Version 1
: Received: 26 August 2024 / Approved: 27 August 2024 / Online: 27 August 2024 (10:39:25 CEST)
How to cite:
Gomes, R. H. M.; Perger, E. L. P.; Vasques, L. H.; Silva, E. G. M. D.; Simões, R. P. Deep Learning Method Applied to Autonomous Image Diagnosis for Prick Test. Preprints2024, 2024081932. https://doi.org/10.20944/preprints202408.1932.v1
Gomes, R. H. M.; Perger, E. L. P.; Vasques, L. H.; Silva, E. G. M. D.; Simões, R. P. Deep Learning Method Applied to Autonomous Image Diagnosis for Prick Test. Preprints 2024, 2024081932. https://doi.org/10.20944/preprints202408.1932.v1
Gomes, R. H. M.; Perger, E. L. P.; Vasques, L. H.; Silva, E. G. M. D.; Simões, R. P. Deep Learning Method Applied to Autonomous Image Diagnosis for Prick Test. Preprints2024, 2024081932. https://doi.org/10.20944/preprints202408.1932.v1
APA Style
Gomes, R. H. M., Perger, E. L. P., Vasques, L. H., Silva, E. G. M. D., & Simões, R. P. (2024). Deep Learning Method Applied to Autonomous Image Diagnosis for Prick Test. Preprints. https://doi.org/10.20944/preprints202408.1932.v1
Chicago/Turabian Style
Gomes, R. H. M., Elaine Gagete Miranda Da Silva and Rafael Plana Simões. 2024 "Deep Learning Method Applied to Autonomous Image Diagnosis for Prick Test" Preprints. https://doi.org/10.20944/preprints202408.1932.v1
Abstract
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.
Keywords
deep learning applied to diagnosis; prick test; measurement of wheal area; IgE response; sensitization to antigens
Subject
Medicine and Pharmacology, Dermatology
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
