Semi-Supervised Classification with Generative Adversarial Networks on Medial Datasets with Limited Size and Label

About the scholar: Lutfi Eren Erdogan grew up in Turkey and attended Uskudar American Academy in Istanbul, Turkey.

The Research:

Using advanced computer technology to classify medical images has proven challenging because the datasets of images are limited in size and mostly lack annotations, whereas the supervised convolutional neural networks that can aid diagnosis generally require large datasets annotated by experts to guarantee high performance. Pioneer scholar Lutfi thought a semi-supervised neural network might be used to train a powerful classifier that could provide accurate results. His semi-supervised classification approach worked well with medical datasets with limited images and few labels, outperforming a state-of-the-art classification network. Lutfi has made his code available for public use as part of his paper.

ClientThe Car Rental Co
SkillsPhotography / Media Production
WebsiteGoodlayers.com

Project Title

Far far away, behind the word mountains, far from the countries Vokalia and Consonantia, there live the blind texts. Separated they live in Bookmarksgrove right at the coast of the Semantics, a large language ocean. A small river named Duden flows by their place and supplies it with the necessary regelialia. It is a paradisematic country, in which roasted parts of sentences fly into your mouth.