Abstract
With recent advances in deep learning, neuroimaging studies increasingly rely on convolutional networks (ConvNets) to predict diagnosis based on MR images. To gain a better understanding of how a disease impacts the brain, the studies visualize the salience maps of the ConvNet highlighting voxels within the brain majorly contributing to the prediction. However, these salience maps are generally confounded, i.e., some salient regions are more predictive of confounding variables (such as age) than the diagnosis. To avoid such misinterpretation, we propose in this paper an approach that aims to visualize confounder-free saliency maps that only highlight voxels predictive of the diagnosis. The approach incorporates univariate statistical tests to identify confounding effects within the intermediate features learned by ConvNet. The influence from the subset of confounded features is then removed by a novel partial back-propagation procedure. We use this two-step approach to visualize confounder-free saliency maps extracted from synthetic and two real datasets. These experiments reveal the potential of our visualization in producing unbiased model-interpretation.
Q. Zhao and E. Adeli—Equal contribution.
Source code: github.com/QingyuZhao/Confounder-Aware-CNN-Visualization.git.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Topol, E.J.: High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25(1), 44–56 (2019)
Esmaeilzadeh, S., Belivanis, D.I., Pohl, K.M., Adeli, E.: End-to-end Alzheimer’s disease diagnosis and biomarker identification. In: Shi, Y., Suk, H.-I., Liu, M. (eds.) MLMI 2018. LNCS, vol. 11046, pp. 337–345. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00919-9_39
He, J., Baxter, S.L., Xu, J., Zhou, X., Zhang, K.: The practical implementation of artificial intelligence technologies in medicine. Nat. Med. 25(1), 30–36 (2019)
Pourhoseingholi, M.A., Baghestani, A.R., Vahedi, M.: How to control confounding effects by statistical analysis. Gastroenterol. Hepatol. Bed Bench 5(2), 79–83 (2012)
Simonyan, K., et al.: Deep inside convolutional networks: Visualising image classification models and saliency maps. CoRR abs/1312.6034 (2013)
Dobson, A.J.: An Introduction to Generalized Linear Models. Chapman and Hall, New York (1990)
MacKinnon, D.P.: Introduction to Statistical Mediation Analysis. Erlbaum, New York (2008)
Adeli, E., et al.: Chained regularization for identifying brain patterns specific to HIV infection. Neuroimage 183, 425–437 (2018)
Park, S.H., et al.: Alcohol use effects on adolescent brain development revealed by simultaneously removing confounding factors, identifying morphometric patterns, and classifying individuals. Sci. Rep. 8(1), 1–14 (2018)
Cole, J., et al.: Increased brain-predicted aging in treated HIV disease. Neurology 88(14), 1349–1357 (2017)
Kaye, J.A., et al.: The significance of age-related enlargement of the cerebral ventricles in healthy men and women measured by quantitative computed X-ray tomography. J. Am. Geriatr. Soc. 40(3), 225–31 (1992)
Brown, S., Brumback, T., Tomlinson, K., et al.: The national consortium on alcohol and neurodevelopment in adolescence (NCANDA): a multisite study of adolescent development and substance use. J. Stud. Alcohol Drugs 76(6), 895–908 (2015)
Sowell, E.R., Trauner, D.A., Gamst, A., Jernigan, T.L.: Development of cortical and subcortical brain structures in childhood and adolescence: a structural MRI study. Dev. Med. Child Neurol. 44(1), 4–16 (2002)
Acknowledgements.
This research was supported in part by NIH grants AA017347, AA005965, AA010723, AA021697, AA013521, AA026762 and MH113406.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, Q., Adeli, E., Pfefferbaum, A., Sullivan, E.V., Pohl, K.M. (2019). Confounder-Aware Visualization of ConvNets. In: Suk, HI., Liu, M., Yan, P., Lian, C. (eds) Machine Learning in Medical Imaging. MLMI 2019. Lecture Notes in Computer Science(), vol 11861. Springer, Cham. https://doi.org/10.1007/978-3-030-32692-0_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-32692-0_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32691-3
Online ISBN: 978-3-030-32692-0
eBook Packages: Computer ScienceComputer Science (R0)