Towards integrating spatial localization in convolutional neural networks for brain image segmentation

Semantic segmentation is an established while rapidly evolving field in medical imaging. In this paper we focus on the segmentation of brain Magnetic Resonance Images (MRI) into cerebral structures using convolutional neural networks (CNN). CNNs achieve good performance by finding effective high dimensional image features describing the patch content only. In this work, we propose different ways to introduce spatial constraints into the network to further reduce prediction inconsistencies. A patch based CNN architecture was trained, making use of multiple scales to gather contextual information. Spatial constraints were introduced within the CNN through a distance to landmarks feature or through the integration of a probability atlas. We demonstrate experimentally that using spatial information helps to reduce segmentation inconsistencies.

[1]  Michaël Sdika.  Enhancing atlas based segmentation with multiclass linear classifiers. , 2015, Medical physics.

[2]  Satrajit S. Ghosh,et al.  Mindboggle: Automated brain labeling with multiple atlases , 2005, BMC Medical Imaging.

[3]  Daniel Rueckert,et al.  Automatic anatomical brain MRI segmentation combining label propagation and decision fusion , 2006, NeuroImage.

[4]  Giovanni Montana,et al.  Deep neural networks for anatomical brain segmentation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[5]  Max A. Viergever,et al.  Automatic Segmentation of MR Brain Images With a Convolutional Neural Network , 2016, IEEE Transactions on Medical Imaging.

[6]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Koen L. Vincken,et al.  Probabilistic segmentation of brain tissue in MR imaging , 2005, NeuroImage.

[8]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[9]  Nico Karssemeijer,et al.  Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin , 2016, NeuroImage: Clinical.

[10]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[11]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[12]  Michael Brady,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[13]  Paul A. Yushkevich,et al.  Multi-atlas segmentation with joint label fusion and corrective learning—an open source implementation , 2013, Front. Neuroinform..

[14]  Nassir Navab,et al.  Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data , 2017, MICCAI.

[15]  Jürgen Schmidhuber,et al.  Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation , 2015, NIPS.

[16]  Arno Klein,et al.  Towards a deep learning approach to brain parcellation , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.