SHAP-Driven Explicability of CNN-Based Computer-Aided Diagnosis for Malaria

• Matheus Silva dos Santos UFAM
• Fagner Cunha UFAM
• Rafael Giusti UFAM
• Juan Gabriel Colonna UFAM

DOI: https://doi.org/10.5753/eniac.2025.13859

Abstract

Convolutional Neural Networks (CNN) hold great promise for medical image classification, but their clinical adoption depends on model reliability. In this study, we leverage Shapley Additive Explanations (SHAP) to explain a CNN-based Computer-Aided Diagnosis (CAD) system for malaria detection from microscopy images. We employ SHAP’s Gradient Explainer to highlight key pixel regions driving the CAD model predictions. By providing transparent, pixel-level insights, this approach empowers healthcare professionals to understand system decisions and enhances trust in automated malaria diagnosis.

References

Ali, M. S., Miah, M. S., Haque, J., Rahman, M. M., and Islam, M. K. (2021). An enhanced technique of skin cancer classification using deep convolutional neural network with transfer learning models. Machine Learning with Applications, 5:100036.

Ashley, E. A., Pyae Phyo, A., and Woodrow, C. J. (2018). Malaria. The Lancet, 391(10130):1608–1621.

Berezsky, O., Liashchynskyi, P., Pitsun, O., and Izonin, I. (2024). Synthesis of convolutional neural network architectures for biomedical image classification. Biomedical Signal Processing and Control, 95:106325.

Boit, S. and Patil, R. (2024). An efficient deep learning approach for malaria parasite detection in microscopic images. Diagnostics, 14(23):2738.

Chiodini, P. L. (2014). Malaria diagnostics: now and the future. Parasitology, 141(14):1873–1879.

Das, A., Sahu, W., Ojha, D. K., Reddy, K. S., and Suar, M. (2022). Comparative analysis of host metabolic alterations in murine malaria models with uncomplicated or severe malaria. Journal of Proteome Research, 21(10):2261–2276.

Eke, C. I. and Shuib, L. (2025). The role of explainability and transparency in fostering trust in ai healthcare systems: a systematic literature review, open issues and potential solutions. Neural Computing and Applications, 37(4):1999–2034.

Ersoy, I., Bunyak, F., Higgins, J. M., and Palaniappan, K. (2012). Coupled edge profile active contours for red blood cell flow analysis. In 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), pages 748–751. IEEE.

Gaouar, A., Cherif, S. H., Rahmoun, A., and Daho, M. E. H. (2025). Explainable ai for early malaria detection using stacked-lstm and attention mechanisms. Informatics in Medicine Unlocked, 57:101667.

Glowac, C., Ferrão, J. L., and Searle, K. M. (2024). The association between infrastructure damage in the aftermath of cyclone idai and malaria risk in sofala province, mozambique: an ecological study. Malaria Journal, 23(1):355.

Guerra, C. A., Gikandi, P. W., Tatem, A. J., Noor, A. M., Smith, D. L., Hay, S. I., and Snow, R. W. (2008). The limits and intensity of plasmodium falciparum transmission: implications for malaria control and elimination worldwide. PLoS medicine, 5(2):e38.

Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., and Pedreschi, D. (2018). A survey of methods for explaining black box models. ACM computing surveys (CSUR), 51(5):1–42.

Keras (2020). Keras: the Python deep learning API. Disponível em [link]. Acessado em 29 de setembro de 2022.

Liang, Z., Powell, A., Ersoy, I., Poostchi, M., Silamut, K., Palaniappan, K., Guo, P., Hossain, M. A., Sameer, A., Maude, R. J., et al. (2016). Cnn-based image analysis for malaria diagnosis. In 2016 IEEE international conference on bioinformatics and biomedicine (BIBM), pages 493–496. IEEE.

Lundberg, S. M. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30.

Megersa, D. M. and Luo, X.-S. (2025). Effects of climate change on malaria risk to human health: A review. Atmosphere, 16(1):71.

Molnar, C. (2022). Interpretable Machine Learning. 2 edition.

Moody, A. (2002). Rapid diagnostic tests for malaria parasites. Clinical microbiology reviews, 15(1):66–78.

NIH (2022). Malaria Datasheet. Disponível em [link]. Acessado em 10 de setembro de 2022.

Parvin, B., Yang, Q., Han, J., Chang, H., Rydberg, B., and Barcellos-Hoff, M. H. (2007). Iterative voting for inference of structural saliency and characterization of subcellular events. IEEE Transactions on Image Processing, 16(3):615–623.

Poostchi, M., Silamut, K., Maude, R. J., Jaeger, S., and Thoma, G. (2018). Image analysis and machine learning for detecting malaria. Translational Research, 194:36–55.

Rajaraman, S., Antani, S. K., Poostchi, M., Silamut, K., Hossain, M. A., Maude, R. J., Jaeger, S., and Thoma, G. R. (2018a). Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images. PeerJ, 6:e4568.

Rajaraman, S., Silamut, K., Hossain, M. A., Ersoy, I., Maude, R. J., Jaeger, S., Thoma, G. R., and Antani, S. K. (2018b). Understanding the learned behavior of customized convolutional neural networks toward malaria parasite detection in thin blood smear images. Journal of Medical Imaging, 5(3):034501–034501.

SHAP (2020). Welcome to the SHAP documentation. Disponível em [link]. Acessado em 18 de junho de 2022.

Shapiro, H. M., Apte, S. H., Chojnowski, G. M., Hänscheid, T., Rebelo, M., and Grimberg, B. T. (2013). Cytometry in malaria—a practical replacement for microscopy? Current Protocols in Cytometry, 65(1):11–20.

Shapley, L. S. (1988). A value for n-person games. The Shapley value: essays in honor of Lloyd S. Shapley, page 31.

Sokolova, M., Japkowicz, N., and Szpakowicz, S. (2006). Beyond accuracy, f-score and roc: a family of discriminant measures for performance evaluation. In Australasian joint conference on artificial intelligence, pages 1015–1021. Springer.

Yadav, A., Verma, K., Singh, K., Tyagi, S., Kori, L., and Bharti, P. K. (2024). Analysis of diagnostic biomarkers for malaria: Prospects on rapid diagnostic test (rdt) development. Microbial Pathogenesis, 196:106978.