COVLIAS 1.0Lesion vs. MedSeg An Artificial Intelligence Framework for Automated Lesion Segmentation in COVID-19 Lung Computed Tomography Scans /

COVID-19 is a disease with multiple variants, and is quickly spreading throughout the world. It is crucial to identify patients who are suspected of having COVID-19 early, because the vaccine is not readily available in certain parts of the world.Lung computed tomography (CT) imaging can be used to...

Teljes leírás

Elmentve itt :
Bibliográfiai részletek
Szerzők: Suri Jasjit S
Agarwal Sushant
Chabert Gian Luca
Carriero Alessandro
Paschè Alessio
Danna Pietro S. C.
Saba Luca
Mehmedovic Armin
Faa Gavino
Singh Inder M.
Turk Monika
Chadha Paramjit S.
Johri Amer M.
Nagy Ferenc Tamás
Ruzsa Zoltán
Dokumentumtípus: Cikk
Megjelent: 2022
Sorozat:DIAGNOSTICS 12 No. 5
Tárgyszavak:
doi:10.3390/diagnostics12051283

mtmt:32913495
Online Access:http://publicatio.bibl.u-szeged.hu/24631
LEADER 03035nab a2200385 i 4500
001 publ24631
005 20220701100010.0
008 220701s2022 hu o 0|| Angol d
022 |a 2075-4418 
024 7 |a 10.3390/diagnostics12051283  |2 doi 
024 7 |a 32913495  |2 mtmt 
040 |a SZTE Publicatio Repozitórium  |b hun 
041 |a Angol 
100 1 |a Suri Jasjit S 
245 1 0 |a COVLIAS 1.0Lesion vs. MedSeg   |h [elektronikus dokumentum] :  |b An Artificial Intelligence Framework for Automated Lesion Segmentation in COVID-19 Lung Computed Tomography Scans /  |c  Suri Jasjit S 
260 |c 2022 
300 |a Terjedelem: 34 p.-Azonosító: 1283 
490 0 |a DIAGNOSTICS  |v 12 No. 5 
520 3 |a COVID-19 is a disease with multiple variants, and is quickly spreading throughout the world. It is crucial to identify patients who are suspected of having COVID-19 early, because the vaccine is not readily available in certain parts of the world.Lung computed tomography (CT) imaging can be used to diagnose COVID-19 as an alternative to the RT-PCR test in some cases. The occurrence of ground-glass opacities in the lung region is a characteristic of COVID-19 in chest CT scans, and these are daunting to locate and segment manually. The proposed study consists of a combination of solo deep learning (DL) and hybrid DL (HDL) models to tackle the lesion location and segmentation more quickly. One DL and four HDL models-namely, PSPNet, VGG-SegNet, ResNet-SegNet, VGG-UNet, and ResNet-UNet-were trained by an expert radiologist. The training scheme adopted a fivefold cross-validation strategy on a cohort of 3000 images selected from a set of 40 COVID-19-positive individuals.The proposed variability study uses tracings from two trained radiologists as part of the validation. Five artificial intelligence (AI) models were benchmarked against MedSeg. The best AI model, ResNet-UNet, was superior to MedSeg by 9% and 15% for Dice and Jaccard, respectively, when compared against MD 1, and by 4% and 8%, respectively, when compared against MD 2. Statistical tests-namely, the Mann-Whitney test, paired t-test, and Wilcoxon test-demonstrated its stability and reliability, with p < 0.0001. The online system for each slice was <1 s.The AI models reliably located and segmented COVID-19 lesions in CT scans. The COVLIAS 1.0Lesion lesion locator passed the intervariability test. 
650 4 |a Radiológia, sugárgyógyászat és orvosi képalkotás 
700 0 1 |a Agarwal Sushant  |e aut 
700 0 1 |a Chabert Gian Luca  |e aut 
700 0 1 |a Carriero Alessandro  |e aut 
700 0 1 |a Paschè Alessio  |e aut 
700 0 1 |a Danna Pietro S. C.  |e aut 
700 0 1 |a Saba Luca  |e aut 
700 0 1 |a Mehmedovic Armin  |e aut 
700 0 1 |a Faa Gavino  |e aut 
700 0 1 |a Singh Inder M.  |e aut 
700 0 1 |a Turk Monika  |e aut 
700 0 1 |a Chadha Paramjit S.  |e aut 
700 0 1 |a Johri Amer M.  |e aut 
700 0 1 |a Nagy Ferenc Tamás  |e aut 
700 0 1 |a Ruzsa Zoltán  |e aut 
856 4 0 |u http://publicatio.bibl.u-szeged.hu/24631/1/Suri2022.pdf  |z Dokumentum-elérés