A novel unsupervised approach based on the hidden features of Deep Denoising Autoencoders for COVID-19 disease detection

作者：

Highlights：

• Unsupervised high-performance automatic COVID-19 disease detection.

• Deep Denoising Convolutional Autoencoders for CT scans classification.

• Distance-based hidden feature robust statistical representation for anomaly detection.

摘要

•Unsupervised high-performance automatic COVID-19 disease detection.•Deep Denoising Convolutional Autoencoders for CT scans classification.•Distance-based hidden feature robust statistical representation for anomaly detection.

论文关键词：Deep denoising autoencoder,Convolutional autoencoders,Feature learning,Computed Tomography (CT),Coronavirus disease 2019,COVID-19,Pneumonia,Anomaly detection

论文评审过程：Received 26 April 2021, Revised 15 October 2021, Accepted 30 November 2021, Available online 16 December 2021, Version of Record 21 December 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116366