Abstract
Neural networks have demonstrated remarkable performance in classification and regression tasks on chest X-rays. In order to establish trust in the clinical routine, the networks’ prediction mechanism needs to be interpretable. One principal approach to interpretation is feature attribution. Feature attribution methods identify the importance of input features for the output prediction. Building on Information Bottleneck Attribution (IBA) method, for each prediction we identify the chest X-ray regions that have high mutual information with the network’s output. Original IBA identifies input regions that have sufficient predictive information. We propose Inverse IBA to identify all informative regions. Thus all predictive cues for pathologies are highlighted on the X-rays, a desirable property for chest X-ray diagnosis. Moreover, we propose Regression IBA for explaining regression models. Using Regression IBA we observe that a model trained on cumulative severity score labels implicitly learns the severity of different X-ray regions. Finally, we propose Multi-layer IBA to generate higher resolution and more detailed attribution/saliency maps. We evaluate our methods using both human-centric (ground-truth-based) interpretability metrics, and human-agnostic feature importance metrics on NIH Chest X-ray8 and BrixIA datasets. The code (https://github.com/CAMP-eXplain-AI/CheXplain-IBA) is publicly available.
A. Khakzar and Y. Zhang—Shared first authorship.
S. T. Kim and N. Navab—Shared senior authorship.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. arXiv preprint arXiv:1810.03292 (2018)
Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. arXiv preprint arXiv:1612.00410 (2016)
Ancona, M., Ceolini, E., Öztireli, C., Gross, M.: Towards better understanding of gradient-based attribution methods for deep neural networks. arXiv preprint arXiv:1711.06104 (2017)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS One 10(7), e0130140 (2015)
Hooker, S., Erhan, D., Kindermans, P.J., Kim, B.: A benchmark for interpretability methods in deep neural networks. In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019). https://proceedings.neurips.cc/paper/2019/file/fe4b8556000d0f0cae99daa5c5c5a410-Paper.pdf
Irvin, J., et al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol, 33, pp. 590–597 (2019)
Johnson, A.E., et al.: MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)
Karim, M., Döhmen, T., Rebholz-Schuhmann, D., Decker, S., Cochez, M., Beyan, O., et al.: DeepCOVIDExplainer: explainable covid-19 predictions based on chest x-ray images. arXiv preprint arXiv:2004.04582 (2020)
Khakzar, A., Albarqouni, S., Navab, N.: Learning interpretable features via adversarially robust optimization. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 793–800. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_88
Khakzar, A., Baselizadeh, S., Khanduja, S., Kim, S.T., Navab, N.: Explaining neural networks via perturbing important learned features. arXiv preprint arXiv:1911.11081 (2019)
Khakzar, A., Baselizadeh, S., Khanduja, S., Rupprecht, C., Kim, S.T., Navab, N.: Neural response interpretation through the lens of critical pathways. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021)
Khakzar, A., Baselizadeh, S., Navab, N.: Rethinking positive aggregation and propagation of gradients in gradient-based saliency methods. arXiv preprint arXiv:2012.00362 (2020)
Li, Z., et al.: Thoracic disease identification and localization with limited supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8290–8299 (2018)
Montavon, G., Lapuschkin, S., Binder, A., Samek, W., Müller, K.R.: Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recogn. 65, 211–222 (2017)
Nie, W., Zhang, Y., Patel, A.: A theoretical explanation for perplexing behaviors of backpropagation-based visualizations. In: International Conference on Machine Learning, pp. 3809–3818. PMLR (2018)
Oh, Y., Park, S., Ye, J.C.: Deep learning COVID-19 features on CXR using limited training data sets. IEEE Trans. Med. Imaging 39(8), 2688–2700 (2020)
Petsiuk, V., Das, A., Saenko, K.: Rise: Randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421 (2018)
Punn, N.S., Agarwal, S.: Automated diagnosis of COVID-19 with limited posteroanterior chest X-ray images using fine-tuned deep neural networks. Appl. Intell. 51(5), 2689–2702 (2020). https://doi.org/10.1007/s10489-020-01900-3
Rajpurkar, P., et al.: CheXNet: radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225 (2017)
Samek, W., Binder, A., Montavon, G., Lapuschkin, S., Müller, K.R.: Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Netw. Learn. Syst. 28(11), 2660–2673 (2016)
Schulz, K., Sixt, L., Tombari, F., Landgraf, T.: Restricting the flow: information bottlenecks for attribution. arXiv preprint arXiv:2001.00396 (2020)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Signoroni, A., et al.: End-to-end learning for semiquantitative rating of COVID-19 severity on chest X-rays. arXiv preprint arXiv:2006.04603 (2020)
Signoroni, A., et al.: BS-Net: learning COVID-19 pneumonia severity on a large chest X-ray dataset. Med. Image Anal. 71, 102046 (2021)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Singh, R.K., Pandey, R., Babu, R.N.: COVIDScreen: explainable deep learning framework for differential diagnosis of COVID-19 using chest X-rays. Neural Comput. Appl. 33(14), 8871–8892 (2021). https://doi.org/10.1007/s00521-020-05636-6
Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806 (2014)
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319–3328. PMLR (2017)
Taghanaki, S.A., et al.: InfoMask: masked variational latent representation to localize chest disease. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 739–747. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_82
Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097–2106 (2017)
Zhang, J., Bargal, S.A., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. Int. J. Comput. Vis. 126(10), 1084–1102 (2018). https://doi.org/10.1007/s11263-017-1059-x
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Acknowledgement
This work was partially funded by the Munich Center for Machine Learning (MCML) and the Bavarian Research Foundation grant AZ-1429-20C. The computational resources for the study are provided by the Amazon Web Services Diagnostic Development Initiative. S.T. Kim is supported by the Korean MSIT, under the National Program for Excellence in SW (2017-0-00093), supervised by the IITP.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Khakzar, A. et al. (2021). Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12903. Springer, Cham. https://doi.org/10.1007/978-3-030-87199-4_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-87199-4_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87198-7
Online ISBN: 978-3-030-87199-4
eBook Packages: Computer ScienceComputer Science (R0)