Abstract
Resting state functional magnetic resonance images (fMRI) based on BOLD signals are commonly used for classification of patients as having Alzheimer’s disease (AD), mild cognitive impairment (MCI) or being cognitive normal (CN). In this research, we represent Resting-State brain activity in Regions-of-Interest (ROI) by subsets of anatomical region voxels formed by segments of a whole brain bounding box Hilbert curve resulting in an average 5× fewer voxels per ROI than the average number of AAL90 region voxels. We represent each 4D ROI data set with a vector that on average reduces a ROI data set from about 55,000 voxel signal values to 100 to 200 aggregated values in our spatial representation and to 15,000–30,000 in our spatial-temporal representation. We show that a Convolutional Neural Network (CNN) with a model size of about 168 kiB and a Transformer model of only 37 kiB yields classification accuracies of 80–90% for AD, MCI, and CN subject binary classification. Training the CNN and Transformer models on a data set of 551 subjects required 188 and 27 s respectively using Pytorch.1.5.0, Python 3.7.7, and CUDA 10.1 on a system with two 10 cores, 2.8 GHz Intel Xeon E5-2670v2 CPUs and one NVIDIA K40 GPU.
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
References
Ogawa, S., Lee, T.M., Kay, A.R., Tank, D.W.: Brain magnetic resonance imaging with contrast dependent on blood oxygenation. Proc. Natl. Acad. Sci. 87(24), 9868–9872 (1990)
Logothetis, N.K.: The neural basis of the blood–oxygen–level–dependent functional magnetic resonance imaging signal. Philos. Trans. R. Soc. London. Ser. B Biol. Sci. 357(1424), 1003–1037 (2002)
Grabner, G., Janke, A.L., Budge, M.M., Smith, D., Pruessner, J., Collins, D.L.: Symmetric atlasing and model based segmentation: an application to the hippocampus in older adults. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 58–66. Springer, Heidelberg (2006). https://doi.org/10.1007/11866763_8
Tzourio-Mazoyer, N., et al.: Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage 15(1), 273–289 (2002)
Fan, L., et al.: The human brainnetome atlas: a new brain atlas based on connectional architecture. Cereb. Cortex 26(8), 3508–3526 (2016)
Craddock, R.C., James, G.A., Holtzheimer, P.E., III., Hu, X.P., Mayberg, H.S.: A whole brain fMRI atlas generated via spatially constrained spectral clustering. Hum. Brain Mapp. 33(8), 1914–1928 (2012)
Biswal, B., Zerrin Yetkin, F., Haughton, V.M., Hyde, J.S.: Functional connectivity in the motor cortex of resting human brain using echo-planar MRI. Magn. Reson. Med. 34(4), 537–541 (1995)
Beckmann, C.F., DeLuca, M., Devlin, J.T., Smith, S.M.: Investigations into resting-state connectivity using independent component analysis. Philos. Trans. R. Soc. B Biol. Sci. 360(1457), 1001–1013 (2005)
Hilbert, D.: Über die stetige Abbildung einer Linie auf ein Flächenstück. In: Dritter Band: Analysis · Grundlagen der Mathematik · Physik Verschiedenes. Springer, Heidelberg (1935). https://doi.org/10.1007/978-3-662-38452-7_1
Odusami, M., Maskeliūnas, R., Damaševičius, R., Krilavičius, T.: Analysis of features of Alzheimer’s disease: detection of early stage from functional brain changes in magnetic resonance images using a finetuned ResNet18 network. Diagnostics 11(6), 1071 (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/a100/pdf/nvidia-a100-datasheet.pdf
Sarraf, S., DeSouza, D.D., Anderson, J., Tofighi, G.: DeepAD: Alzheimer’s disease classification via deep convolutional neural networks using MRI and fMRI. BioRxiv 70441 (2016)
Kim, J., Calhoun, V.D., Shim, E., Lee, J.H.: Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: evidence from whole-brain resting-state functional connectivity patterns of schizophrenia. Neuroimage 124, 127–146 (2016)
Shi, Y., Zeng, W., Deng, J., Nie, W., Zhang, Y.: The identification of Alzheimer’s disease using functional connectivity between activity voxels in resting-state fMRI data. IEEE J. Transl. Eng. Heal. Med. 8, 1–11 (2020)
Challis, E., Hurley, P., Serra, L., Bozzali, M., Oliver, S., Cercignani, M.: Gaussian process classification of Alzheimer’s disease and mild cognitive impairment from resting-state fMRI. Neuroimage 112, 232–243 (2015)
Chen, G., et al.: Classification of Alzheimer disease, mild cognitive impairment, and normal cognitive status with large-scale network analysis based on resting-state functional MR imaging. Radiology 259(1), 213–221 (2011)
Bi, X.A., Jiang, Q., Sun, Q., Shu, Q., Liu, Y.: Analysis of Alzheimer’s disease based on the random neural network cluster in fMRI. Front. Neuroinform. 12, 60 (2018)
LaMontagne, P.J., et al.: OASIS-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease. MedRxiv (2019)
Studholme, C., Hill, D.L., Hawkes, D.J.: An overlap invariant entropy measure of 3D medical image alignment. Pattern Recognit. 32(1), 71–86 (1999)
Ashburner, J., Friston, K.J.: Unified segmentation. Neuroimage 26(3), 839–851 (2005)
Sakoglu, U., Bhupati, L., Beheshti, N., Tsekos, N., Johnsson, L.: An adaptive space-filling curve trajectory for ordering 3D datasets to 1D: application to brain magnetic resonance imaging data for classification. In: Krzhizhanovskaya, V.V., et al. (eds.) ICCS 2020. LNCS, vol. 12139, pp. 635–646. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-50420-5_48
Benesty, J., Chen, J., Huang, Y., Cohen, I.: Pearson correlation coefficient. In: Noise Reduction in Speech Processing, pp. 1–4. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-00296-0_5
Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. arXiv Prepr. arXiv2101.01169 (2021)
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv Prepr. arXiv2010.11929 (2020)
Vaswani, A., et al.: Attention is all you need (2017)
Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv Prepr. arXiv1611.01144 (2016)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv Prepr. arXiv1412.6980 (2014)
Acknowledgement
We are grateful for the University of Houston support that included resources provided by the UH-HPE Data Science Institute and thank members of the ACRL group for many helpful discussions. Access to the ADNI (funded by NIH Grant U01 AG024904 and DOD award W81XWH-12-2-0012) and OASIS (funded by NIH grants P50 AG00561, P30 NS09857781, P01 AG026276, P01 AG003991, R01 AG043434, UL1 TR000448, R01 EB009352) data is gratefully acknowledged.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Beheshti, N., Johnsson, L. (2022). Classification of 4D fMRI Images Using ML, Focusing on Computational and Memory Utilization Efficiency. In: Xu, X., Li, X., Mahapatra, D., Cheng, L., Petitjean, C., Fu, H. (eds) Resource-Efficient Medical Image Analysis. REMIA 2022. Lecture Notes in Computer Science, vol 13543. Springer, Cham. https://doi.org/10.1007/978-3-031-16876-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-16876-5_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16875-8
Online ISBN: 978-3-031-16876-5
eBook Packages: Computer ScienceComputer Science (R0)
