SARS-CoV-2 Detection in Genosensor Images via Deep Learning and Data Augmentation

Ana Beatriz S. Zerati; Luan B. Guerra; Osvaldo N. Oliveira Jr; Lucas C. Ribas

doi:10.22456/2175-2745.150894

Authors

Ana Beatriz S. Zerati Universidade Estadual Paulista (Unesp) https://orcid.org/0009-0005-9051-6522
Luan B. Guerra Universidade Estadual Paulista (Unesp)
Osvaldo N. Oliveira Jr Universidade de São Paulo (USP) https://orcid.org/0000-0002-5399-5860
Lucas C. Ribas Universidade Estadual Paulista (Unesp) https://orcid.org/0000-0003-2490-180X

DOI:

https://doi.org/10.22456/2175-2745.150894

Keywords:

data augmentation, genosensors, deep learning

Abstract

This work addresses the challenge of classifying genosensor images obtained by scanning electron microscopy (SEM) for SARS-CoV-2 diagnosis. Due to the specialized nature of the data, image datasets are inherently small, which limits the effectiveness of deep learning models. To overcome this limitation, we investigated the impact of seven data augmentation strategies - Flipping, Shift, Random Erasing, AugMix, AutoAugment, RandAugment and TrivialAugment - on the performance of four Convolutional Neural Networks (CNNs): ResNet50, ResNet101, DenseNet121, and ConvNeXt-Tiny. Our analyses demonstrated that data augmentation is crucial for the success of the task, achieving a remarkable accuracy of 97.85%, surpassing both traditional feature extraction methods and previously tested deep learning approaches. Furthermore, our findings indicate that the choice of augmentation technique is critical, with aggressive methods proving detrimental for highly specialized microscopy data.

Downloads

Download data is not yet available.

References

[1] SEO, G. et al. Rapid detection of COVID-19 causative virus (SARS-CoV-2) in human nasopharyngeal swab specimens using field-effect transistor-based biosensor. ACS Nano, American Chemical Society (ACS), v. 14, n. 4, p. 5135–5142, abr. 2020. ISSN 1936-086X. Disponível em: ⟨http://dx.doi.org/10.1021/acsnano.0c02823⟩.

[2] BABAEI, A. et al. Genosensors as an alternative diagnostic sensing approaches for specific detection of virus species: A review of common techniques and outcomes. TrAC Trends in Analytical Chemistry, Elsevier BV, v. 155, p. 116686, out. 2022. ISSN 0165-9936. Disponível em: ⟨http://dx.doi.org/10.1016/j.trac.2022.116686⟩.

[3] SOARES, J. C. et al. Detection of a SARS-CoV-2 sequence with genosensors using data analysis based on information visualization and machine learning techniques. Materials Chemistry Frontiers, Royal Society of Chemistry (RSC), v. 5, n. 15, p. 5658–5670, 2021. ISSN 2052-1537. Disponível em: ⟨http://dx.doi.org/10.1039/D1QM00665G⟩.

[4] RODRIGUES, V. C. et al. Electrochemical and optical detection and machine learning applied to images of genosensors for diagnosis of prostate cancer with the biomarker PCA3. Talanta, Elsevier BV, v. 222, p. 121444, jan. 2021. ISSN 0039-9140. Disponível em: ⟨http://dx.doi.org/10.1016/j.talanta.2020.121444⟩.

[5] SHORTEN, C.; KHOSHGOFTAAR, T. M. A survey on image data augmentation for deep learning. Journal of Big Data, Springer Science and Business Media LLC, v. 6, n. 1, jul. 2019. ISSN 2196-1115. Disponível em: ⟨http://dx.doi.org/10.1186/s40537-019-0197-0⟩.

[6] GOCERI, E. Medical image data augmentation: techniques, comparisons and interpretations. Artificial Intelligence Review, Springer Science and Business Media LLC, v. 56, n. 11, p. 12561–12605, mar. 2023. ISSN 1573-7462. Disponível em: ⟨http://dx.doi.org/10.1007/s10462-023-10453-z⟩.

[7] CUNHA, I. et al. Machine learning in microscopy – insights, opportunities and challenges. Journal of Cell Science, The Company of Biologists, v. 137, n. 20, out. 2024. ISSN 1477-9137. Disponível em: ⟨http://dx.doi.org/10.1242/jcs.262095⟩.

[8] RIBAS, L. C.; CASACA, W.; FARES, R. T. Conditional generative adversarial networks and deep learning data augmentation: A multi-perspective data-driven survey across multiple application fields and classification architectures. AI, MDPI, v. 6, n. 2, p. 32, 2025.

[9] SCABINI, L. et al. A comparative survey of vision transformers for feature extraction in texture analysis. Journal of Imaging, MDPI, v. 11, n. 9, p. 304, 2025.

[10] WELSMAN, J. A. et al. Enhancing electron microscopy image classification using data augmentation. In: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis. [S.l.: s.n.], 2024. p. 64–71.

[11] ZHONG, Z. et al. Random erasing data augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), v. 34, n. 07, p. 13001–13008, abr. 2020. ISSN 2159-5399. Disponível em: ⟨http://dx.doi.org/10.1609/aaai.v34i07.7000⟩.

[12] CUBUK, E. D. et al. Autoaugment: Learning augmentation strategies from data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [S.l.]: IEEE, 2019. p. 113–123.

[13] CUBUK, E. D. et al. Randaugment: Practical automated data augmentation with a reduced search space. In: LAROCHELLE, H. et al. (Ed.). Advances in Neural Information Processing Systems. [S.l.]: Curran Associates, Inc., 2020. v. 33, p. 18613–18624.

[14] MÜLLER, S. G.; HUTTER, F. Trivialaugment: Tuning-free yet state-of-the-art data augmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, QC, Canada: IEEE, 2021. p. 774–782.

[15] HENDRYCKS, D. et al. AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty. arXiv, 2019. Disponível em: ⟨https://arxiv.org/abs/1912.02781⟩.

[16] KINGMA, D. P.; BA, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.