Abstract
Neurodegenerative parkinsonism can be assessed by dopamine transporter single photon emission computed tomography (DaT-SPECT). Although generating images is time consuming, these images can show interobserver variability and they have been visually interpreted by nuclear medicine physicians to date. Accordingly, this study aims to provide an automatic and robust method based on diffusion Maps and machine learning classifiers to classify the SPECT images into two types, namely Normal and Abnormal DaT-SPECT image groups. In comparison with deep learning methods, our contribution is to propose an explainable diagnosis process with high prediction accuracy. In the proposed method, the 3D images of N patients are mapped to an \(N \times N\) pairwise distance matrix and are visualized in diffusion Maps coordinates. The images of the training set are embedded into a low-dimensional space by using diffusion maps. Moreover, we use Nystr\(\ddot{o}\)m’s out-of-sample extension, which embeds new sample points as the testing set in the reduced space. Testing samples in the embedded space are then classified into two types through the ensemble classifier with Linear Discriminant Analysis (LDA) and voting procedure through twenty-five-fold cross-validation results. The feasibility of the method is demonstrated via Parkinsonism Progression Markers Initiative (PPMI) dataset of 1097 subjects and a clinical cohort from Kaohsiung Chang Gung Memorial Hospital (KCGMH-TW) of 630 patients. We compare performances using diffusion maps with those of three alternative manifold methods for dimension reduction, namely Locally Linear Embedding (LLE), Isomorphic Mapping Algorithm (Isomap), and Kernel Principal Component Analysis (Kernel PCA). We also compare results using 2D and 3D CNN methods. The diffusion maps method has an average accuracy of 98% for the PPMI and 90% for the KCGMH-TW dataset with twenty-five fold cross-validation results. It outperforms the other three methods concerning the overall accuracy and the robustness in the training and testing samples.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kalia, L.V., Lang, A.E.: Parkinson’s disease. The Lancet 9996, 896–912, Elsevier Ltd, 386 (2015). https://doi.org/10.1016/S0140-6736(14)61393--3
Keener, A.M., Bordelon, Y.M.: Parkinsonism. Semin Neurol. 36(4), 330–334 (2016). https://doi.org/10.1055/s-0036-1585097
Hayes, M.T.: Parkinson’s disease and parkinsonism. Am J.. Med. 132(7), 802–807 (2019). https://doi.org/10.1016/j.amjmed.2019.03.001
Kung, H.F., Kung, M.P., Wey, S.P., Lin, K.J., Yen, T.C.: Clinical acceptance of a molecular imaging agent: a long march with [99mTc]TRODAT. Nuclear Med. Biol. 34(7), 787–789 (2007) 132(7), 802–807 (2019). https://doi.org/10.1016/j.nucmedbio.2007.03.010
Prashanth, R., Dutta Roy, S., Mandal, P.K., Ghosh, S.: High-accuracy classification of parkinson’s disease through shape analysis and surface fitting in \(^{123}\)I-Ioflupane SPECT imaging. IEEE J. Biomed. Health Inf. 21, 794–802 (2016) 132(7), 802–807 (2019). https://doi.org/10.1109/jbhi.2016.2547901
Faaeq, A., Guruler, H., Peker, M.: Image classification using manifold learning based non-linear dimensionality reduction. In: 26th IEEE Signal Processing and Communications Applications Conference, pp. 1–4 (2018). 132(7), 802–807 (2019). https://doi.org/10.1109/SIU.2018.8404441
Coifman, R.R., Lafon, S., Lee, A.B., Maggioni, M., Warner, F., Zucker, S.: Geometric diffusions as a tool for harmonic analysis and structure definition of data: diffusion maps. Proc. Natl. Acad. Sci. 102(21), 7426–7431 (2005). https://doi.org/10.1073/pnas.0500334102
Cummings, J.L., HencNormalliffe, C., Schaier, S., Simuni, T., Waxman, A., Kemp, P.: The role of dopaminergic imaging in patients with symptoms of dopaminergic system neurodegeneration. Brain 134(11), 3146–66 (2011) https://doi.org/10.1093/brain/awr177
Faro, A., Giordano, D., Spampinato, C., Ullo, S., Di Stefano, A.: Basal ganglia activity measurement by automatic 3-D striatum segmentation in SPECT images. IEEE Trans. Instrumentation Measur. 60(10), 3269–3280 (2011). https://doi.org/10.1109/TIM.2011.2159315
Quan, J., Xu, L., Xu, R., Tong, T., Su, J.: DaTscan SPECT image classification for Parkinson’s disease. arXiv. 1–9 (2019) https://doi.org/arXiv:1909.04142v1
Djang, D,S.W. et al.: SNM practice guideline for dopamine transporter imaging with \(^{123}\)I-ioflupane SPECT 1.0. J. Nuclear Med. 53, 154–163 (2012) https://doi.org/10.2967/jnumed.111.100784
ScNormallar, A., Rokach, L., Amit, A.: Diffusion ensemble classifiers. In: IJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence, pp. 443–450 (2012). https://doi.org/10.5220/0004102804430450
De La Porte, J., Herbst, B.M., Hereman, W., Van Der Walt, S.J.: An introduction to diffusion maps. In: The 19th Symposium of the Pattern Recognition Association of South Africa (2008)
Bengio, Y., et al.: Out-of-sample extensions for LLE, Isomap, MDS, eigenmaps, and spectral clustering. In: Advances in Neural Information Processing Systems
Prashanth, R., Dutta Roy, S., Mandal, P.K., Ghosh, S.: Automatic classification and prediction models for early Parkinson’s disease diagnosis from SPECT imaging. Expert Syst. Appl. 41, 3333–3342 (2014). https://doi.org/10.1016/j.eswa.2013.11.031
Raeper, R., Lisowska, A., Rekik, I.: Joint correlational and discriminative ensemble classifier learning for dementia stratification using shallow brain multiplexes. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 599–607. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_68
Krizhevsky.: Imagenet classification with deep convolutional neural networks, Alex and Sutskever, Ilya and Hinton, Geoffrey E. Neural Inf. Process. Syst. 25 (2012). https://doi.org/10.1145/3065386
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR, pp. 1–14 (2015). https://arxiv.org/abs/1409.1556
Esmaeilzadeh, S., Yang, Y., Adeli, E.: End-to-end parkinson disease diagnosis using brain MR-images by 3D-CNN, Arxiv (2018). https://arxiv.org/abs/1806.05233
Kim, D.H., Wit, H., Thurston, M.: Artificial intelligence in the diagnosis of Parkinson’s disease from ioflupane-123 single-photon emission computed tomography dopamine transporter scans using transfer learning. Nucl. Med. Commun. 39(10), 887–893 (2018). https://doi.org/10.1097/MNM.0000000000000890
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
Ding, JE., Chu, CH., Huang, MN.L., Hsu, CC. (2021). Dopamine Transporter SPECT Image Classification for Neurodegenerative Parkinsonism via Diffusion Maps and Machine Learning Classifiers. In: Papież, B.W., Yaqub, M., Jiao, J., Namburete, A.I.L., Noble, J.A. (eds) Medical Image Understanding and Analysis. MIUA 2021. Lecture Notes in Computer Science(), vol 12722. Springer, Cham. https://doi.org/10.1007/978-3-030-80432-9_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-80432-9_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80431-2
Online ISBN: 978-3-030-80432-9
eBook Packages: Computer ScienceComputer Science (R0)