In recent years, Brain Tumor has become one of the most common deadly diseases and MRI is commonly used to diagnose it. Automated recognition of brain tumors from MRI is a difficult task because of the variability of size, shape, and contrast of the tumor. On the other hand, it has a huge impact in helping the physicians by assessing the type, size, exact topological location and other related parameters of the tumor. Image segmentation techniques are often applied in identifying the tumor from the MRI images in addition to other techniques. There are numerous segmentation techniques available for this purpose such as: (i) Region based (ii) Edge based (iii) Threshold based. Here a threshold based approach has been designed and proposed to do the segmentation of edema, where the threshold is determined by MAXNET, a Self Organization Map (SOM) based artificial neural network.

Artificial Neural Network (ANN), Brain Tumor, Least centre distance method, Magnetic resonance imaging, MAXNET, segmentation, Self Organizing Map (SOM)

[1] Abdel-Maksoud, E., et al., “Brain tumor segmentation based on a hybrid clustering technique.” Egyptian Informatics Journal, Vol. 16(1), pp.71-81. 2015.
[2] Yogamangalam, R. and B. Karthikeyan, “Segmentation Techniques Comparison in Image Processing.” International Journal of Engineering and Technology, Vol. 5(1), pp.307-313. 2013.
[3] Esquenazi, Y, Victor P. Lo, and Kiwon Lee, “Critical Care Management of Cerebral Edema in Brain Tumors.” Journal of Intensive Care Medicine, Vol. 30(8), pp. 15-24. 2015.
[4] Drevelegas, A and Nickolas Papanikolaou, “Imaging Modalities in Brain Tumors. Imaging of Brain Tumors with Histological Correlations.” Antonios Drevelegas, Springer Berlin Heidelberg. pp. 13-33. 2015.
[5] Essig, M et al., "Cerebral Gliomas And Metastases: Assessment With Contrast-Enhanced Fast Fluid-Attenuated Inversion-Recovery MR Imaging". N.p., 2017. Print.
[6] Njeh, I et al.,, “3D multimodal MRI brain glioma tumor and edema segmentation: A graph cut distribution matching approach.” Computerized Medical Imaging and Graphics. Vol. 40, pp. 108–119. 2015.
[7] Reza, S. and K. M. Iftekharuddin. “Multi-fractal Texture Features For Brain Tumor and Edema Segmentation.” Proc. of SPIE- The International Society for Optical Engineering, 2014.
[8] Prastawa, M et al., "Robust Estimation For Brain Tumor Segmentation". Lecture Notes in Computer Science pp.530-537.2013.
[9] Al-Naami, B et al., "Statistical Approach For Brain Cancer Classification Using A Region Growing Threshold". Journal of Medical Systems. Vol. 35(4), pp.463–471. 2009.
[10] Wu, W et al., "Brain Tumor Detection And Segmentation In A CRF (Conditional Random Fields) Framework With Pixel-Pairwise Affinity And Superpixel-Level Features". International Journal of Computer Assisted Radiology and Surgery, Vol. 9(2), pp.241–253. 2013.
[11] Dvorak, P, Karel Bartusek, and W. G. Kropatsch. “Automated Segmentation of Brain Tumor Edema in FLAIR MRI Using Symmetry and Thresholding”, Proc. of PIERS, Stockholm pp. 936-939. 2013
[12] Sarkar, K, Ardhendu Mandal, and Rakesh Kumar Mandal, “Brain Tumor Detection from T1 Weighted MRI Using Histogram Peak Difference Threshol”, Proc. of National Conference on Research Trends in Computer Science and Application, India, pp. 32-37, 2015.
[13] Sarkar, K, Ardhendu Mandal, and Rakesh Kumar Mandal, “Histogram Peak Normalization Based Threshold to Detect Brain Tumor from T1 Weighted MRI”, International Journal of Computer Sciences and Engineering. Vol. 4(1), pp. 16-24. 2016.
[14] Fausett, L. V. “Fundamentals of Neural Networks: Architectures, Algorithms, and Applications” 1st ed. Delhi, India: Pearson Education, 2004 pp. 158-160.
[15] Castro, A, and D. L. Donoho., “Does median filter truly preserve edges better than linear filtering?”, The Annals of Statistics. Vol. 37(3), pp. 1172–1206. 2009.
[16] Bjoern H. Menze, et al.,, “The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)”, IEEE Transactions on Medical Imaging. Vol.34(10), pp. 1993 - 2024. 2014.