Detection of mass and circumscribed mass in mammograms employing radial-basis-function neural networks
Snehal S. Kolhe, Dr.Sudhir Deoraoji Sawarkar · 2010
The proposed method detects the exact location of masses and circumscribed masses in mammograms based on RBFNN (Redial Basis Function Neural Network) with accuracy of 62% and 50% respectively for mammograms containing masses. The recognition rate for the normal one reaches 94.89% in MIAS (Mammography Image Analysis Society) database. Also the results are independent of preprocessing. This procedure is implemented by performing sub-image windowing analysis. The evaluation of the proposed mass and circumscribed mass detection was carried out in the MIAS database, giving reliable detection.