Hi Muhammed,
As per my understanding, you want to extract feature from a image such that those features can be used for cancer image classification.
The specific features to be extracted can vary depending upon the dataset of the images. As a general approach, following example can be helpful. Using this method, you can extract 4096-dimensional feature vector for each image.
The example shows how to extract learned image features from a pretrained convolutional neural network and use those features to train an image classifier.
I hope this helps!
