Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging

Aim: Brain tumors are among the most fatal cancers worldwide. Diagnosing and manually segmenting tumors are time-consuming clinical tasks, and success strongly depends on the doctor's experience. Automatic quantitative analysis and accurate segmentation of brain tumors are greatly needed for cancer diagnosis. Methods:This paper presents an advanced three-dimensional multimodal segmentation algorithm called nested dilation networks (NDNs). It is inspired by the U-Net architecture, a convolutional neural network (CNN) developed for biomedical image segmentation and is modified to achieve better performance for brain tumor segmentation. Thus, we propose residual blocks nested with dilations (RnD) in the encoding part to enrich the low-level features and use squeeze-and-excitation (SE) blocks in both the encoding and decoding parts to boost significant features. To prove the reliability of the network structure, we compare our results with those of the standard U-Net and its transmutation networks. Different loss functions are considered to cope with class imbalance problems to maximize the brain tumor segmentation results. A cascade training strategy is employed to run NDNs for coarse-to-fine tumor segmentation. This strategy decomposes the multiclass segmentation problem into three binary segmentation problems and trains each task sequentially. Various augmentation techniques are utilized to increase the diversity of the data to avoid overfitting. Results: This approach achieves Dice similarity scores of 0.6652, 0.5880, and 0.6682 for edema, non-enhancing tumors, and enhancing tumors, respectively, in which the Dice loss is used for single-pass training. After cascade training, the Dice similarity scores rise to 0.7043, 0.5889, and 0.7206, respectively. Conclusion: Experiments show that the proposed deep learning algorithm outperforms other U-Net transmutation networks for brain tumor segmentation. Moreover, applying cascade training to NDNs facilitates better performance than other methods. The findings of this study provide considerable insight into the automatic and accurate segmentation of brain tumors.

[1]  Konstantinos Kamnitsas,et al.  DeepMedic for Brain Tumor Segmentation , 2016, BrainLes@MICCAI.

[2]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[4]  Iasonas Kokkinos,et al.  Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs , 2014, ICLR.

[5]  Bowen Xin,et al.  Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations , 2019, Front. Neurosci..

[6]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[9]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Sébastien Ourselin,et al.  Automatic Brain Tumor Segmentation Using Cascaded Anisotropic Convolutional Neural Networks , 2017, BrainLes@MICCAI.

[11]  Hyunjin Park,et al.  Classification of low-grade and high-grade glioma using multi-modal image radiomics features , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[12]  Mayur Sharma,et al.  Updated response assessment criteria for high-grade glioma: beyond the MacDonald criteria. , 2017, Chinese clinical oncology.

[13]  Philip Gerlee,et al.  The Impact of Phenotypic Switching on Glioblastoma Growth and Invasion , 2012, PLoS Comput. Biol..

[14]  Guang Yang,et al.  Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks , 2017, MIUA.

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

[16]  Yong Fan,et al.  A deep learning model integrating FCNNs and CRFs for brain tumor segmentation , 2017, Medical Image Anal..

[17]  Hai Thanh Le,et al.  Brain tumour segmentation using U-Net based fully convolutional networks and extremely randomized trees , 2018, Vietnam Journal of Science, Technology and Engineering.

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

[19]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[20]  Marek Bodnar,et al.  A mathematical model describes the malignant transformation of low grade gliomas: Prognostic implications , 2017, PloS one.

[21]  Chi-Wing Fu,et al.  H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes , 2018, IEEE Transactions on Medical Imaging.

[22]  Garrison W. Cottrell,et al.  Understanding Convolution for Semantic Segmentation , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[23]  R. Velthuizen,et al.  Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation. , 2004, International journal of radiation oncology, biology, physics.

[24]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[25]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[27]  Susan M. Chang,et al.  Updated response assessment criteria for high-grade gliomas: response assessment in neuro-oncology working group. , 2010, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[28]  Di Guo,et al.  Convolutional Neural Networks-Based MRI Image Analysis for the Alzheimer’s Disease Prediction From Mild Cognitive Impairment , 2018, Front. Neurosci..

[29]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[30]  Patrick van der Smagt,et al.  CNN-based Segmentation of Medical Imaging Data , 2017, ArXiv.

[31]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[32]  Yang Yang,et al.  Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning , 2018, Front. Neurosci..

[33]  Pablo Arbeláez,et al.  Volumetric multimodality neural network for brain tumor segmentation , 2017, Symposium on Medical Information Processing and Analysis.

[34]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[35]  Tanzila Saba,et al.  Brain tumor segmentation in multi‐spectral MRI using convolutional neural networks (CNN) , 2018, Microscopy research and technique.

[36]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[38]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  S. Bauer,et al.  A survey of MRI-based medical image analysis for brain tumor studies , 2013, Physics in medicine and biology.

[40]  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.

[41]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).