How does the PNN algorithm differentiate between malignant and benign tumors?

I mean, how does he know the difference between the images in which there are benign tumors and the malignant ones, even if the images look similar. I read a lot of writers and books but can't understand how it works. Thank you in advance!

Answer 1

[Ashu]

Hey Roxana

PNN (Probabilistic Neural Network) is used for classification problems and differentiating between Malignant and Benign Tumors is a problem of that domain.

To get a good classifier which can differentiate between very similar looking images, training the Neural Network is an important aspect.

Here is an architecture of a PNN.

So when you present an input to a PNN

1. The first layer computes distances from the input vector to the training input vectors and produces a vector whose elements indicate how close the input is to a training input. (When you talk about classification between similar looking images, calculation of this distance is an important aspect)
2. The second layer sums these contributions for each class of inputs to produce as its net output a vector of probabilities.
3. Finally, a compete transfer function on the output of the second layer picks the maximum of these probabilities, and produces a 1 for that class and a 0 for the other classes.

For more information on how to use PNN and how it works you can refer to this link : https://www.mathworks.com/help/deeplearning/ug/probabilistic-neural-networks.html