Abstract
Decoding and encoding models are popular multivariate approaches used to study representations in functional neuroimaging data. Encoding approaches seek to predict brain activation patterns using aspects of the stimuli as features. Decoding models, in contrast, utilize measured brain responses as features to make predictions about experimental manipulations or behavior. Both approaches have typically included linear classification components. Ideally, decoding and encoding models could be used for the dual purpose of prediction and neuroscientific knowledge gain. However, even within a linear framework, interpretation can be difficult. Encoding models suffer from feature fallacy; multiple combinations of features derived from a stimulus may describe measured brain responses equally well. Interpreting linear decoding models also requires great care, particularly when informative predictor variables (e.g., fMRI voxels) are present in great quantity (redundant) and correlated with noise measurements. In certain cases, noise channels may be assigned a stronger weight than channels that contain relevant information. Although corrections for this problem exist, there are certain noise sources - common to functional neuroimaging recordings - that may complicate corrective approaches, even after regularization is applied. Here, we review potential pitfalls for making inferences based on encoding and decoding hypothesis testing, and suggest a form of feature fallacy also extends to the decoding framework.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alpaydin, E.: Introduction to Machine Learning, 3rd edn. MIT Press, Cambridge (2014)
Anderson, A., Han, D., Douglas, P.K., Bramen, J., Cohen, M.S.: Real-time functional MRI classification of brain states using Markov-SVM hybrid models: peering inside the rt-fMRI black box. In: Langs, G., Rish, I., Grosse-Wentrup, M., Murphy, B. (eds.) MLINI 2011. LNCS (LNAI), vol. 7263, pp. 242–255. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-34713-9_31
Blankertz, B., Lemm, S., Treder, M., Haufe, S., Müller, K.R.: Single-trial analysis and classification of ERP components – a tutorial. NeuroImage 56, 814–825 (2011)
Bruce, D.: Fifty years since lashley’s in search of the Engram: refutations and conjectures. J. Hist. Neurosci. 10, 308–318 (2001)
Chu, C., Hsu, A.L., Chou, K.H., Bandettini, P., Lin, C.: Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images. NeuroImage 60, 59–70 (2012)
Colby, J.B., Rudie, J.D., Brown, J.A., Douglas, P.K., Cohen, M.S., Shehzad, Z.: Insights into multimodal imaging classification of ADHD. Front. Syst. Neurosci. 6, 59 (2012)
Cox, D.D., Savoy, R.L.: Functional magnetic resonance imaging (fMRI) ‘brain reading’: detecting and a classifying distributed patterns of fMRI activity in human visual cortex. NeuroImage 19, 261–270 (2003)
Cukur, T., Huth, A.G., Nishimoto, S., Gallant, J.L.: Functional subdomains within human FFA. J. Neurosci. 33, 16748–16766 (2013)
De Angelis, V., De Martino, F., Moerel, M., Santoro, R., Hausfeld, L., Formisano, E.: Cortical processing of pitch: model-based encoding and decoding of auditory fMRI responses to real-life sounds. NeuroImage 180, 291–300 (2018)
DiCarlo, J.J., Zoccolan, D., Rust, N.C.: How does the brain solve visual object recognition? Neuron 73, 415–434 (2012)
Diedrichsen, J., Kriegeskorte, N.: Representational models: a common framework for understanding encoding, pattern-component, and representational-similarity analysis. bioRxiv 071472 (2016)
Diedrichsen, J., Wiestler, T., Krakauer, J.W.: Two distinct ipsilateral cortical representations for individuated finger movements. Cereb. Cortex 23, 1362–1377 (2013)
Douglas, P.K., Anderson, A.: Interpreting fMRI decoding weights: additional considerations. In: NIPS, Interpretable Machine Learning Workshop (2017)
Douglas, P.K., Harris, S., Cohen, M.S.: Naive Bayes classification of belief and disbelief using event related functional neuroimaging data. In: Human Brain Mapping Conference Poster (2009)
Douglas, P.K., Harris, S., Yuille, A., Cohen, M.S.: Performance comparison of machine learning algorithms and number of independent components used in fMRI decoding of belief vs. disbelief. NeuroImage 56, 544–553 (2011)
Douglas, P.K., et al.: Single trial decoding of belief decision making from EEG and fMRI data using independent components features. Front. Hum. Neurosci. 7, 392 (2013)
Friston, K.J.: Modalities, modes, and models in functional neuroimaging. Science 326, 399–403 (2009)
Gazzaniga, M.S.: Regional differences in cortical organization. Science 289, 1887–1888 (2000)
Gotsopoulos, A., et al.: Reproducibility of importance extraction methods in neural network based fMRI classification. NeuroImage 181, 44–54 (2018)
Gross, C.G.: Genealogy of the “grandmother cell”. Neurosci. 8, 512–518 (2002)
Güçü, U., van Gerven, M.A.J.: Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream. J. Neurosci. 35, 10005–10014 (2015)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Hampton, A.N., O’Doherty, J.P.: Decoding the neural substrates of reward-related decision making with functional MRI. Proc. Natl. Acad. Sci. 104, 1377–1382 (2007)
Handwerker, D.A., Ollinger, J.M., D’Esposito, M.: Variation of BOLD hemodynamic responses across subjects and brain regions and their effects on statistical analyses. NeuroImage 21, 1639–1651 (2004)
Haufe, S., et al.: On the interpretation of weight vectors of linear models in multivariate neuroimaging. NeuroImage 87, 96–110 (2014)
Haxby, J.V.: Distributed and overlapping representations of faces and objects in ventral temporal cortex. Science 293, 2425–2430 (2001)
Haynes, J.D.: A primer on pattern-based approaches to fMRI: principles, pitfalls, and perspectives. Neuron 87, 257–270 (2015)
Haynes, J.D., Rees, G.: Predicting the stream of consciousness from activity in human visual cortex. Curr. Biol 15, 1301–1307 (2005)
Haynes, J.D., Rees, G.: Decoding mental states from brain activity in humans. Nat. Rev. Neurosci. 7, 523–534 (2006)
Hodgkin, A.L., Huxley, A.F.: A quantitative description of membrane current and its application to conduction and excitation in nerve. J. Physiol. 117, 500–544 (1952)
Hong, H., Yamins, D.L.K., Majaj, N.J., DiCarlo, J.J.: Explicit information for category-orthogonal object properties increases along the ventral stream. Nat. Neurosci. 19, 613–622 (2016)
Huth, A.G., de Heer, W.A., Griffiths, T.L., Theunissen, F.E., Gallant, J.L.: Natural speech reveals the semantic maps that tile human cerebral cortex. Nature 532, 453–458 (2016)
Kamitani, Y., Tong, F.: Decoding the visual and subjective contents of the human brain. Nat. Neurosci. 8, 679–685 (2005)
Kanwisher, N., Yovel, G.: The fusiform face area: a cortical region specialized for the perception of faces. Philos. Trans. Roy. Soc. B: Biol. Sci. 361, 2109–2128 (2006)
Kay, K.N., Naselaris, T., Prenger, R.J., Gallant, J.L.: Identifying natural images from human brain activity. Nature 452, 352–355 (2008)
Kerr, W.T., Douglas, P.K., Anderson, A., Cohen, M.S.: The utility of data-driven feature selection: Re: Chu et al. 2012. NeuroImage 84, 1107–1110 (2014)
Khaligh-Razavi, S.M., Kriegeskorte, N.: Deep supervised, but not unsupervised, models may explain IT cortical representation. PLOS Comput. Biol. 10(11), e1003915 (2014)
Khaligh-Razavi, S., Kriegeskorte, N.: Object-vision models that better explain IT also categorize better, but all models fail at both. Cosyne Abstracts (2013)
Koopmans, P.J., Barth, M., Orzada, S., Norris, D.G.: Multi-echo fMRI of the cortical laminae in humans at 7T. NeuroImage 56, 1276–1285 (2011)
Kriegeskorte, N.: Deep neural networks: a new framework for modeling biological vision and brain information processing. Ann. Rev. Vis. Sci. 1, 417–446 (2015)
Kriegeskorte, N.: Pattern-information analysis: from stimulus decoding to computational-model testing. NeuroImage 56, 411–421 (2011)
Kriegeskorte, N., Douglas, P.K.: Cognitive computational neuroscience. Nat. Neurosci. 21, 1148–1160 (2018)
Kriegeskorte, N., Douglas, P.K.: Interpreting encoding and decoding models. arXiv:1812.00278 (2018)
Lee, A.T., Glover, G.H., Meyer, C.H.: Discrimination of large venous vessels in time-course spiral blood-oxygen-level-dependent magnetic-resonance functional neuroimaging. Magn. Reson. Med. 33, 745–754 (1995)
Lemm, S., Blankertz, B., Dickhaus, T., Müller, K.R.: Introduction to machine learning for brain imaging. NeuroImage 56, 387–399 (2011)
Logothetis, N.K., Pauls, J., Augath, M., Trinath, T., Oeltermann, A.: Neurophysiological investigation of the basis of the fMRI signal. Nature 412, 150–157 (2001)
Meshkat, N., Kuo, C.E., DiStefano, J.: On finding and using identifiable parameter combinations in nonlinear dynamic systems biology models and COMBOS: a novel web implementation. PLoS One 9, e110261 (2014)
Mikl, M., et al.: Effects of spatial smoothing on fMRI group inferences. Magn. Reson. Imaging 26, 490–503 (2008)
Naselaris, T., Kay, K.N.: Resolving ambiguities of MVPA using explicit models of representation. Trends Cogn. Sci. 19, 551–554 (2015)
Naselaris, T., Kay, K.N., Nishimoto, S., Gallant, J.L.: Encoding and decoding in fMRI. NeuroImage 56, 400–410 (2011)
Naselaris, T., Prenger, R.J., Kay, K.N., Oliver, M., Gallant, J.L.: Bayesian reconstruction of natural images from human brain activity. Neuron 63, 902–915 (2009)
Norman, K.A., Polyn, S.M., Detre, G.J., Haxby, J.V.: Beyond mind-reading: multi-voxel pattern analysis of fMRI data. Trends Cogn. Sci. (Regul. Ed.) 10, 424–430 (2006)
de Beeck, H.P.O.: Against hyperacuity in brain reading: spatial smoothing does not hurt multivariate fMRI analyses? NeuroImage 49, 1943–1948 (2010)
Poldrack, R.A.: Can cognitive processes be inferred from neuroimaging data? Trends Cogn. Sci. (Regul. Ed.) 10, 59–63 (2006)
Pouget, A., Dayan, P., Zemel, R.: Information processing with population codes. Nat. Rev. Neurosci. 1, 125–132 (2000)
Power, J.D., Mitra, A., Laumann, T.O., Snyder, A.Z., Schlaggar, B.L., Petersen, S.E.: Methods to detect, characterize, and remove motion artifact in resting state fMRI. NeuroImage 84, 320–341 (2014)
Quiroga, R.Q., Reddy, L., Kreiman, G., Koch, C., Fried, I.: Invariant visual representation by single neurons in the human brain. Nature 435, 1102–1107 (2005)
Selemon, L., Goldman-Rakic, P.: Common cortical and subcortical targets of the dorsolateral prefrontal and posterior parietal cortices in the rhesus monkey: evidence for a distributed neural network subserving spatially guided behavior. J. Neurosci. 8, 4049–4068 (1988)
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)
Thomas, A.W., Heekeren, H.R., Müller, K.R., Samek, W.: Analyzing neuroimaging data through recurrent deep learning models. arXiv:1810.09945 (2018)
Tomsett, R., et al.: Why the failure? How adversarial examples can provide insights for interpretable machine learning. In: 21st International Conference on Information Fusion (2018)
VanRullen, R., Reddy, L.: Reconstructing faces from fMRI patterns using deep generative neural networks. arXiv:1810.03856 (2018)
Varoquaux, G., Raamana, P.R., Engemann, D.A., Hoyos-Idrobo, A., Schwartz, Y., Thirion, B.: Assessing and tuning brain decoders: cross-validation, caveats, and guidelines. NeuroImage 145, 166–179 (2017)
Worsley, K.J., Marrett, S., Neelin, P., Vandal, A.C., Friston, K.J., Evans, A.C.: A unified statistical approach for determining significant signals in images of cerebral activation. Hum. Brain Mapp. 4, 58–73 (1996)
Wu, G.R., Liao, W., Stramaglia, S., Ding, J.R., Chen, H., Marinazzo, D.: A blind deconvolution approach to recover effective connectivity brain networks from resting state fMRI data. Med. Image Anal. 17, 365–374 (2013)
Xie, J., Douglas, P.K., Wu, Y., Anderson, A.: Decoding the Encoding of functional brain networks: an fMRI classification comparison of non-negative matrix factorization (NMF), independent component analysis (ICA), and sparse coding algorithms. Int. J. Imaging Syst. Technol. 21, 223–231 (2016)
Zhao, S., et al.: Automatic recognition of fMRI-derived functional networks using 3D convolutional neural networks. IEEE Trans. Biomed. Eng. 65(9), 1975–1984 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Douglas, P.K., Anderson, A. (2019). Feature Fallacy: Complications with Interpreting Linear Decoding Weights in fMRI. In: Samek, W., Montavon, G., Vedaldi, A., Hansen, L., Müller, KR. (eds) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. Lecture Notes in Computer Science(), vol 11700. Springer, Cham. https://doi.org/10.1007/978-3-030-28954-6_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-28954-6_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-28953-9
Online ISBN: 978-3-030-28954-6
eBook Packages: Computer ScienceComputer Science (R0)