume, formed by eigenfunctions of the Laplace‐Beltrami operator. As network architecture, we use three convolutional layers with pooling, batch normalization, and non‐linearities, followed by fully connected layers with dropout. The final segmentation is inferred from the probabilistic output of the network with a 3D fully connected conditional random field, which ensures label agreement between close voxels. The roughly 2.7 million parameters in the network are learned with stochastic gradient descent. Our results show that DeepNAT compares favorably to state‐of‐the‐art methods. Finally, the purely learning‐based method may have a high potential for the adaptation to young, old, or diseased brains by fine‐tuning the pre‐trained network with a small training sample on the target application, where the availability of larger datasets with manual annotations may boost the overall segmentation accuracy in the future. HIGHLIGHTSBrain segmentation with deep convolutional neural network.Jointly learned feature representation and classification.Multi‐task learning for brain segmentation.Hierarchal segmentation to address class imbalance.Spectral coordinates for intrinsic brain parameterization.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/542c57d7fd240c7c0a7f891b9dbb7a63d64b8b4a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

FastSurfer - A fast and accurate deep learning based neuroimaging pipeline (2019, neutral): “Most of these brain segmentation networks were trained on extracted 3D patches (de Br ^ ebisson and Montana, 2015; Wachinger et al., 2018; Mehta et al., 2017) or 2D slices (Moeskops et al., 2016; Roy et al., 2017, 2019; Jog et al., 2019).”
Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review (2017, methodology): “This category was popular in the literature [14, 16, 22, 29, 76, 120, 128] perhaps due to its fast computation and simplicity compared to multi-path architectures.”
Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI (2018, background): “…approach has found usage in diﬀerent types of segmentation tasks in MRI, for example brain tumor segmentation in [57, 58, 59], white matter segmentation in multiple sclerosis patients [60], segmentation of 25 diﬀerent structures in brain [61], and for rectal cancer segmentation in pelvis MRI [62].”
Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation (2019, methodology): “spectral coordinates characterization by Wachinger et al. (2018) for neuroanatomy segmentation in MR Images.”
A Survey of Deep Learning for Scientific Discovery (2020, background): “Examples include segmenting brain MR images [156, 236], identifying key regions of cells in diﬀerent tissues [254, 217] and even studying bone structure [129].”
3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles (2019, neutral): “Recently, DeepNAT [46]”
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, background): “Recent research has focused on important tasks such as deep learning based brain extraction [111], cortical and subcortical segmentation [112], [113], [114], [115], and tumor and lesion segmentation [116], [117].”
Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks (2017, methodology): “This includes automatic segmentation of brain lesions [2,10], tumors [9,15,21], and neuroanatomy [14,22,3], using voxelwise network architectures [14,9,17], and more recently using 3D voxelwise networks [3,10], and fully convolutional networks (FCNs) [4,13,17].”