Abstract: In this project a forceful segmentation tool for the detection of brain tumour is used to assist clinician and researchers in radio surgery applications. A clustering based approach using hierarchal self-organizing map algorithm is proposed for MR image segmentation. Hierarchal self-organizing map (HSOM) is a dynamically growing neural network model evolves into a hierarchical structure according to the requirements of the input data during an unsupervised training process. This algorithm proved to be exceptionally successful for data visualization applications. HSOM is the extension of the conventional self organizing map which is used to classify the image row by row. This project describe segmentation method consists of two phases. In the first phase, the MRI brain image is acquired from patient database. In that film artifact and noise are removed. In the second phase (MR) image segmentation is to accurately identify the principal tissue structures in these image volumes. Finally the numbers of affected cells are counted using the row and column wise scanning method.
Keywords - HSOM, Image analysis, Magnetic Resonance Imaging (MRI) Segmentation, Tumor detection.
[1] AndacHamamci, Nadir Kucuk, KutlayKaraman, KayihanEngin, and GozdeUnal,(2012). "Tumor-Cut: Segmentation of Brain Tumors on Contrast Enhanced MR Imagesfor Radiosurgery Applications". IEEE Transactions on Medical Imaging, Vol. 31, No.3.
[2] Fedde van der Lijn, Marleen de Bruijne, Stefan Klein, Tom den Heijer, Yoo Y. Hoogendam, Aad van der Lugt, Monique M. B. Breteler, and Wiro J. Niessen(2012). "Automated Brain Structure Segmentation Based on Atlas Registration and Appearance Models". IEEE Transactions On Medical Imaging, Vol. 31, No. 2
[3] Shanhui Sun, Christian Bauer, and ReinhardBeichel (2012). "Automated 3-D Segmentation of Lungs With Lung Cancer in CT Data Using a Novel Robust Active Shape Model Approach". IEEE Transactions OnMedical Imaging, Vol. 31, No. 2.
[4] Nazem-ZadehM.R, Davoodi-Bojd.E., and Soltanian-ZadehH.,(2011). "Atlasbasedfiber bundle segmentation using principal diffusion directions and spherical harmonic coefficients," NeuroImage, vol. 54, pp. S146–S164.
[5] Gooya, G. Biros, and DavatzikosC., (2011). "Deformable registration of glioma images using em algorithm and diffusion reaction modeling," IEEETrans. Med. Imag., vol. 30, no. 2, pp. 375–390.
[6] Menze,Leemput.K.VLashkari.D,Weber.M.A,. Ayache.N, andGolland.P, (2010)"A generative model for brain tumor segmentation in multimodal images," Med. Image Comput. Comput. Assist. Intervent., vol. 13, pp. 151–159.
[7] Hamamci, Unal.G,.Kucuk.N, and Engin.K., (2010) "Cellular automata segmentation of brain tumors on post contrast MR images," in MICCAI. New York: Springer, pp. 137–146.
[8] Kauffmann and Pich.N., (2010) "Seeded ND medical image segmentation by cellular automaton on GPU," Int. J. Comput. Assist. Radiol. Surg., vol. 5, pp. 251–262.
[9] Bai.X, and Sapiro.G,(2009)., "Geodesic matting: A framework for fast interactive image and video segmentation and matting," Int. J. Comput. Vis., vol. 82, pp. 113–132.
[10] Couprie.C, Grady.L, Najman.L, and Talbot.H. (2009), "Power watersheds:A new image segmentation framework extending graph cuts, randomwalker and optimal spanning forest," in ICCV , pp. 731–738.