George Darmiton da Cunha Cavalcanti

Prof. George Darmiton da Cunha Cavalcanti

Universidade Federal de Pernambuco (UFPE)
orcid

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2018 in Information Fusion
Verified
Journal Article
Closed access
RCRafael M.O. Cruz
Rafael M.O. Cruz
RSRobert Sabourin
Robert Sabourin
GCGeorge Darmiton da Cunha Cavalcanti
George Darmiton da Cunha Cavalcanti

15 December 2022 in Applied Soft Computing
Verified
Journal Article
Closed access
LALucas B.V. de Amorim
Lucas B.V. de Amorim
GCGeorge Darmiton da Cunha Cavalcanti
George Darmiton da Cunha Cavalcanti
RCRafael M.O. Cruz
Rafael M.O. Cruz

1 October 2013 in Expert Systems with Applications
Verified
Journal Article
Closed access
RFRafael Ferreira
Rafael Ferreira
LCLuciano de Souza Cabral
Luciano de Souza Cabral
RLRafael Dueire Lins
Rafael Dueire Lins
GSGabriel Pereira e Silva
Gabriel Pereira e Silva
FFFred Freitas
Fred Freitas
LFLuciano Favaro
Luciano Favaro

1 May 2015 in Pattern Recognition
Verified
Journal Article
Closed access
RCRafael M.O. Cruz
Rafael M.O. Cruz
RSRobert Sabourin
Robert Sabourin
GCGeorge Darmiton da Cunha Cavalcanti
George Darmiton da Cunha Cavalcanti
TRTsang Ing Ren
Tsang Ing Ren

27 October 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Lucas Oliveira TeixeiraLucas Oliveira Teixeira
Lucas Oliveira Teixeira
Rodolfo Miranda PereiraRodolfo Miranda Pereira
Rodolfo Miranda Pereira
DBDiego Bertolini
Diego Bertolini
LOLuiz Eduardo Oliveira
Luiz Eduardo Oliveira
Loris NanniLoris Nanni
Loris Nanni
YCYandre Maldonado e Gomes Costa
Yandre Maldonado e Gomes Costa
COVID-19 frequently provokes pneumonia, which can be diagnosed using imaging exams. Chest X-ray (CXR) is often useful because it is cheap, fast, widespread, and uses less radiation. Here, we demonstrate the impact of lung segmentation in COVID-19 identification using CXR images and evaluate which contents of the image influenced the most. Semantic segmentation was performed using a U-Net CNN architecture, and the classification using three CNN architectures (VGG, ResNet, and Inception). Explainable Artificial Intelligence techniques were employed to estimate the impact of segmentation. A three-classes database was composed: lung opacity (pneumonia), COVID-19, and normal. We assessed the impact of creating a CXR image database from different sources, and the COVID-19 generalization from one source to another. The segmentation achieved a Jaccard distance of 0.034 and a Dice coefficient of 0.982. The classification using segmented images achieved an F1-Score of 0.88 for the multi-class setup, and 0.83 for COVID-19 identification. In the cross-dataset scenario, we obtained an F1-Score of 0.74 and an area under the ROC curve of 0.9 for COVID-19 identification using segmented images. Experiments support the conclusion that even after segmentation, there is a strong bias introduced by underlying factors from different sources.

1 April 2018 in Neurocomputing
Verified
Journal Article
Closed access
ARAnandarup Roy
Anandarup Roy
RCRafael M.O. Cruz
Rafael M.O. Cruz
RSRobert Sabourin
Robert Sabourin
GCGeorge Darmiton da Cunha Cavalcanti
George Darmiton da Cunha Cavalcanti