Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging
Abstract
Our motivating application is a real-world problem: COVID-19 classification from CT imaging, for which we present an explainable Deep Learning approach based on a semi-supervised classification pipeline that employs variational autoencoders to extract efficient feature embedding. We have optimized the architecture of two different networks for CT images: (i) a novel conditional variational autoencoder (CVAE) with a specific architecture that integrates the class labels inside the encoder layers and uses side information with shared attention layers for the encoder, which make the most of the contextual clues for representation learning, and (ii) a downstream convolutional neural network for supervised classification using the encoder structure of the CVAE. With the explainable classification results, the proposed diagnosis system is very effective for COVID-19 classification. Based on the promising results obtained qualitatively and quantitatively, we envisage a wide deployment of our developed technique in large-scale clinical studies.Code is available at https://git.etrovub.be/AVSP/ct-based-covid-19-diagnostic-tool.git.
Keywords
Cite
@article{arxiv.2011.11719,
title = {Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging},
author = {Abel Díaz Berenguer and Hichem Sahli and Boris Joukovsky and Maryna Kvasnytsia and Ine Dirks and Mitchel Alioscha-Perez and Nikos Deligiannis and Panagiotis Gonidakis and Sebastián Amador Sánchez and Redona Brahimetaj and Evgenia Papavasileiou and Jonathan Cheung-Wai Chana and Fei Li and Shangzhen Song and Yixin Yang and Sofie Tilborghs and Siri Willems and Tom Eelbode and Jeroen Bertels and Dirk Vandermeulen and Frederik Maes and Paul Suetens and Lucas Fidon and Tom Vercauteren and David Robben and Arne Brys and Dirk Smeets and Bart Ilsen and Nico Buls and Nina Watté and Johan de Mey and Annemiek Snoeckx and Paul M. Parizel and Julien Guiot and Louis Deprez and Paul Meunier and Stefaan Gryspeerdt and Kristof De Smet and Bart Jansen and Jef Vandemeulebroucke},
journal= {arXiv preprint arXiv:2011.11719},
year = {2021}
}