Brain Tumor Diagnosis Using Hidden Markov Model and Wavelet Transform

Brain Tumor Diagnosis Using Hidden Markov Model and Wavelet Transform

pooneh ghasemi nezhad raeeni1

1) Iran university of science tecnology

IOI Code : XYCZ-AADCG
Publication : International Conference on Engineering and Applied Science(iceasconf.com)
Abstract :
    Out-of-control growth of cells in the brain, result in brain tumors. If tumors are not treated properly at the right time, they may cause permanent brain damages, or even lead to patient’s death. Since knowledge of the location and size of the tumor affects treatment success rate, discovering a way to accurately and automatically provide the doctor with these information is necessary [1]. In this research, an effective and accurate method is presented so as to automatically diagnose cancerous tumors of the human brain. The method is based on learning using Hidden Markov Model and tumor localization by wavelet transform. Using the proposed method, we were able to distinguish images containing tumors in MRI images collection of the BRAINIX database, with an accuracy of 88.8 percent. Using this method, we were also able to localize the cancer and its growth area after the image was labeled as tumorous. .

Keywords : tumor magnetic intensity image hidden markov model wavelet transform