Edson Luiz Pontes Perger

Edson Luiz Pontes Perger

Auto-generated profile, based on publicly available information

Edson Luiz Pontes Perger


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
2 October 2024 in Life
Verified
Journal Article
Open access
PDF file
RGRamon Hernany Martins Gomes
Ramon Hernany Martins Gomes
EPEdson Luiz Pontes Perger
Edson Luiz Pontes Perger
LVLucas Hecker Vasques
Lucas Hecker Vasques
EGElaine Gagete
Elaine Gagete
RSRafael Simões
Rafael Simões
Background: The skin prick test (SPT) is used to diagnose sensitization to antigens. This study proposes a deep learning approach to infer wheal dimensions, aiming to reduce dependence on human interpretation. Methods: A dataset of SPT images (n = 5844) was used to infer a convolutional neural network for wheal segmentation (ML model). Three methods for inferring wheal dimensions were evaluated: the ML model; the standard protocol (MA1); and approximation of the area as an ellipse using diameters measured by an allergist (MA2). The results were compared with assisted image segmentation (AIS), the most accurate method. Bland–Altman analysis, distribution analyses, and correlation tests were applied to compare the methods. This study also compared the percentage deviation among these methods in determining the area of wheals with regular geometric shapes (n = 150) and with irregular shapes (n = 150). Results: The Bland–Altman analysis showed that the difference between methods was not correlated with the absolute area. The ML model achieved a segmentation accuracy of 85.88% and a strong correlation with the AIS method (ρ = 0.88), outperforming all other methods. Additionally, MA1 showed significant error (13.44 ± 13.95%) for pseudopods. Conclusions: The ML protocol can potentially automate the reading of SPT, offering greater accuracy than the standard protocol.

18 February 2022 in Brazilian Journal of Radiation Sciences
Verified
Journal Article
Open access
PDF file
EPEdson Luiz Pontes Perger
Edson Luiz Pontes Perger
RGRodrigo Sanchez Giarola
Rodrigo Sanchez Giarola
ILIzabella Santos Silva Lemes
Izabella Santos Silva Lemes
GAGabriel Augusto Arruda
Gabriel Augusto Arruda
MFMarco Antônio Rodrigues Fernandes
Marco Antônio Rodrigues Fernandes
APAlexandre Dal Pai
Alexandre Dal Pai
All living things are constantly exposed to background radiation. The presence of radioactive materials in the earth's crust and cosmic radiation are largely responsible for this exposure. The present study aimed to develop a new methodology of easy applicability and low cost to carry out measurements of environmental background radiation and to be able to establish a map of environmental radiation for primary monitoring of these exposures. For that, ionizing radiation measurements, Meteorological and Radiometric measurements were performed. Geiger Mueller Counter (GM) was used, as it is widely used in services that use radioactive sources and research centers. Measurements obtained showed that there were no statistically significant changes in the 24 hours of measurements with the GM, in relation to the variations presented in the Meteorological and Radiometric measurements that changed according to the time of day. The average value of the background radiation readings was 0.0194 mR/h, with an average variance of 1.8E-06 and an average standard deviation of 1.35E-03. GM proved to be useful for primary measurement of background radiation. The map was developed using open source libraries for the Python programming language. The map may be hosted on an open access website, so that professionals, students and researchers may contribute, sending new data from different locations. It is essential that the levels of radiation exposure are demonstrated and understood. Easy access to this information may contribute to health organizations, agriculture and research centers to establish a baseline for future research.

27 August 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
RGRamon Hernany Martins Gomes
Ramon Hernany Martins Gomes
EPEdson Luiz Pontes Perger
Edson Luiz Pontes Perger
LVLucas Hecker Vasques
Lucas Hecker Vasques
ESElaine Gagete Miranda Da Silva
Elaine Gagete Miranda Da Silva
RSRafael Simões
Rafael Simões
Background: The skin prick test (SPT) is used to diagnose sensitization to antigens. This study proposes a deep learning approach to infer wheal dimensions, aiming to reduce dependence on human interpretation. Methods: A dataset of SPT images (n=5844) was used to infer a convolutional neural network for wheal segmentation (ML model). Three methods for inferring wheal dimensions were evaluated: the ML model; the standard protocol (MA1); and approximation of the area as an ellipse using diameters measured by an allergist (MA2). The results were compared with assisted image segmentation (AIS), the most accurate method. Bland-Altman, distribution analyses, and correlation tests were applied to compare the methods. The study also compared the percentage deviation among these methods in determining the area of wheals with regular geometric shapes (n = 150) and with irregular shapes (n=150). Results: The Bland-Altman analysis showed that the difference between methods was not correlated with the absolute area. The ML model achieved a segmentation accuracy of 85.88% and a strong correlation with the AIS method (ρ=0.88), outperforming all other methods. Additionally, MA1 showed significant error (13.44±13.95%) for pseudopods. Conclusions: The ML protocol can potentially automate the reading of SPT, offering greater accuracy than the standard protocol.