A. The Model Training Results
The 830 clinical instances of the mammographic mass dataset were used in mammographic diagnosis to distinguish malignant breast cancer and benign disease for breast biopsy outcome predictions. The pattern dataset, which contained all of the available 830 clinical instances of the mammographic mass data, was used to train the neural network training model as shown in Figure 1. The iterative training process was employed during the training processes.
For the results, the training model, which used the pattern dataset, stopped at epochs with the final SSE dropping to 64.3082 throughout the last iterative training process. This is equivalent to the final MMSE dropping to 0.0775. This result implied that our training model would have reliably and highly accurately diagnosed and distinguished malignant breast cancer and benign disease for breast biopsy outcome predictions.