Abstract
Deep learning-based regression and classification models are used in most subareas of neuroimaging because of their accuracy and flexibility. While such models achieve state-of-the-art results in many different applications scenarios, their decision-making process is usually difficult to explain. This black box behaviour is problematic when non-technical users like clinicians and patients need to trust them and make decisions based on their results. In this work, we propose to build self-explainable generative classifiers and regressors using a flexible and efficient normalizing flow framework. We directly exploit the invertibility of those normalizing flows to explain the decision-making process in a highly accessible way via consistent and spatially smooth attribution maps and counterfactual images for alternate prediction results. The evaluation using more than 5000 3D MR images highlights the explainability capabilities of the proposed models and shows that they achieve a similar level of accuracy as standard convolutional neural networks for image-based brain age regression and brain sex classification tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
http://fcon_1000.projects.nitrc.org/indi/retro/dlbs.html.
References
Adeli, E., et al.: Deep learning identifies morphological determinants of sex differences in the pre-adolescent brain. Neuroimage 223, 117293 (2020)
Ardizzone, L., Mackowiak, R., Rother, C., Köthe, U.: Training normalizing flows with the information bottleneck for competitive generative classification. NeurIPS 33 (2020)
Arrieta, A.B., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020)
Cole, J.H., et al.: Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker. Neuroimage 163, 115–124 (2017)
Eitel, F., Ritter, K.: Testing the robustness of attribution methods for convolutional neural networks in MRI-based alzheimer’s disease classification. In: Suzuki, K., et al. (eds.) ML-CDS/IMIMIC -2019. LNCS, vol. 11797, pp. 3–11. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-33850-3_1
Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M., Kagal, L.: Explaining explanations: an overview of interpretability of machine learning. In: 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), pp. 80–89. IEEE (2018)
Goyal, Y., Wu, Z., Ernst, J., Batra, D., Parikh, D., Lee, S.: Counterfactual visual explanations. In: ICML, pp. 2376–2384 (2019)
Graziani, M., Andrearczyk, V., Marchand-Maillet, S., Müller, H.: Concept attribution: explaining CNN decisions to physicians. Comput. Biol. Med. 123, 103865 (2020)
Hedman, A.M., van Haren, N.E., Schnack, H.G., Kahn, R.S., Hulshoff Pol, H.E.: Human brain changes across the life span: a review of 56 longitudinal magnetic resonance imaging studies. Human Brain Mapp. 33(8), 1987–2002 (2012)
Holzinger, A., Biemann, C., Pattichis, C.S., Kell, D.B.: What do we need to build explainable AI systems for the medical domain? (2017) arXiv:1712.09923
Hwang, S.J., Tao, Z., Kim, W.H., Singh, V.: Conditional recurrent flow: conditional generation of longitudinal samples with applications to neuroimaging. In: CVPR, pp. 10692–10701 (2019)
Isensee, F., et al.: Automated brain extraction of multisequence MRI using artificial neural networks. Human Brain Mapp. 40(17), 4952–4964 (2019)
Jeyakumar, J.V., Noor, J., Cheng, Y.H., Garcia, L., Srivastava, M.: How can i explain this to you? an empirical study of deep neural network explanation methods. NeurIPS 33 (2020)
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: ICML, pp. 2668–2677. PMLR (2018)
Kobyzev, I., Prince, S., Brubaker, M.: Normalizing flows: an introduction and review of current methods. IEEE TPAMI, 1–1 (2020)
LaMontagne, P.J., et al.: Oasis-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and alzheimer disease. medRxiv (2019)
Levakov, G., Rosenthal, G., Shelef, I., Raviv, T.R., Avidan, G.: From a deep learning model back to the brain–identifying regional predictors and their relation to aging. Human Brain Mapp. 41(12), 3235–3252 (2020)
Mackowiak, R., Ardizzone, L., Köthe, U., Rother, C.: Generative classifiers as a basis for trustworthy computer vision. arXiv:2007.15036 (2020)
Narayanaswamy, A., et al.: Scientific discovery by generating counterfactuals using image translation. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12261, pp. 273–283. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59710-8_27
Reyes, M., et al.: On the interpretability of artificial intelligence in radiology: challenges and opportunities. Radiol. Artif. Intell. 2(3), e190043 (2020)
Rohlfing, T., Zahr, N.M., Sullivan, E.V., Pfefferbaum, A.: The SRI24 multichannel atlas of normal adult human brain structure. Human Brain Mapp. 31(5), 798–819 (2010)
Samek, W., Montavon, G., Lapuschkin, S., Anders, C.J., Müller, K.R.: Explaining deep neural networks and beyond: a review of methods and applications. Proc. IEEE 109(3), 247–278 (2021)
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: CVPR, pp. 618–626 (2017)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv:1312.6034 (2013)
Singla, S., Pollack, B., Wallace, S., Batmanghelich, K.: Explaining the black-box smoothly-a counterfactual approach. arXiv:2101.04230 (2021)
Sixt, L., Schuessler, M., Weiß, P., Landgraf, T.: Interpretability through invertibility: a deep convolutional network with ideal counterfactuals and isosurfaces (2021). https://openreview.net/forum?id=8YFhXYe1Ps
Smilkov, D., Thorat, N., Kim, B., Viégas, F., Wattenberg, M.: Smoothgrad: removing noise by adding noise. arXiv:1706.03825 (2017)
Völzke, H., et al.: Cohort profile: the study of health in pomerania. Int. J. Epidemiol. 40(2), 294–307 (2011)
Wei, D., Zhuang, K., Chen, Q., Yang, W., Liu, W., Wang, K., Sun, J., Qiu, J.: Structural and functional MRI from a cross-sectional southwest university adult lifespan dataset (sald). BioRxiv, p. 177279 (2017)
Wilms, M., et al.: Bidirectional Modeling and Analysis of Brain Aging with Normalizing Flows. In: Kia, S.M., et al. (eds.) MLCN/RNO-AI -2020. LNCS, vol. 12449, pp. 23–33. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66843-3_3
Zhen, X., Chakraborty, R., Yang, L., Singh, V.: Flow-based generative models for learning manifold to manifold mappings. arXiv:2012.10013 (2020)
Zhou, S.K., et al.: A review of deep learning in medical imaging: image traits, technology trends, case studies with progress highlights, and future promises. arXiv:2008.09104 (2020)
Acknowledgements
This work was supported by a T. Chen Fong postdoctoral fellowship and the River Fund at Calgary Foundation.
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
Wilms, M., Mouches, P., Bannister, J.J., Rajashekar, D., Langner, S., Forkert, N.D. (2021). Towards Self-explainable Classifiers and Regressors in Neuroimaging with Normalizing Flows. In: Abdulkadir, A., et al. Machine Learning in Clinical Neuroimaging. MLCN 2021. Lecture Notes in Computer Science(), vol 13001. Springer, Cham. https://doi.org/10.1007/978-3-030-87586-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-87586-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87585-5
Online ISBN: 978-3-030-87586-2
eBook Packages: Computer ScienceComputer Science (R0)