MIA-COV19D: COVID-19 Detection through 3-D Chest CT Image Analysis

TL;DR

This paper introduces a new annotated 3-D chest CT scan database for COVID-19 detection and proposes a deep learning model that achieves promising results in diagnosing the disease.

Contribution

The paper provides the COV19-CT-DB database with 5,000 annotated 3-D CT scans and a CNN-RNN based deep learning approach for COVID-19 diagnosis.

Findings

The database includes training, validation, and test datasets.

The deep learning model demonstrates effective COVID-19 detection.

The approach supports AI development in medical environments.

Abstract

Early and reliable COVID-19 diagnosis based on chest 3-D CT scans can assist medical specialists in vital circumstances. Deep learning methodologies constitute a main approach for chest CT scan analysis and disease prediction. However, large annotated databases are necessary for developing deep learning models that are able to provide COVID-19 diagnosis across various medical environments in different countries. Due to privacy issues, publicly available COVID-19 CT datasets are highly difficult to obtain, which hinders the research and development of AI-enabled diagnosis methods of COVID-19 based on CT scans. In this paper we present the COV19-CT-DB database which is annotated for COVID-19, consisting of about 5,000 3-D CT scans, We have split the database in training, validation and test datasets. The former two datasets can be used for training and validation of machine learning models, while the latter will be used for evaluation of the developed models. We also present a deep learning approach, based on a CNN-RNN network and report its performance on the COVID19-CT-DB database.