Paolo Andreini (University of Siena)
Nov 20, 2019 – 11:00 AM
DIISM, Artificial Intelligence laboratory (room 201), Siena SI
In recent years, the use of deep learning is becoming increasingly popular in computer vision. However, the effective training of deep architectures usually relies on huge sets of annotated data. This is critical in the medical field where it is difficult and expensive to obtain annotated images. In this seminar, the use Generative Adversarial Networks (GANs) for synthesizing high quality retinal images, along with the corresponding semantic label-maps, is presented. The generated images can be used instead of real images during the training process.
Differently from other previous proposals, we suggest a two step approach: first, a progressively growing GAN is
trained to generate the semantic label-maps, which describe the blood vessel structure (i.e. vasculature); second, an image-to-image translation approach is used to obtain realistic retinal images from the generated vasculature. By using only a handful of training samples, our approach generates realistic high resolution images, that can be effectively used to enlarge small available datasets.