Title :

COVID-19 Infection Percentage Estimation from Computed Tomography Scans: Results and Insights from the International Per-COVID-19 Challenge

Author(s) :

Bougourzi, Fares [Auteur]
Istituto di Scienze Applicate e Sistemi Intelligenti “Eduardo Caianiello” [ISASI]
Distante, Cosimo [Auteur]
Istituto di Scienze Applicate e Sistemi Intelligenti “Eduardo Caianiello” [ISASI]
Dornaika, Fadi [Auteur]
University of the Basque Country = Euskal Herriko Unibertsitatea [UPV / EHU]
Henan University
Ikerbasque - Basque Foundation for Science
Tahleb Ahmed, Abdelmalik [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Hadid, Abdenour [Auteur]
Sorbonne university Abu Dhabi
Chaudhary, Suman [Auteur]
Yang, Wanting [Auteur]
Qiang, Yan [Auteur]
Anwar, Talha [Auteur]
Breaban, Mihaela [Auteur]
Alexandru Ioan Cuza University of Iași = Universitatea Alexandru Ioan Cuza din Iași [UAIC]
Hsu, Chih-Chung [Auteur]
National Cheng Kung University [NCKU]
Tai, Shen-Chieh [Auteur]
National Cheng Kung University [NCKU]
Chen, Shao-Ning [Auteur]
National Cheng Kung University [NCKU]
Tricarico, Davide [Auteur]
Università degli studi di Torino = University of Turin [UNITO]
Chaudhry, Hafiza [Auteur]
Università degli studi di Torino = University of Turin [UNITO]
Fiandrotti, Attilio [Auteur]
Università degli studi di Torino = University of Turin [UNITO]
Grangetto, Marco [Auteur]
Università degli studi di Torino = University of Turin [UNITO]
Spatafora, Maria [Auteur]
Università degli studi di Catania = University of Catania [Unict]
Ortis, Alessandro [Auteur]
Università degli studi di Catania = University of Catania [Unict]
Battiato, Sebastiano [Auteur]
Università degli studi di Catania = University of Catania [Unict]

Journal title :

Sensors

Publisher :

MDPI

Publication date :

2024-02-28

ISSN :

1424-8220

English keyword(s) :

COVID-19
convolutional neural network
deep learning
segmentation
Per-COVID-19
transformer
estimation

HAL domain(s) :

Informatique [cs]/Imagerie médicale
Informatique [cs]/Apprentissage [cs.LG]
Sciences du Vivant [q-bio]/Médecine humaine et pathologie/Maladies émergentes
Sciences du Vivant [q-bio]/Médecine humaine et pathologie/Maladies infectieuses
Sciences du Vivant [q-bio]/Médecine humaine et pathologie/Pneumologie et système respiratoire

English abstract : [en]

COVID-19 analysis from medical imaging is an important task that has been intensively studied in the last years due to the spread of the COVID-19 pandemic. In fact, medical imaging has often been used as a complementary ...
Show more >COVID-19 analysis from medical imaging is an important task that has been intensively studied in the last years due to the spread of the COVID-19 pandemic. In fact, medical imaging has often been used as a complementary or main tool to recognize the infected persons. On the other hand, medical imaging has the ability to provide more details about COVID-19 infection, including its severity and spread, which makes it possible to evaluate the infection and follow-up the patient’s state. CT scans are the most informative tool for COVID-19 infection, where the evaluation of COVID-19 infection is usually performed through infection segmentation. However, segmentation is a tedious task that requires much effort and time from expert radiologists. To deal with this limitation, an efficient framework for estimating COVID-19 infection as a regression task is proposed. The goal of the Per-COVID-19 challenge is to test the efficiency of modern deep learning methods on COVID-19 infection percentage estimation (CIPE) from CT scans. Participants had to develop an efficient deep learning approach that can learn from noisy data. In addition, participants had to cope with many challenges, including those related to COVID-19 infection complexity and crossdataset scenarios. This paper provides an overview of the COVID-19 infection percentage estimation challenge (Per-COVID-19) held at MIA-COVID-2022. Details of the competition data, challenges, and evaluation metrics are presented. The best performing approaches and their results are described and discussedShow less >

Language :

Anglais

Popular science :

Non

Collections :

• Institut d'Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520

Source :

Harvested from HAL