Interpretabilidade de modelos de aprendizado de máquina para a classificação de lesões celulares

• Pedro A. Euzébio UFOP
• Rafael A. B. de Queiroz UFOP
• Daniela C. Terra UFOP
• Mariana T. Rezende UFOP
• Claudia M. Carneiro UFOP
• Andrea G. Campos Bianchi UFOP

DOI: https://doi.org/10.5753/sbcas.2023.230028

Abstract

Due to the widespread use of machine learning algorithms to automate decision-making processes, it is important that they are interpretable to prove themselves reliable. However, although learning achieves cutting-edge results in real-world applications, the its excessive number of parameters is not well understood by humans. In this work, the Local Interpretable Model Agnostic Explanations (LIME) method was used for the interpretability of random forest models constructed in the context of cervical cell image classifications. The results obtained were individual explanations of the most representative instances of the database, followed by an analysis of occurrences of the characteristics among the generated explanations.

References

Barr Kumarakulasinghe, N., Blomberg, T., Liu, J., Saraiva Leao, A., and Papapetrou, P. (2020). Evaluating local interpretable model-agnostic explanations on clinical machine learning classification models. In 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), pages 7–12.

Chen, W., Gao, L., Li, X., and Shen, W. (2022). Lightweight convolutional neural network with knowledge distillation for cervical cells classification. Biomedical Signal Processing and Control, 71:103177.

Cohen, P. A., Jhingran, A., Oaknin, A., and Denny, L. (2019). Cervical cancer. The Lancet, 393(10167):169–182.

Diniz, D. N., Rezende, M. T., Bianchi, A. G. C., Carneiro, C. M., Ushizima, D. M., de Medeiros, F. N. S., and Souza, M. J. F. (2021). A hierarchical feature-based methodology to perform cervical cancer classification. Applied Sciences, 11(9).

Garreau, D. and von Luxburg, U. (2020). Explaining the explainer: A first theoretical analysis of lime. In Chiappa, S. and Calandra, R., editors, Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, volume 108 of Proceedings of Machine Learning Research, pages 1287–1296. PMLR.

Guanglu Sun, Shaobo Li, Y. C. and Lang, F. (2017). Cervical cancer diagnosis based on random forest. International Journal of Performability Engineering, 13(4):446.

Hamilton, N., Pantelic, R., Hanson, K., and Teasdale, R. (2007). Fast automated cell phenotype classification. BMC bioinformatics, 8:110.

Lundberg, S. M. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R., editors, Advances in Neural Information Processing Systems 30, pages 4765–4774. Curran Associates, Inc.

Marinakis, Y., Dounias, G., and Jantzen, J. (2009). Pap smear diagnosis using a hybrid intelligent scheme focusing on genetic algorithm based feature selection and nearest neighbor classification. Computers in Biology and Medicine, 39(1):69–78.

N. Diniz, D., T. Rezende, M., G. C. Bianchi, A., M. Carneiro, C., J. S. Luz, E., J. P. Moreira, G., M. Ushizima, D., N. S. de Medeiros, F., and J. F. Souza, M. (2021). A deep learning ensemble method to assist cytopathologists in pap test image classification. Journal of Imaging, 7(7).

Pangarkar, M. A. (2022). The bethesda system for reporting cervical cytology. Cytojournal, 19.

Rezende, M. T., Silva, R., Bernardo, F. d. O., Tobias, A. H., Oliveira, P. H., Machado, T. M., Costa, C. S., Medeiros, F. N., Ushizima, D. M., Carneiro, C. M., et al. (2021). Cric searchable image database as a public platform for conventional pap smear cytology data. Scientific Data, 8(1):1–8.

Ribeiro, M., Singh, S., and Guestrin, C. (2016). “why should I trust you?”: Explaining the predictions of any classifier. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pages 97–101, San Diego, California. Association for Computational Linguistics.

Terra, D., Lisboa, A., Rezende, M., Carneiro, C., and Bianchi, A. (2023). Shape-based Features Investigation for Preneoplastic Lesions on Cervical Cancer Diagnosis. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pages 506–513. SCITEPRESS - Science and Technology Publications.

Vellido, A. (2020). The importance of interpretability and visualization in machine learning for applications in medicine and health care. Neural Computing and Applications, 32:1–15.

WHO (2022). World health organization cervical cancer. Accessed = 2022-10-09.

Wright, T. C. (2007). Cervical cancer screening in the 21st century: is it time to retire the pap smear? Clinical obstetrics and gynecology, 50(2):313—323.