Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1101452

Automatic Evaluation of the Lung Condition of COVID-19 Patients Using X-ray Images and Convolutional Neural Networks


Lorencin, Ivan; Baressi Šegota, Sandi; Anđelić, Nikola; Blagojević, Anđela; Šušteršič, Tijana; Protić, Alen; Arsenijević, Miloš; Ćabov, Tomislav; Filipović, Nenad; Car, Zlatan
Automatic Evaluation of the Lung Condition of COVID-19 Patients Using X-ray Images and Convolutional Neural Networks // Journal of personalized medicine, 11 (2021), 1; 28, 31 doi:10.3390/jpm11010028 (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 1101452 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Automatic Evaluation of the Lung Condition of COVID-19 Patients Using X-ray Images and Convolutional Neural Networks

Autori
Lorencin, Ivan ; Baressi Šegota, Sandi ; Anđelić, Nikola ; Blagojević, Anđela ; Šušteršič, Tijana ; Protić, Alen ; Arsenijević, Miloš ; Ćabov, Tomislav ; Filipović, Nenad ; Car, Zlatan

Izvornik
Journal of personalized medicine (2075-4426) 11 (2021), 1; 28, 31

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
AlexNet ; convolutional neural network ; COVID-19 ; ResNet ; VGG-16

Sažetak
COVID-19 represents one of the greatest challenges in modern history. Its impact is most noticeable in the health care system, mostly due to the accelerated and increased influx of patients with a more severe clinical picture. These facts are increasing the pressure on health systems. For this reason, the aim is to automate the process of diagnosis and treatment. The research presented in this article conducted an examination of the possibility of classifying the clinical picture of a patient using X-ray images and convolutional neural networks. The research was conducted on the dataset of 185 images that consists of four classes. Due to a lower amount of images, a data augmentation procedure was performed. In order to define the CNN architecture with highest classification performances, multiple CNNs were designed. Results show that the best classification performances can be achieved if ResNet152 is used. This CNN has achieved AUCmacro and AUCmicro up to 0.94, suggesting the possibility of applying CNN to the classification of the clinical picture of COVID-19 patients using an X-ray image of the lungs. When higher layers are frozen during the training procedure, higher AUCmacro and AUCmicro values are achieved. If ResNet152 is utilized, AUCmacro and AUCmicro values up to 0.96 are achieved if all layers except the last 12 are frozen during the training procedure.

Izvorni jezik
Engleski

Znanstvena područja
Interdisciplinarne tehničke znanosti, Temeljne medicinske znanosti



POVEZANOST RADA


Projekti:
Ostalo-CEI - 305.6019-20 - USE OF REGRESSIVE ARTIFICIAL INTELLIGENCE (AI) AND MACHINE LEARNING (ML) METHODS IN MODELLING OF COVID-19 SPREAD – COVIDAI (COVIDAi) (Car, Zlatan, Ostalo - CEI Extraordinary Call for Proposals 2020) ( POIROT)
InoUstZnVO-CIII-HR-0108-10 - Concurrent Product and Technology Development - Teaching, Research and Implementation of Joint Programs Oriented in Production and Industrial Engineering (Car, Zlatan, InoUstZnVO - CEEPUS) ( POIROT)
MINGO-ESIF-KK.01.2.2.03.0004 - Centar kompetencija za pametne gradove (CEKOM – Centar kompetencija za pametne gradove) (Car, Zlatan, MINGO - Podrška razvoju centara kompetencija u okviru Operativnog programa Konkurentnost i kohezija 2014.-2020.) ( POIROT)
NadSve-Sveučilište u Rijeci-uniri-tehnic-18-275-1447 - Razvoj inteligentnog ekspertnog sustava za online diagnostiku raka mokračnog mjehura (Car, Zlatan, NadSve - UNIRI potpore) ( POIROT)

Ustanove:
Medicinski fakultet, Rijeka,
Tehnički fakultet, Rijeka,
Klinički bolnički centar Rijeka,
Fakultet dentalne medicine, Rijeka

Profili:

Avatar Url Zlatan Car (autor)

Avatar Url Tomislav Ćabov (autor)

Avatar Url Nikola Anđelić (autor)

Avatar Url Alen Protić (autor)

Avatar Url Ivan Lorencin (autor)

Citiraj ovu publikaciju

Lorencin, Ivan; Baressi Šegota, Sandi; Anđelić, Nikola; Blagojević, Anđela; Šušteršič, Tijana; Protić, Alen; Arsenijević, Miloš; Ćabov, Tomislav; Filipović, Nenad; Car, Zlatan
Automatic Evaluation of the Lung Condition of COVID-19 Patients Using X-ray Images and Convolutional Neural Networks // Journal of personalized medicine, 11 (2021), 1; 28, 31 doi:10.3390/jpm11010028 (međunarodna recenzija, članak, znanstveni)
Lorencin, I., Baressi Šegota, S., Anđelić, N., Blagojević, A., Šušteršič, T., Protić, A., Arsenijević, M., Ćabov, T., Filipović, N. & Car, Z. (2021) Automatic Evaluation of the Lung Condition of COVID-19 Patients Using X-ray Images and Convolutional Neural Networks. Journal of personalized medicine, 11 (1), 28, 31 doi:10.3390/jpm11010028.
@article{article, year = {2021}, pages = {31}, DOI = {10.3390/jpm11010028}, chapter = {28}, keywords = {AlexNet, convolutional neural network, COVID-19, ResNet, VGG-16}, journal = {Journal of personalized medicine}, doi = {10.3390/jpm11010028}, volume = {11}, number = {1}, issn = {2075-4426}, title = {Automatic Evaluation of the Lung Condition of COVID-19 Patients Using X-ray Images and Convolutional Neural Networks}, keyword = {AlexNet, convolutional neural network, COVID-19, ResNet, VGG-16}, chapternumber = {28} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • Social Science Citation Index (SSCI)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Citati





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font