Interpretable Deep Learning Model For Cardiomegaly Detection with Chest X-ray Images

• Estela Ribeiro USP
• Diego A. C. Cardenas USP
• Jose E. Krieger USP
• Marco A. Gutierrez USP

DOI: https://doi.org/10.5753/sbcas.2023.229943

Resumo

Cardiomegaly is a medical disorder characterized by an enlargement of the heart. Many works propose to automatically detect cardiomegaly through chest X-rays. However, most of them are based on deep learning models, known for their lack of interpretability. This work propose a deep learning model for the detection of cardiomegaly based on chest x-rays images and the qualitative assessment of three known local explainable methods, i.e., Grad-CAM, LIME and SHAP. Our model achieved Acc, Prec, Se, Spe, F1-score and AUROC of 91.8±0.7%, 74.0±2.7%, 87.0±5.5%, 92.9±1.2%, 79.8±1.9%, and 90.0±0.7%, respectively. Moreover, except for the SHAP method, our interpretable methods were able to pinpoint the expected location for cardiomegaly. However, Grad-CAM method showed faster computational time than LIME and SHAP.

Referências

Alghamdi, S. S., Abdelaziz, I., Albadri, M., Alyanbaawi, S., Aljondi, R., and Tajaldeen, A. (2020). Study of cardiomegaly using chest x-ray. Journal of Radiation Research and Applied Sciences, 13(1):460–467.

Baltruschat, I. M., Nickisch, H., Grass, M., Knopp, T., and Saalbach, A. (2019). Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification. Scientific Reports, 9(1):6381.

Cardenas, D., Junior, J. F., Moreno, R., Rebelo, M., Krieger, J., and Gutierrez, M. (2020). Multicenter validation of convolutional neural networks for automated detection of cardiomegaly on chest radiographs. In Anais do XX Simpósio Brasileiro de Computação Aplicada à Saúde, pages 179–190, Porto Alegre, RS, Brasil. SBC.

Daines, B., Rao, S., Hosseini, O., Prieto, S., Abdelmalek, J., Elmassry, M., Sethi, P., Test, V., and Nugent, K. (2021). The clinical associations with cardiomegaly in patients undergoing evaluation for pulmonary hypertension. Journal of Community Hospital Internal Medicine Perspectives, 11(6):787–792.

Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255.

Hicks, S. A., Isaksen, J. L., Thambawita, V., Ghouse, J., Ahlberg, G., Linneberg, A., Grarup, N., Strümke, I., Ellervik, C., Olesen, M. S., Hansen, T., Graff, C., Holstein-Rathlou, N.-H., Halvorsen, P., Maleckar, M. M., Riegler, M. A., and Kanters, J. K. (2021). Explaining deep neural networks for knowledge discovery in electrocardiogram analysis. Scientific Reports, 11(1):10949.

Junior, J. R. F., Cardenas, D. A. C., Moreno, R. A., de Fátima de Sá Rebelo, M., Krieger, J. E., and Gutierrez, M. A. (2021). A general fully automated deep-learning method to detect cardiomegaly in chest x-rays. In Mazurowski, M. A. and Drukker, K., editors, Medical Imaging 2021: Computer-Aided Diagnosis, volume 11597, pages 537 – 542. International Society for Optics and Photonics, SPIE.

Lundberg, S. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. arXiv: 1705.07874.

Molnar, C. (2019). Interpretable Machine Learning.

Nguyen, H. Q., Lam, K., Le, L. T., Pham, H. H., Tran, D. Q., Nguyen, D. B., Le, D. D., Pham, C. M., Tong, H. T. T., Dinh, D. H., Do, C. D., Doan, L. T., Nguyen, C. N., Nguyen, B. T., Nguyen, Q. V., Hoang, A. D., Phan, H. N., Nguyen, A. T., Ho, P. H., Ngo, D. T., Nguyen, N. T., Nguyen, N. T., Dao, M., and Vu, V. (2020a). Vindr-cxr: An open dataset of chest x-rays with radiologist’s annotations.

Nguyen, H. Q., Lam, K., Le, L. T., Pham, H. H., Tran, D. Q., Nguyen, D. B., Le, D. D., Pham, C. M., Tong, H. T. T., Dinh, D. H., Do, C. D., Doan, L. T., Nguyen, C. N., Nguyen, B. T., Nguyen, Q. V., Hoang, A. D., Phan, H. N., Nguyen, A. T., Ho, P. H., Ngo, D. T., Nguyen, N. T., Nguyen, N. T., Dao, M., and Vu, V. (2020b). Vindr-cxr: An open dataset of chest x-rays with radiologist’s annotations (version 1.0.0).

Pazhitnykh, I. and Petsiuk, V. (2017). Lung segmentation 2d.

Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). ”why should i trust you?”: Explaining the predictions of any classifier. arXiv: 1602.04938.

Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 618–626.

Simonyan, K., Vedaldi, A., and Zisserman, A. (2014). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv: 1312.6034.

Wu, J.-X., Pai, C.-C., Kan, C.-D., Chen, P.-Y., Chen, W.-L., and Lin, C.-H. (2022). Chest x-ray image analysis with combining 2d and 1d convolutional neural network based classifier for rapid cardiomegaly screening. IEEE Access, 10:47824–47836.