• Corpus ID: 227151836

Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging

  title={Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging},
  author={Abel D'iaz Berenguer and Hichem Sahli and B. Joukovsky and Maryna Kvasnytsia and Ine Dirks and Mitchel Alioscha-P{\'e}rez and Nikolaos Deligiannis and Panagiotis Gonidakis and Sebasti'an Amador S'anchez 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 J. 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 Watt'e and Johan de Mey and Annemie 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},
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… 

Semi-supervised Learning for COVID-19 Image Classification via ResNet

A two-path semi-supervised deep learning model, ssResNet, based on Residual Neural Network (ResNet) for COVID-19 image classification, where two paths refer to a supervised path and an unsupervised path, respectively is proposed.

Transfer Learning and Semisupervised Adversarial Detection and Classification of COVID-19 in CT Images

The application of deep learning and adversarial network for the automatic identification of COVID-19 pneumonia in computed tomography (CT) scans of the lungs with experimental evaluation indicates that the proposed semisupervised model achieves reliable classification.

Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey

The ability of VAEs to synthesize new data with more representation variance at state-of-art levels provides hope that the chronic scarcity of labeled data in the biomedical field can be resolved.

A Tutorial on Learning Disentangled Representations in the Imaging Domain

This tutorial paper offers an overview of the disentangled representation learning, its building blocks and criteria, and discusses applications in computer vision and medical imaging, and presents the identified opportunities for the integration of recent machine learning advances into disentanglement.

Covid-19 Chest CT Scan Image Classification Using LCKSVD and Frozen Sparse Coding

A framework for image sparse coding, dictionary learning, and classifier learning is proposed and an accuracy of \(89\%\) is achieved on the cleaned CC-CCII CT lung image dataset.

Deep neural networks for COVID-19 detection and diagnosis using images and acoustic-based techniques: a recent review

The approaches used in the detection of COVID-19 based on deep learning (DL) algorithms, which have been popular in recent years, have been comprehensively discussed and the advantages and disadvantages of different approach used in literature are examined in detail.

AI-Based Chest CT Analysis for Rapid COVID-19 Diagnosis and Prognosis: A Practical Tool to Flag High-Risk Patients and Lower Healthcare Costs

A decision tree model was developed to evaluate the impact of using an artificial intelligence-based chest computed tomography analysis software (icolung, icometrix) to analyze CT scans for the detection and prognosis of COVID-19 cases and found icolung is cost-effective in reducing the risk of transmission, with a low prevalence of CO VID-19 infections.



Multi-task Deep Learning Based CT Imaging Analysis For COVID-19: Classification and Segmentation

A multitask deep learning model is proposed to jointly identify CO VID-19 patient and segment COVID-19 lesion from chest CT images to help improve both segmentation and classification performances.

Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans

An Self-Trans approach is proposed, which synergistically integrates contrastive self-supervised learning with transfer learning to learn powerful and unbiased feature representations for reducing the risk of overfitting in COVID-19.

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar.

A Weakly-Supervised Framework for COVID-19 Classification and Lesion Localization From Chest CT

A weakly-supervised deep learning model can accurately predict the COVID-19 infectious probability and discover lesion regions in chest CT without the need for annotating the lesions for training.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Learning Disentangled Representations with Reference-Based Variational Autoencoders

The ability of the proposed reference-based variational autoencoders, a novel deep generative model designed to exploit the weak-supervision provided by the reference set, to learn disentangled representations from this minimal form of supervision is validated.

Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients

This study compares twelve deep learning algorithms using a multi-center dataset, including both open-source and in-house developed algorithms, and shows that all methods perform binary lesion segmentation with an average volume error that is better than visual assessment by human raters, suggesting these methods are mature enough for a large-scale evaluation for use in clinical practice.

COVID-CT-Dataset: A CT Scan Dataset about COVID-19

An open-sourced dataset, which contains 349 COVID-19 CT images from 216 patients and 463 non-COVID- 19 CTs, is built, which is used to develop diagnosis methods based on multi-task learning and self-supervised learning that achieve an F1 of 0.90, an AUC of0.98, and an accuracy of 1.89.

Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT

A deep learning model can accurately detect COVID-19 and differentiate it from community acquired pneumonia and other lung diseases.