Cancer tissues recognition system using box counting method and artificial neural network

The research presented in this paper was aimed to develop a recognition system for microscopic images of breast tissues samples. The system should classify breast tissues as malignant or not, or identifying their malignancy types. In this paper, multi-scale fractal dimension concept was used to extract a set of textural features in order to perform texture analysis for breast tissues samples. The box counting method was used to estimate the multi fractal dimensions. A feed forward neural network was used to classify different types of breast tissues according to the extracted fractal dimension vectors. For ANN training purpose the back-propagation training algorithm was used. Evaluation tests were carried on 368 breast tissues images. The test results indicated that the best attained success rate was around 97%.