Brain Tumor Segmentation Using Bit-plane and UNET

The extraction of brain tumor tissues in 3D Brain Magnetic Resonance Imaging plays an important role in diagnosis gliomas. In this paper, we use clinical data to develop an approach to segment Enhancing Tumor, Tumor Core, and Whole Tumor which are the sub-regions of glioma. Our proposed method starts with Bit-plane to get the most significant and least significant bits which can cluster and generate more images. Then U-Net, a popular CNN model for object segmentation, is applied to segment all of the glioma regions. In the process, U-Net is implemented by multiple kernels to acquire more accurate results. We evaluated the proposed method with the database BRATS challenge in 2018. On validation data, the method achieves a performance of 82%, 68%, and 70% Dice scores and of 77%, 48%, and 51% on testing data for the Whole Tumor, Enhancing Tumor, and Tumor Core respectively.

[1]  S. Bauer,et al.  Atlas-based segmentation of brain tumor images using a Markov Random Field-based tumor growth model and non-rigid registration , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

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

[3]  Nelly Gordillo,et al.  State of the art survey on MRI brain tumor segmentation. , 2013, Magnetic resonance imaging.

[4]  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.

[5]  G. G. Lakshmi Priya,et al.  Automated brain tumour segmentation techniques— A review , 2017, Int. J. Imaging Syst. Technol..

[6]  Bilwaj Gaonkar,et al.  GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation , 2015, Brainles@MICCAI.

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

[8]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[9]  Ping Wang,et al.  A fuzzy feature fusion method for auto-segmentation of gliomas with multi-modality diffusion and perfusion magnetic resonance images in radiotherapy , 2018, Scientific Reports.

[10]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

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

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

[13]  Spyridon Bakas,et al.  Advanced magnetic resonance imaging in glioblastoma: a review. , 2017, Chinese clinical oncology.

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

[15]  Pham The Bao,et al.  3D brain magnetic resonance imaging segmentation by using bitplane and adaptive fast marching , 2018, Int. J. Imaging Syst. Technol..

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

[17]  M. M. Sufyan Beg,et al.  Improved Edge Detection Algorithm for Brain Tumor Segmentation , 2015, Procedia Computer Science.

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

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

[20]  Yogita K. Dubey,et al.  Segmentation of brain MR images using rough set based intuitionistic fuzzy clustering , 2016 .