Accurate and Consistent Hippocampus Segmentation Through Convolutional LSTM and View Ensemble

In this work, a novel deep neural network is developed to automatically segment human hippocampi from MR images. To take advantage of the efficiency of 2D convolutional operations, as well the inter-slice dependence within 3D volumes, our model stacks fully convolutional neural networks (CNN) throug...

Full description

Saved in:
Bibliographic Details
Published inMachine Learning in Medical Imaging pp. 88 - 96
Main Authors Chen, Yani, Shi, Bibo, Wang, Zhewei, Sun, Tao, Smith, Charles D., Liu, Jundong
Format Book Chapter
LanguageEnglish
Published Cham Springer International Publishing 07.09.2017
SeriesLecture Notes in Computer Science
Subjects
Brain
CNN
Hippocampus segmentation
LSTM
MRI
Online AccessGet full text

Cover

More Information
Summary:In this work, a novel deep neural network is developed to automatically segment human hippocampi from MR images. To take advantage of the efficiency of 2D convolutional operations, as well the inter-slice dependence within 3D volumes, our model stacks fully convolutional neural networks (CNN) through convolutional long short-term memory (CLSTM) to extract voxel labels. Enhanced slice-wise label consistency is ensured, leading to improved segmentation stability and accuracy. We apply our model on ADNI dataset, and demonstrate that our proposed model outperforms the state-of-the-art solutions.
ISBN:9783319673882
3319673882
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-67389-9_11