1

I have a general question regarding bio-medical image analysis. As bio-medical images require registration for alignment of images in same space and for better feature extraction. My question is does deep learning based classification also requires image registration of images for training dataset? As in deep learning the architecture define best features by itself, does registration required for abdominal CT scan images classification using Deep Neural Networks ? As we perform data augmentation for better training of data does image registration still required in this case?

Rayyan Khan
  • 117
  • 1
  • 2
  • 10
  • What do you mea by “image registration”? – Dai Jun 04 '19 at 02:15
  • Yes, Image registration means image alignment so that multiple images become in same space, this technique is more often used in bio-medical images pre-processing. – Rayyan Khan Jun 04 '19 at 02:21

1 Answers1

3

Generally deep learning approaches for image data is done using convolutional neural networks (CNNs) which are at least shift invariant. By using image pyramids or specially constructed neural network layouts, they can also be made scale invariant. Generally they are not rotation invariant.

This does not mean that they cannot work with differently rotated input images, but you may need much bigger models and more training data to get it to work well. The neural net will learn the differently rotated features of whatever you're trying to detect. If the range of rotation is small, this is probably not a big issue.

In summary, you don't necessarily need registration, but it can improve your final results.

Richard K. Wade
  • 299
  • 1
  • 5