Explainable COVID-19 Classification Via Variational and Perceptual Autoencoder-Guided Occlusion
DOI:
https://doi.org/10.19153/cleiej.29.3.6Keywords:
COVID classification, Artificial Vision, Variational autoncoder, Perceptual autoncoderAbstract
Technology played a crucial role in combating the COVID pandemic, both in the rapid
development of vaccines and the early detection of the virus. Consequently, numerous
studies in the medical field have focused on leveraging the power of artificial intelligence
for COVID-19 detection. However, in the medical domain, it is essential to have a clear
understanding of the processes and algorithms used in decision-making, as these directly
impact people’s health. Therefore, efforts have been made to implement explainable
artificial intelligence techniques, enabling humans to understand and explain the deep
learning algorithms used in disease detection. In this work, we present an approach to
detecting COVID-19 in chest X-rays that combines reconstruction-based anomaly discov-
ery with perturbation-based attribution. Specifically, we use a Variational Autoencoder
trained on healthy lungs to identify lung anomalies, and we additionally evaluate a Per-
ceptual Autoencoder (PAE) that incorporates a perceptual loss to produce sharper recon-
structions and more contrastive residual maps. These signals are then used to highlight
critical image evidence through both patch-level scoring (grid-based occlusion) and pixel-
level masking derived from reconstruction-error maps, enabling healthcare professionals
to localize relevant regions more effectively. Moreover, the proposed framework provides
clearer explanations of the model’s decisions by quantifying the prediction change after
occluding the identified regions, reducing the complexity of the “black boxes” generated
by deep learning neural networks. With this methodology, we aim to improve the effec-
tiveness and reliability of early COVID-19 detection through chest X-rays.
References
PLOS Biology, “A positive feedback synapse from retinal horizontal cells to cone photoreceptors,” PLOS Biology, May 03 2011.
Organizaci´on Mundial de la Salud, “Brote de enfermedad por coronavirus (covid-19),” https://www. who.int/es/emergencies/diseases/novel-coronavirus-2019, n.d.
Gobierno de Chile, “Cifras oficiales del plan paso a paso,” n.d. [Online]. Available: https:
//www.gob.cl/pasoapaso/cifrasoficiales/
National Library of Medicine, “Diagn´ostico radiol´ogico del paciente con covid-19,” National Library of Medicine (NCBI), Nov 24 2020. [Online]. Available: https://www.ncbi.nlm.nih.gov/pmc/articles/
PMC7685043/
European Journal of Radiology, “Artificial intelligence for imaging-based covid-19 detection:
Systematic review comparing added value of ai versus human readers,” European Journal of Radiology, Nov 16 2021. [Online]. Available: https://doi.org/10.1016/j.ejrad.2021.110028
B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, “Learning deep features for discriminative localization,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2921–2929.
R. Bayuk, J. Manquel, O. Nicolis, L. Caro, and B. Peralta, “Explainable covid-19 classification via variational autoencoder-guided patch occlusion,” in 2025 LI Latin American Computer Conference (CLEI). IEEE, 2025, pp. 1–10.
I. Allaouzi and M. Ahmed, “A novel approach for multi-label chest x-ray classification of common thorax diseases,” IEEE Access, vol. PP, pp. 1–1, 05 2019.
M. Hanif, M. Bilal, A. Alsaggaf, and U. Al-Saggaf, “Enhancing multi-label chest x-ray classification using an improved ranking loss,” Bioengineering, vol. 12, no. 6, p. 593, 2025. [Online]. Available: https://doi.org/10.3390/bioengineering12060593
X. Zhao and X. Wang, “Multi-label chest x-ray image classification based on long-range dependencies capture and label relationships learning,” Biomedical Signal Processing and Control, vol. 100, p. 107018, 2025.
M. Chetoui, M. Akhloufi, B. Yousefi, and E. Bouattane, “Explainable covid-19 detection on chest x-rays using an end-to-end deep convolutional neural network architecture,” Big Data and Cognitive Computing, vol. 5, no. 4, p. 73, 2021.
J. Rocha, S. Pereira, P. Sousa et al., “Clare-xr: Explainable regression-based classification of chest radiographs with label embeddings,” Scientific Reports, vol. 14, p. 31024, 2024.
R. F. Mansour, J. Escorcia-Gutierrez, M. Gamarra, D. Gupta, O. Castillo, and S. Kumar, “Unsupervised deep learning based variational autoencoder model for covid-19 diagnosis and classification,” Pattern Recognition Letters, vol. 151, pp. 267–274, 2021.
D. Addo, S. Zhou, J. Jackson, G. Nneji, H. Monday, K. Sarpong, R. Patamia, F. Ekong, and C. OwusuAgyei, “Evae-net: An ensemble variational autoencoder deep learning network for covid-19 classification based on chest x-ray images,” Diagnostics, vol. 12, no. 11, p. 2569, 2022.
Q. Zhou, S. Wang, X. Zhang, and Y. Zhang, “Wvale: Weak variational autoencoder for localisation and enhancement of covid-19 lung infections,” Computer Methods and Programs in Biomedicine, vol. 221, p. 106883, June 2022.
N. Jahan and M. A. Hasan, “Autoencoder-based unsupervised anomaly detection for covid-19 screening on chest x-ray images,” in 2022 19th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE), 11 2022, pp. 1–6.
H. Guan, P.-T. Yap, A. Bozoki, and M. Liu, “Federated learning for medical image analysis: A survey,” Pattern recognition, vol. 151, p. 110424, 2024.
X. Chen, X. Wang, K. Zhang, K. Fung, T. Thai, K. Moore, R. Mannel, H. Liu, B. Zheng, and Y. Qiu, “Recent advances and clinical applications of deep learning in medical image analysis,” Medical Image Analysis, vol. 79, p. 102444, July 2022.
J. Mart´?nez, O. Nicolis, L. Caro, and B. Peralta, “A proposal for the deep unsupervised identification of relevant areas in x-rays for covid detection,” in 2021 IEEE Chilean Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON). IEEE, 2021, pp. 1–6.
G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4700–4708.
D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” in 2nd International Conference on Learning Representations, 2014.
R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The unreasonable effectiveness of deep features as a perceptual metric,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
A. Dosovitskiy and T. Brox, “Generating images with perceptual similarity metrics based on deep networks,” in Advances in Neural Information Processing Systems (NeurIPS), 2016.
T. Rahman, S. C. H. Hossain, M. Shishir et al., “Covid-19 radiography database,” https://www.kaggle.com/tawsifurrahman/covid19-radiography-database, 2020, accessed: 2025-06-05.
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-cam: Visual explanations from deep networks via gradient-based localization,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 618–626.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rodrigo Bayuk, Joel Manquel, Orietta Nicolis, Billy Peralta, Luis Caro
This work is licensed under a Creative Commons Attribution 4.0 International License.
CLEIej is supported by its home institution, CLEI, and by the contribution of the Latin American and international researchers community, and it does not apply any author charges whatsoever for submitting and publishing. Since its creation in 1998, all contents are made publicly accesibly. The current license being applied is a (CC)-BY license (effective October 2015; between 2011 and 2015 a (CC)-BY-NC license was used).
