Automatic Brain Tumor Segmentation with Domain Adaptation

Deep convolution neural networks, in particular, the encoder-decoder networks, have been extensively used in image segmentation. We develop a deep learning approach for tumor segmentation by combining a modified U-Net and its domain-adapted version (DAU-Net). We divide training samples into two domains according to preliminary segmentation results, and then equip the modified U-Net with domain adaptation structure to obtain a domain invariant feature representation. Our proposed segmentation approach is applied to the BraTS 2018 challenge for brain tumor segmentation, and achieves the mean dice score of 0.91044, 0.85057 and 0.80536 for whole tumor, tumor core and enhancing tumor, respectively, on the challenge’s validation data set.

[1]  Andrea Vedaldi,et al.  Instance Normalization: The Missing Ingredient for Fast Stylization , 2016, ArXiv.

[2]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Trevor Darrell,et al.  Simultaneous Deep Transfer Across Domains and Tasks , 2015, ICCV.

[4]  Christos Davatzikos,et al.  Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features , 2017, Scientific Data.

[5]  Jing Huo,et al.  Sampling-based ensemble segmentation against inter-operator variability , 2011, Medical Imaging.

[6]  Hongtu Zhu,et al.  TPCNN: Two-Phase Patch-Based Convolutional Neural Network for Automatic Brain Tumor Segmentation and Survival Prediction , 2017, BrainLes@MICCAI.

[7]  Konstantinos Kamnitsas,et al.  Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation , 2017, BrainLes@MICCAI.

[8]  Kaiming He,et al.  Group Normalization , 2018, ECCV.

[9]  et al.,et al.  Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge , 2018, ArXiv.

[10]  Arno Klein,et al.  Large-scale evaluation of ANTs and FreeSurfer cortical thickness measurements , 2014, NeuroImage.

[11]  Malik Magdon-Ismail,et al.  Examining the Use of Neural Networks for Feature Extraction: A Comparative Analysis using Deep Learning, Support Vector Machines, and K-Nearest Neighbor Classifiers , 2018, ArXiv.

[12]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[13]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[15]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[16]  Klaus H. Maier-Hein,et al.  Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge , 2017, BrainLes@MICCAI.

[17]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[18]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[19]  Hongtu Zhu,et al.  A label-fusion-aided convolutional neural network for isointense infant brain tissue segmentation , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).