Algorithm 1: Presented system: Breast Cancer Identification and Diagnosis

Input: an image: mammographic.

Output: the detection and classification of Breast Cancer: 1) BC and 2) MC or HB.

1. Read an image from a file.

2. In the preprocessing phase: Do the following:

3. Remove any detected noise.

4. Resize the input into a compatible size with AlexNet.

5. Utilize the Gabor filter, DWT, and PCA.

6. Transform the resultant image into a gray image.

7. End of Preprocessing phase.

8. For the Deep Learning phase (DCNN): Do the following:

9. Create a Zero matrix with a size = size of the input image.

10. For i =1: size of the input

11.     Perform a masking operation using the morphological operation to extract: Area, shape, diameter, and correlation of the potential area of Interest (PoI).

12.     Determine a dynamic threshold for every image.

13.     Invert the image to separate the foreground and the background.

14.     Compute variance, standard deviation, mean, and correlation for every PoI in each input.

15. Extract the required features.

16. End

17. End of DCNN phase.

18. For the classification phase: Do the following:

19. Create a Binary image to detect and classify the disease with a size = 1024 × 1024 in every PoI.

20. Find a mass area and draw a circle around it.

21. Determine the number of detected areas and their drawn circles.

22. For i = 1: 1024

23.     For j = 1: 1024

24.         Compute the number of white pixels z to compare it with the threshold.

25.         If z > threshold:

26.         Cancer is Detected.

27.     End

28.     Classify detected cancer: BC or MC or display a message saying that there is no cancer.

29. End

30. End

31. End the classification phase.

32. Find TP, TN, FP, and FN.

33. Compute accuracy, precision, recall, specificity, and F-score.

34. End of the algorithm.