loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Francesca Lizzi 1 ; 2 ; Francesca Brero 3 ; 4 ; Raffaella Fiamma Cabini 5 ; 4 ; Maria Evelina Fantacci 6 ; 1 ; Stefano Piffer 7 ; 8 ; Ian Postuma 4 ; Lisa Rinaldi 3 ; 4 and Alessandra Retico 1

Affiliations: 1 National Institute for Nuclear Physics (INFN), Pisa Division, Pisa, Italy ; 2 Scuola Normale Superiore, Pisa, Italy ; 3 Department of Physics, University of Pavia, Pavia, Italy ; 4 INFN, Pavia Division, Pavia, Italy ; 5 Department of Mathematics, University of Pavia, Pavia, Italy ; 6 Department of Physics, University of Pisa, Pisa, Italy ; 7 Department of Biomedical Experimental Clinical Science ”M. Serio”, University of Florence, Florence, Italy ; 8 INFN, Florence Division, Florence, Italy

Keyword(s): COVID-19, Lung CT, U-net, Data Aggregation, Image Segmentation.

Abstract: Lung Computed Tomography (CT) is an imaging technique useful to assess the severity of COVID-19 infection in symptomatic patients and to monitor its evolution over time. Lung CT can be analysed with the support of deep learning methods for both aforementioned tasks. We have developed a U-net based algorithm to segment the COVID-19 lesions. Unfortunately, public datasets populated with a huge amount of labelled CT scans of patients affected by COVID-19 are not available. In this work, we first review all the currently available public datasets of COVID-19 CT scans, presenting an extensive description of their characteristics. Then, we describe the design of the U-net we developed for the automated identification of COVID-19 lung lesions. Finally, we discuss the results obtained by using the different publicly available datasets. In particular, we trained the U-net on the dataset made available within the COVID-19 Lung CT Lesion Segmentation Challenge 2020, and we tested it on data fro m the MosMed and the COVID-19-CT-Seg datasets to explore the transferability of the model and to assess whether the image annotation process affects the detection performances. We evaluated the performance of the system in lesion segmentation in terms of the Dice index, which measures the overlap between the ground truth and the predicted masks. The proposed U-net segmentation model reaches a Dice index equal to 0.67, 0.42 and 0.58 on the independent validation sets of the COVID-19 Lung CT Lesion Segmentation Challenge 2020, on the MosMed and on the COVID-19-CT-Seg datasets, respectively. This work focusing on lesion segmentation constitutes a preliminary work for a more accurate analysis of COVID-19 lesions, based for example on the extraction and analysis of radiomic features. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.128.94.74

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Lizzi, F.; Brero, F.; Cabini, R.; Fantacci, M.; Piffer, S.; Postuma, I.; Rinaldi, L. and Retico, A. (2021). Making Data Big for a Deep-learning Analysis: Aggregation of Public COVID-19 Datasets of Lung Computed Tomography Scans. In Proceedings of the 10th International Conference on Data Science, Technology and Applications - DATA; ISBN 978-989-758-521-0; ISSN 2184-285X, SciTePress, pages 316-321. DOI: 10.5220/0010584403160321

@conference{data21,
author={Francesca Lizzi. and Francesca Brero. and Raffaella Fiamma Cabini. and Maria Evelina Fantacci. and Stefano Piffer. and Ian Postuma. and Lisa Rinaldi. and Alessandra Retico.},
title={Making Data Big for a Deep-learning Analysis: Aggregation of Public COVID-19 Datasets of Lung Computed Tomography Scans},
booktitle={Proceedings of the 10th International Conference on Data Science, Technology and Applications - DATA},
year={2021},
pages={316-321},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010584403160321},
isbn={978-989-758-521-0},
issn={2184-285X},
}

TY - CONF

JO - Proceedings of the 10th International Conference on Data Science, Technology and Applications - DATA
TI - Making Data Big for a Deep-learning Analysis: Aggregation of Public COVID-19 Datasets of Lung Computed Tomography Scans
SN - 978-989-758-521-0
IS - 2184-285X
AU - Lizzi, F.
AU - Brero, F.
AU - Cabini, R.
AU - Fantacci, M.
AU - Piffer, S.
AU - Postuma, I.
AU - Rinaldi, L.
AU - Retico, A.
PY - 2021
SP - 316
EP - 321
DO - 10.5220/0010584403160321
PB - SciTePress