Abstract
Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically rely on saliency maps to quantify the voxel-wise or feature-level importance for classification through partial derivatives. Despite providing some level of localization, these maps are not human-understandable from the neuroscience perspective as they often do not inform the specific type of morphological changes linked to the brain disorder. Inspired by the image-to-image translation scheme, we propose to train simulator networks to inject (or remove) patterns of the disease into a given MRI based on a warping operation, such that the classifier increases (or decreases) its confidence in labeling the simulated MRI as diseased. To increase the robustness of training, we propose to couple the two simulators into a unified model based on conditional convolution. We applied our approach to interpreting classifiers trained on a synthetic dataset and two neuroimaging datasets to visualize the effect of Alzheimer’s disease and alcohol dependence. Compared to the saliency maps generated by baseline approaches, our simulations and visualizations based on the Jacobian determinants of the warping field reveal meaningful and understandable patterns related to the diseases.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Source code can be found at https://github.com/ZucksLiu/DeepInterpret.
References
Zhu, G., Jiang, B., Tong, L., Xie, Y., Zaharchuk, G., Wintermark, M.: Applications of deep learning to neuro-imaging techniques. Front. Neurol. 10, 1–13 (2019)
Lee, G., Nho, K., Kang, B., Sohn, K.A., Kim, D.: Predicting Alzheimer’s disease progression using multi-modal deep learning approach. Sci. Rep. 9, 1–12 (2019)
Willemink, M., et al.: Preparing medical imaging data for machine learning. Radiology 295, 4–15 (2020)
Brammer, M.: The role of neuroimaging in diagnosis and personalized medicine-current position and likely future directions. Dialogues Clin. Neurosci. 11, 389–96 (2009)
Ouyang, J., et al.: Longitudinal pooling & consistency regularization to model disease progression from MRIs. IEEE J. Biomed. Health Inform. (2020, in press)
Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806 (2014)
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 ICCV, pp. 618–626 (2017)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Ghorbani, A., Wexler, J., Zou, J.Y., Kim, B.: Towards automatic concept-based explanations. In: NeurIPS, vol. 32 (2019)
Kaji, S., Kida, S.: Overview of image-to-image translation by use of deep neural networks: denoising, super-resolution, modality conversion, and reconstruction in medical imaging. Radiol. Phys. Technol. 12, 235–248 (2019). https://doi.org/10.1007/s12194-019-00520-y
Qin, C., Shi, B., Liao, R., Mansi, T., Rueckert, D., Kamen, A.: Unsupervised deformable registration for multi-modal images via disentangled representations. In: Chung, A.C.S., Gee, J.C., Yushkevich, P.A., Bao, S. (eds.) IPMI 2019. LNCS, vol. 11492, pp. 249–261. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20351-1_19
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV, pp. 2242–2251 (2017)
Yang, B., Bender, G., Le, Q.V., Ngiam, J.: CondConv: conditionally parameterized convolutions for efficient inference. In: Advances in Neural Information Processing Systems, pp. 1307–1318 (2019)
Balakrishnan, G., Zhao, A., Sabuncu, M., Guttag, J., Dalca, A.: VoxelMorph: a learning framework for deformable medical image registration. IEEE Trans. Med. Imaging 38, 1788–1800 (2019)
Pini, L., et al.: Brain atrophy in Alzheimer’s disease and aging. Ageing Res. Rev. 30, 25–48 (2016)
Sullivan, E., et al.: The role of aging, drug dependence, and hepatitis C comorbidity in alcoholism cortical compromise. JAMA Psychiatry 75, 474–483 (2018)
Moorman, D.: The role of the orbitofrontal cortex in alcohol use, abuse, and dependence. Prog. Neuro-Psychopharmacol. Biol. Psychiatry 87, 85–107 (2018)
Acknowledgements
This work was supported by NIH Grants MH113406, AA005965, AA010723, and AA017347, and by Stanford HAI AWS Cloud Credit.
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
Liu, Z., Adeli, E., Pohl, K.M., Zhao, Q. (2021). Going Beyond Saliency Maps: Training Deep Models to Interpret Deep Models. In: Feragen, A., Sommer, S., Schnabel, J., Nielsen, M. (eds) Information Processing in Medical Imaging. IPMI 2021. Lecture Notes in Computer Science(), vol 12729. Springer, Cham. https://doi.org/10.1007/978-3-030-78191-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-78191-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78190-3
Online ISBN: 978-3-030-78191-0
eBook Packages: Computer ScienceComputer Science (R0)