IJMTES – A GNN MODEL FOR BRAIN TUMOR SEGMENTATION IN MULTI- MODAL IMAGES USING GUSTAFSON KESSEL ALGORITHM

Journal Title : International Journal of Modern Trends in Engineering and Science

Paper Title : A GNN MODEL FOR BRAIN TUMOR SEGMENTATION IN MULTI- MODAL IMAGES USING GUSTAFSON KESSEL ALGORITHM

Author’s Name : R Muthaiyan | M Indhupriyadaharshini | C Sujatha | A Deepika
unnamed

Volume 04 Issue 12 2017

ISSN no:  2348-3121

Page no: 26-31

Abstract – Brain tumors is an uncontrolled mass of tissue may be embedded in the regions of the brain that makes the sensitive functioning of the body to be disabled. A new approach for brain tumors detection and classification is proposed by using metrics Patches. The proposed approach works in the stages of detection the brain tumors from PET/ MRI Scan images then the GNN to recognize the type of tumors based on feature enhancement. Coronal metric patches used to determine the intensity value of the entire image distinguishes object and background pixels by comparing with threshold value chosen and use binary partition to segment the image. The segmentation process start by a pre-processing stage consisting of partiality pastures alteration, intensity and patch normalization. After that, during training, the number of training patches is artificially augmented by rotating the training patches, and using samples of PET/MRI images. MICCAI Brats 2017 dataset is used for testing the proposed technique and experiments are performed for Low Grade Glioma and High Grade Glioma datasets by securing average accuracy maybe 89.75% and 86.87% is obtained. The results are compared with different classifiers.

Keywords – PET Scan Image; Coronel Patches; GNN; Threshold Value; Intensity Value

References

  1. Sérgio Pereira, Adriano Pinto,Victor Alves, and Carlos A. Silva” Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images” 0278-0062 © 2016 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission
  2. Bjoern Weissler*, Pierre Gebhardt, Peter M. Dueppenbecker, Jakob Wehner, David Schug,” A Digital Preclinical PET/MRI Insert and Initial Results” IEEE Transactions on Medical Imaging, Vol. 34, No. 11, November 2015
  3. Seyed Sadegh Mohseni Salehi, Deniz Erdogmus, Ali Gholipour,” Auto-context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging” Hepatic Tumor Volumetrics”, Medical Physics, 35(12): 5869–5881, 2008.
  4. W. Yang and M. Siliang, “Automatic Detection and Segmentation of Brain Tumor using Fuzzy Classification and Deformable Models,” 4th International Conference on Biomedical Engineering and Informatics (BMEI):1680 – 1683, 15-17 October 2011.
  5. N. Zhang, S. Ruan, S. Lebonvallet, L. Qingmin and Z. Yuemin, “Multi-kernel SVM Based Classification for Brain Tumor Segmentation of MRI Multi-Sequence”, 16th IEEE International Conference on Image Processing (ICIP): 3373 -3376, 7-10 November 2009
  6. CiteSeer: http://braintumor.org/brain-tumor-information/treatment-options/,                                      https://onlinecourses.science.psu.edu/stat507/node/71.
  7. C. Wanhyun, P. Jonghyun, P. Soonyoung and K. Soohyung, “Level-Set Segmentation of Brain Tumors Using a New Hybrid Speed Function”, 20th International Recognition (ICPR): 1545 – 1548, 23-26, August 2010.
  8. CiteSeer: https://www.healthline.com/health/brain-tumor#risk- factors
  9. http://neuralnetworksanddeeplearning.com/chap1.html
  10. B. Vijayakumar, A. Chaturvedi, “Automatic Brain Tumors Segmentation of MR Images using Fluid Vector flow and Support vector Machine”, Research Journal of Information Technology, 4(3): 108 -114, 2012.
  11. CiteSeer:http://ufldl.stanford.edu/tutorial/supervised/ConvolutionalN euralNetwork/