A Deep Learning Algorithm for Fully Automatic Brain Tumor Segmentation

Tumor segmentation is of great importance for diagnosis and prognosis of brain cancer in medical field. Many of the existing brain tumor segmentation methods are semiautomatic which need interventions of raters or specialists. In this paper an automatic method, named wide residual & pyramid pool network (WRN-PPNet), which can automatically segment glioma end to end is put forward. The main idea is described below. Firstly, substantial two-dimensional (2D) slices are obtained from three-dimensional (3D) MRI brain tumor images. Secondly, the 2D slices are normalized and put into the WRN-PPNet model, and the model will output the tumor segmentation results. Finally, dice coefficient (Dice), sensitivity coefficient (Sensitivity) and predictive positivity value (PPV) coefficient are used to evaluate the performance of WRN-PPNet quantitatively. The experimental results show that the proposed method is simple and robust compared with the other state-of- the-art methods, and the average Dice, Sensitivity and PPV on the randomly selected test data can reach 0.94, 0.92 and 0.97 respectively.

[1]  Yurong Liu,et al.  A survey of deep neural network architectures and their applications , 2017, Neurocomputing.

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

[3]  Maximilien Vermandel,et al.  On image segmentation methods applied to glioblastoma: state of art and new trends , 2016 .

[4]  Marios Savvides,et al.  Deep Recurrent Level Set for Segmenting Brain Tumors , 2018, MICCAI.

[5]  Dinggang Shen,et al.  ORBIT: A Multiresolution Framework for Deformable Registration of Brain Tumor Images , 2008, IEEE Transactions on Medical Imaging.

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

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

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

[9]  M. Mohammed Thaha,et al.  Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images , 2019, Journal of Medical Systems.

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

[11]  Christopher Joseph Pal,et al.  Brain tumor segmentation with Deep Neural Networks , 2015, Medical Image Anal..

[12]  Ralph Weissleder,et al.  A multimodal nanoparticle for preoperative magnetic resonance imaging and intraoperative optical brain tumor delineation. , 2003, Cancer research.

[13]  Wei Liu,et al.  ParseNet: Looking Wider to See Better , 2015, ArXiv.

[14]  Olivier Clatz,et al.  Glioma Dynamics and Computational Models: A Review of Segmentation, Registration, and In Silico Growth Algorithms and their Clinical Applications , 2007 .

[15]  Daniel L. Rubin,et al.  Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions , 2017, Journal of Digital Imaging.

[16]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[17]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Christos Davatzikos,et al.  GLISTR: Glioma Image Segmentation and Registration , 2012, IEEE Transactions on Medical Imaging.