Deep Learning for COVID-19 Diagnosis from CT Images
COVID-19, an infectious coronavirus disease, caused a pandemic with countless deaths. From the outset, clinical institutes have explored computed tomography as an effective and complementary screening tool alongside the reverse transcriptase-polymerase chain reaction. Deep learning techniques have s...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/17/8227 |
_version_ | 1797521640147386368 |
---|---|
author | Andrea Loddo Fabio Pili Cecilia Di Ruberto |
author_facet | Andrea Loddo Fabio Pili Cecilia Di Ruberto |
author_sort | Andrea Loddo |
collection | DOAJ |
description | COVID-19, an infectious coronavirus disease, caused a pandemic with countless deaths. From the outset, clinical institutes have explored computed tomography as an effective and complementary screening tool alongside the reverse transcriptase-polymerase chain reaction. Deep learning techniques have shown promising results in similar medical tasks and, hence, may provide solutions to COVID-19 based on medical images of patients. We aim to contribute to the research in this field by: (i) Comparing different architectures on a public and extended reference dataset to find the most suitable; (ii) Proposing a patient-oriented investigation of the best performing networks; and (iii) Evaluating their robustness in a real-world scenario, represented by cross-dataset experiments. We exploited ten well-known convolutional neural networks on two public datasets. The results show that, on the reference dataset, the most suitable architecture is VGG19, which (i) Achieved 98.87% accuracy in the network comparison; (ii) Obtained 95.91% accuracy on the patient status classification, even though it misclassifies some patients that other networks classify correctly; and (iii) The cross-dataset experiments exhibit the limitations of deep learning approaches in a real-world scenario with 70.15% accuracy, which need further investigation to improve the robustness. Thus, VGG19 architecture showed promising performance in the classification of COVID-19 cases. Nonetheless, this architecture enables extensive improvements based on its modification, or even with preprocessing step in addition to it. Finally, the cross-dataset experiments exposed the critical weakness of classifying images from heterogeneous data sources, compatible with a real-world scenario. |
first_indexed | 2024-03-10T08:15:24Z |
format | Article |
id | doaj.art-2d0d70cc40b24c699b152e87415b2897 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T08:15:24Z |
publishDate | 2021-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-2d0d70cc40b24c699b152e87415b28972023-11-22T10:23:36ZengMDPI AGApplied Sciences2076-34172021-09-011117822710.3390/app11178227Deep Learning for COVID-19 Diagnosis from CT ImagesAndrea Loddo0Fabio Pili1Cecilia Di Ruberto2Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124 Cagliari, ItalyDepartment of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124 Cagliari, ItalyDepartment of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124 Cagliari, ItalyCOVID-19, an infectious coronavirus disease, caused a pandemic with countless deaths. From the outset, clinical institutes have explored computed tomography as an effective and complementary screening tool alongside the reverse transcriptase-polymerase chain reaction. Deep learning techniques have shown promising results in similar medical tasks and, hence, may provide solutions to COVID-19 based on medical images of patients. We aim to contribute to the research in this field by: (i) Comparing different architectures on a public and extended reference dataset to find the most suitable; (ii) Proposing a patient-oriented investigation of the best performing networks; and (iii) Evaluating their robustness in a real-world scenario, represented by cross-dataset experiments. We exploited ten well-known convolutional neural networks on two public datasets. The results show that, on the reference dataset, the most suitable architecture is VGG19, which (i) Achieved 98.87% accuracy in the network comparison; (ii) Obtained 95.91% accuracy on the patient status classification, even though it misclassifies some patients that other networks classify correctly; and (iii) The cross-dataset experiments exhibit the limitations of deep learning approaches in a real-world scenario with 70.15% accuracy, which need further investigation to improve the robustness. Thus, VGG19 architecture showed promising performance in the classification of COVID-19 cases. Nonetheless, this architecture enables extensive improvements based on its modification, or even with preprocessing step in addition to it. Finally, the cross-dataset experiments exposed the critical weakness of classifying images from heterogeneous data sources, compatible with a real-world scenario.https://www.mdpi.com/2076-3417/11/17/8227COVID-19 detectionconvolutional neural networkdeep learninglung CT analysisimage classificationSARS-CoV-2 |
spellingShingle | Andrea Loddo Fabio Pili Cecilia Di Ruberto Deep Learning for COVID-19 Diagnosis from CT Images Applied Sciences COVID-19 detection convolutional neural network deep learning lung CT analysis image classification SARS-CoV-2 |
title | Deep Learning for COVID-19 Diagnosis from CT Images |
title_full | Deep Learning for COVID-19 Diagnosis from CT Images |
title_fullStr | Deep Learning for COVID-19 Diagnosis from CT Images |
title_full_unstemmed | Deep Learning for COVID-19 Diagnosis from CT Images |
title_short | Deep Learning for COVID-19 Diagnosis from CT Images |
title_sort | deep learning for covid 19 diagnosis from ct images |
topic | COVID-19 detection convolutional neural network deep learning lung CT analysis image classification SARS-CoV-2 |
url | https://www.mdpi.com/2076-3417/11/17/8227 |
work_keys_str_mv | AT andrealoddo deeplearningforcovid19diagnosisfromctimages AT fabiopili deeplearningforcovid19diagnosisfromctimages AT ceciliadiruberto deeplearningforcovid19diagnosisfromctimages |