Abstract
The application of artificial neural networks (ANNs) to functional magnetic resonance imaging (fMRI) data has recently gained renewed attention for signal analysis, modeling the underlying processes, and knowledge extraction. Although adequately trained ANNs characterize by high predictive performance, the intrinsic models tend to be inscrutable due to their complex architectures. Still, explainable artificial intelligence (xAI) looks to find methods that can help to delve into ANNs’ structures and reveal which inputs most contribute to correct predictions and how the networks unroll calculations until the final decision.
Several methods have been proposed to explain the black-box ANNs’ decisions, with layer-wise relevance propagation (LRP) being the current state-of-the-art. This study aims to investigate the consistency between LRP-based and path-weight-based analysis and how the network’s pruning and retraining processes affect each method in the context of fMRI data analysis.
The procedure is tested with fMRI data obtained in a motor paradigm. Both methods were applied to a fully connected ANN, and to pruned and retrained versions. The results show that both methods agree on the most relevant inputs for each stimulus. The pruning process did not lead to major disagreements. Retraining affected both methods similarly, exacerbating the changes initially observed in the pruning process. Notably, the inputs retained for the ultimate ANN are in accordance with the established neuroscientific literature concerning motor action in the brain, validating the procedure and explaining methods. Therefore, both methods can yield valuable insights for understanding the original fMRI data and extracting knowledge.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hanson, S.J., Matsuka, T., Haxby, J.V.: Combinatorial codes in ventral temporal lobe for object recognition: Haxby (2001) revisited: is there a “face” area? Neuroimage 23, 156–166 (2004). https://doi.org/10.1016/j.neuroimage.2004.05.020
Sona, D., Veeramachaneni, S., Olivetti, E., Avesani, P.: Inferring cognition from fMRI brain images. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds.) ICANN 2007. LNCS, vol. 4669, pp. 869–878. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74695-9_89
do Espírito Santo, R., Sato, J.R., Martin, M.G.M.: Discriminating brain activated area and predicting the stimuli performed using artificial neural network. Exacta 5, 311–320 (2007). https://doi.org/10.5585/exacta.v5i2.1180
Santos, J.P., Moutinho, L.: Tackling the cognitive processes that underlie brands’ assessments using artificial neural networks and whole brain fMRI acquisitions. In: 2011 IEEE International Workshop on Pattern Recognition in NeuroImaging (PRNI), Seoul, Republic of Korea, pp. 9–12. IEEE Computer Society (2011)
Hacker, C.D., et al.: Resting state network estimation in individual subjects. Neuroimage 82, 616–633 (2013). https://doi.org/10.1016/j.neuroimage.2013.05.108
Thomas, A.W., Heekeren, H.R., Müller, K.-R., Samek, W.: Analyzing neuroimaging data through recurrent deep learning models. Front. Neurosci. 13 (2019). https://doi.org/10.3389/fnins.2019.01321
Liu, M., Amey, R.C., Backer, R.A., Simon, J.P., Forbes, C.E.: Behavioral studies using larges-scale brain networks – methods and validations. Front. Hum. Neurosci. 16 (2022). https://doi.org/10.3389/fnhum.2022.875201
Haynes, J.-D., Rees, G.: Decoding mental states from brain activity in humans. Nat. Rev. Neurosci. 7, 523–534 (2006). https://doi.org/10.1038/nrn1931
Samek, W., Müller, K.-R.: Towards explainable artificial intelligence. In: Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., Müller, K.-R. (eds.) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNCS (LNAI), vol. 11700, pp. 5–22. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28954-6_1
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018). https://doi.org/10.1109/ACCESS.2018.2870052
Marques dos Santos, J.P., Moutinho, L., Castelo-Branco, M.: ‘Mind reading’: hitting cognition by using ANNs to analyze fMRI data in a paradigm exempted from motor responses. In: International Workshop on Artificial Neural Networks and Intelligent Information Processing (ANNIIP 2014), Vienna, Austria, pp. 45–52. Scitepress (Science and Technology Publications, Lda.) (2014)
de Oña, J., Garrido, C.: Extracting the contribution of independent variables in neural network models: a new approach to handle instability. Neural Comput. Appl. 25, 859–869 (2014). https://doi.org/10.1007/s00521-014-1573-5
Montavon, G., Binder, A., Lapuschkin, S., Samek, W., Müller, K.-R.: Layer-wise relevance propagation: an overview. In: Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., Müller, K.-R. (eds.) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNCS (LNAI), vol. 11700, pp. 193–209. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28954-6_10
Clark, P., Matwin, S.: Using qualitative models to guide inductive learning. In: Utgoff, P. (ed.) Proceedings of the Tenth International Conference on International Conference on Machine Learning, ICML 1993, pp. 49–56. Morgan Kaufmann Publishers Inc., University of Massachusetts, Amherst (1993)
Marques dos Santos, J.D., Marques dos Santos, J.P.: Towards XAI: interpretable shallow neural network used to model HCP’s fMRI motor paradigm data. In: Rojas, I., Valenzuela, O., Rojas, F., Herrera, L.J., Ortuño, F. (eds.) IWBBIO 2022. LNCS, vol. 13347, pp. 260–274. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-07802-6_22
Marques dos Santos, J.D., Marques dos Santos, J.P.: Path weights analyses in a shallow neural network to reach Explainable Artificial Intelligence (XAI) of fMRI data. In: Nicosia, G., et al. (eds.) Machine Learning, Optimization, and Data Science. LNCS, vol. 13811, pp. 417–431. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-25891-6_31
Thomas, A.W., Ré, C., Poldrack, R.A.: Benchmarking explanation methods for mental state decoding with deep learning models. Neuroimage 273, 120109 (2023). https://doi.org/10.1016/j.neuroimage.2023.120109
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, e0130140 (2015). https://doi.org/10.1371/journal.pone.0130140
Sturm, I., Lapuschkin, S., Samek, W., Müller, K.-R.: Interpretable deep neural networks for single-trial EEG classification. J. Neurosci. Methods 274, 141–145 (2016). https://doi.org/10.1016/j.jneumeth.2016.10.008
Penfield, W., Boldrey, E.: Somatic motor and sensory representation in the cerebral cortex of man as studied by electrical stimulation. Brain 60, 389–443 (1937). https://doi.org/10.1093/brain/60.4.389
Buckner, R.L., Krienen, F.M., Castellanos, A., Diaz, J.C., Yeo, B.T.T.: The organization of the human cerebellum estimated by intrinsic functional connectivity. J. Neurophysiol. 106, 2322–2345 (2011). https://doi.org/10.1152/jn.00339.2011
Yeo, B.T.T., et al.: The organization of the human cerebral cortex estimated by intrinsic functional connectivity. J. Neurophysiol. 106, 1125–1165 (2011). https://doi.org/10.1152/jn.00338.2011
Buckner, R.L.: Event-related fMRI and the hemodynamic response. Hum. Brain Mapp. 6, 373–377 (1998). https://doi.org/10.1002/(SICI)1097-0193(1998)6:5/6<373::AID-HBM8>3.0.CO;2-P
Limas, M.C., et al.: AMORE: A MORE flexible neural network package (0.2-15). León (2014)
R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna (2010)
Bondarenko, A., Borisov, A., Alekseeva, L.: Neurons vs weights pruning in artificial neural networks. In: 10th International Scientific and Practical Conference on Environment. Technologies. Resources, vol. 3, pp. 22–28. Rēzekne Academy of Technologies, Rēzekne (2015)
Koenen, N., Baudeu, R.: Innsight: Get the Insights of your Neural Network (0.2.0) (2023)
Acknowledgments
This work was partially financially supported by Base Funding - UIDB/00027/2020 of the Artificial Intelligence and Computer Science Laboratory – LIACC - funded by national funds through the FCT/MCTES (PIDDAC).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Marques dos Santos, J.D., Marques dos Santos, J.P. (2024). Path-Weights and Layer-Wise Relevance Propagation for Explainability of ANNs with fMRI Data. In: Nicosia, G., Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P.M., Umeton, R. (eds) Machine Learning, Optimization, and Data Science. LOD 2023. Lecture Notes in Computer Science, vol 14506. Springer, Cham. https://doi.org/10.1007/978-3-031-53966-4_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-53966-4_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53965-7
Online ISBN: 978-3-031-53966-4
eBook Packages: Computer ScienceComputer Science (R0)