prikaz prve stranice dokumenta Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework
  Download
PDF 33.93 MB
Scientific paper - Original scientific paper
Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework
Diagnostics, 13 (2023), 11; 1954. https://doi.org/10.3390/diagnostics13111954
Dubey, Arun Kumar; Chabert, Gian Luca; Carriero, Alessandro; Pasche, Alessio; Danna, Pietro S. C.; Agarwal, Sushant; Mohanty, Lopamudra; Nillmani, Lopamudra; Sharma, Neeraj; Yadav, Sarita; Jain, Achin; Kumar, Ashish; Kalra, Mannudeep K.; Sobel, David W.; Laird, John R.; Singh, Inder M.; Singh, Narpinder; Tsoulfas, George; Fouda, Mostafa M.; Alizad, Azra; Kitas, George D.; Khanna, Narendra N.; Viskovic, Klaudija; Kukuljan, Melita; Al-Maini, Mustafa; El-Baz, Ayman; Saba, Luca; Suri, Jasjit S. More authors...

Institutional repository: Repository of the University of Rijeka, Faculty of Medicine

Cite this document

Dubey, A. K., Chabert, G. L., Carriero, A., Pasche, A., Danna, P. S. C., Agarwal, S. ... Suri, J. S. (2023). Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework. Diagnostics, 13. (11). doi: 10.3390/diagnostics13111954

Dubey, Arun Kumar, et al. "Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework." Diagnostics, vol. 13, no. 11, 2023. https://doi.org/10.3390/diagnostics13111954

Dubey, Arun Kumar, Gian Luca Chabert, Alessandro Carriero, Alessio Pasche, Pietro S. C. Danna, Sushant Agarwal, Lopamudra Mohanty, et al. "Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework." Diagnostics 13, no. 11 (2023). https://doi.org/10.3390/diagnostics13111954

Dubey, A. K., et al. (2023) 'Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework', Diagnostics, 13(11). doi: 10.3390/diagnostics13111954

Dubey AK, Chabert GL, Carriero A, Pasche A, Danna PSC, Agarwal S, and sur.. Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework. Diagnostics [Internet]. 2023 June 02 [cited 2024 May 16];13(11). doi: 10.3390/diagnostics13111954

A. K. Dubey, et al., "Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework", Diagnostics, vol. 13, no. 11, June 2023. [Online]. Available at: https://urn.nsk.hr/urn:nbn:hr:184:366471. [Accessed: 16 May 2024]

Metadata
Title (english)Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework
AuthorArun Kumar Dubey
AuthorGian Luca Chabert
AuthorAlessandro Carriero
AuthorAlessio Pasche
AuthorPietro S. C. Danna
AuthorSushant Agarwal
AuthorLopamudra Mohanty
AuthorLopamudra Nillmani
AuthorNeeraj Sharma
AuthorSarita Yadav
AuthorAchin Jain
AuthorAshish Kumar
AuthorMannudeep K. Kalra
AuthorDavid W. Sobel
AuthorJohn R. Laird
AuthorInder M. Singh
AuthorNarpinder Singh
AuthorGeorge Tsoulfas
AuthorMostafa M. Fouda
AuthorAzra Alizad
AuthorGeorge D. Kitas
AuthorNarendra N. Khanna
AuthorKlaudija Viskovic
AuthorMelita Kukuljan
AuthorMustafa Al-Maini
AuthorAyman El-Baz
AuthorLuca Saba
AuthorJasjit S. Suri
Author's institution(Clinical Hospital Center Rijeka)
Author's institutionUniversity of Rijeka
Faculty of Medicine
(Department of Radiology)
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Clinical Medical Sciences
Radiology
Abstract (english)
Background and motivation: Lung computed tomography (CT) techniques are high-resolution and are well adopted in the intensive care unit (ICU) for COVID-19 disease control classification. Most artificial intelligence (AI) systems do not undergo generalization and are typically overfitted. Such trained AI systems are not practical for clinical settings and therefore do not give accurate results when executed on unseen data sets. We hypothesize that ensemble deep learning (EDL) is superior to deep transfer learning (TL) in both non-augmented and augmented frameworks. Methodology: The system consists of a cascade of quality control, ResNet–UNet-based hybrid deep learning for lung segmentation, and seven models using TL-based classification followed by five types of EDL’s. To prove our hypothesis, five different kinds of data combinations (DC) were designed using a combination of two multicenter cohorts—Croatia (80 COVID) and Italy (72 COVID and 30 controls)—leading to 12,000 CT slices. As part of generalization, the system was tested on unseen data and statistically tested for reliability/stability. Results: Using the K5 (80:20) cross-validation protocol on the balanced and augmented dataset, the five DC datasets improved TL mean accuracy by 3.32%, 6.56%, 12.96%, 47.1%, and 2.78%, respectively. The five EDL systems showed improvements in accuracy of 2.12%, 5.78%, 6.72%, 32.05%, and 2.40%, thus validating our hypothesis. All statistical tests proved positive for reliability and stability. Conclusion: EDL showed superior performance to TL systems for both (a) unbalanced and unaugmented and (b) balanced and augmented datasets for both (i) seen and (ii) unseen paradigms, validating both our hypotheses.
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionPublished version
Journal titleDiagnostics
Numberingvol. 13, no. 11, 1954
e-ISSN2075-4418
DOIhttps://doi.org/10.3390/diagnostics13111954
URN:NBNurn:nbn:hr:184:366471
Publication2023-06-02
Document URLhttps://www.mdpi.com/2075-4418/13/11/1954
Type of resourceText
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2023-06-19 12:16:58