Breast Cancer Detection Using MMRF
Anna Rejani, Noorul Islam · 2005
The main p urpose of t his paper is to present an algorithm, which uses discrete wavelet transform (DWT) based multiresolution markov random field (MMRF ) for detection of t umors in mammogram. The proposed technique aims to assist the radiologist towards fast detection and early diagnosis of breast cancer. The technique includes four major steps viz fractal analysis, multiresolution markov random field, dogs- and- rabbits algorithm and the use of neural network for classification. The algorithm was verified with fifty mammograms and the verification results s how that an accuracy of 85% was obtained.