3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles
| Autor: | Prasanna Parvathaneni, Zhoubing Xu, Camilo Bermudez, Laurie E. Cutting, Susan M. Resnick, Yunxi Xiong, Shunxing Bao, Bennett A. Landman, Katherine S. Aboud, Yuankai Huo |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer science Cognitive Neuroscience Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Image processing Neuroimaging Convolutional neural network 050105 experimental psychology Article Upsampling 03 medical and health sciences 0302 clinical medicine Atlases as Topic Deep Learning Imaging Three-Dimensional Image Processing Computer-Assisted Brain segmentation Humans 0501 psychology and cognitive sciences Segmentation business.industry Deep learning 05 social sciences Brain Pattern recognition Pipeline (software) Magnetic Resonance Imaging Neurology Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | Neuroimage |
| Popis: | 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 h to 15 min. The method has been made available in open source ( https://github.com/MASILab/SLANTbrainSeg ). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|