3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles

By Yuankai Huo, Zhoubing Xu, Yunxi Xiong, Katherine Aboud, P. Parvathaneni, Shunxing Bao, Camilo Bermudez, Susan M. Resnick, Laurie E. Cutting, Bennett A. Landman. NeuroImage, 2019

296 citations recorded by the source corpus.

Detailed whole brain segmentation is an essential quantitative technique in medical image analysis, which provides a non-invasive way of measuring brain regions from a clinical acquired structural magnetic resonance imaging (MRI). Recently, deep convolution neural network (CNN) has been applied to whole brain segmentation. However, restricted by current GPU memory, 2D based methods, downsampling based 3D CNN methods, and patch-based high-resolution 3D CNN methods have been the de facto standard solutions. 3D patch-based high resolution methods typically yield superior performance among CNN approaches on detailed whole brain segmentation (>100 labels), however, whose performance are still commonly inferior compared with state-of-the-art multi-atlas segmentation methods (MAS) due to the following challenges: (1) a single network is typically used to learn both spatial and contextual information for the patches, (2) limited manually traced whole brain volumes are available (typically less than 50) for training a network. In this work, we propose the spatially localized atlas network tiles (SLANT) method to distribute multiple independent 3D fully convolutional networks (FCN) for high-resolution whole brain segmentation. To address the first challenge, multiple spatially distributed networks were used in the SLANT method, in which each network learned contextual information for a fixed spatial location. To address the second challenge, auxiliary labels on 5111 initially unlabeled scans were created by multi-atlas segmentation for training. Since the method integrated multiple traditional medical image processing methods with deep learning, we developed a containerized pipeline to deploy the end-to-end solution. From the results, the proposed method achieved superior performance compared with multi-atlas segmentation methods, while reducing the computational time from >30 hours to 15 minutes. The method has been made available in open source (https://github.com/MASILab/SLANTbrainSeg).

Subfields: Computer Vision and Pattern Recognition, Neurology

View Paper: https://www.semanticscholar.org/paper/dbd9c471ff1b9ead9241c75a54bb6826cf9b4f79

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 Neurology

Citations in the corpus

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, methodology): “Recent research has focused on important tasks, such as DL-based brain extraction [123], cortical and subcortical segmentation [124]–[127], and tumor and lesion segmentation [128], [129].”
FastSurfer - A fast and accurate deep learning based neuroimaging pipeline (2019, unknown): “…so far have runtimes of around 15 – 60 min on the GPU (de Br ^ ebisson and Montana, 2015; Moe-skops et al., 2016; Mehta et al., 2017; Wachinger et al., 2018; Huo et al., 2019; Coup (cid:1) e et al., 2019) which makes them unattractive for integration into a maximally fast neuroimaging pipeline.”
Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images (2022, background): “Furthermore, automated medical image segmentation techniques [18] have shown prominence for providing an accurate and reproducible solution for brain tumor delineation.”