Top

EJNMMI Research

Published in:

Open Access 01-12-2018 | Original research

Glucose metabolic brain patterns to discriminate amyotrophic lateral sclerosis from Parkinson plus syndromes

Authors: Martijn Devrome, Donatienne Van Weehaeghe, Joke De Vocht, Philip Van Damme, Koen Van Laere, Michel Koole

Published in: EJNMMI Research | Issue 1/2018

Abstract

Background

¹⁸F-FDG brain PET measures metabolic changes in neurodegenerative disorders and may discriminate between different diseases even at an early stage. The objective of this study was to classify patients with amyotrophic lateral sclerosis (ALS) and Parkinson plus syndromes (PP). To this end, different approaches were evaluated using generalized linear models and corresponding glucose metabolic brain patterns. Besides direct classification, healthy controls were also included to generate disease-specific metabolic brain patterns and to perform a classification using disease expression scores.

Methods

ALS patients (n = 70) and PP patients (n = 33: 20 PSP, 3 CBD, and 10 MSA) were available from an existing database of patients with neuromuscular and movement disorders while age-matched healthy controls (n = 29) were selected from a prospective study. To generate both disease-discriminative (direct classification) and disease-specific (classification versus controls) metabolic brain patterns, data were spatially normalized and a principal component analysis (PCA) was performed prior to classification using either logistic regression (PCA-LR) or a support vector machine (PCA-SVM). Furthermore, a direct SVM approach was considered. To compare the three different approaches, Pearson correlations (r) between pattern expression scores and metabolic brain patterns were evaluated, while pairs of ALS- and PP-specific pattern expression scores were compared using the RV coefficient.

Results

Classification between ALS and PP resulted in a sensitivity and specificity ≥ 0.82 for both direct classification and classification according to disease-specific pattern expression scores. PCA-LR, PCA-SVM, and SVM generated very similar metabolic brain patterns with voxelwise correlations ≥ 0.66, while all patterns allowed straightforward identification of ALS- and PP-specific brain regions of hyper- and hypometabolism. Moreover, pattern expression scores were highly correlated among different classifiers with a mean r of 0.94 while a RV coefficient ≥ 0.91 was found between pairs of ALS- and PP-specific pattern expression scores.

Conclusion

We demonstrated that a classification between ALS and PP using expression scores of an ALS and PP metabolic brain pattern leads to a similar and high prediction accuracy as direct classification between ALS and PP. Classification performance and disease-specific metabolic patterns, which could support visual reading and improve insight in brain pathology, were very related for different classifiers.

Marcus C, Mena E, Subramaniam RM. Brain PET in the diagnosis of Alzheimer's disease. Clin Nucl Med. 2014;39(10):e413–22; quiz e23–6. https://doi.org/10.1097/RLU.0000000000000547.CrossRefPubMedPubMedCentral

Silverman DH. Brain 18F-FDG PET in the diagnosis of neurodegenerative dementias: comparison with perfusion SPECT and with clinical evaluations lacking nuclear imaging. J Nucl Med. 2004;45(4):594–607.PubMed

Moeller JR, Strother SC, Sidtis JJ, Rottenberg DA. Scaled subprofile model: a statistical approach to the analysis of functional patterns in positron emission tomographic data. J Cereb Blood Flow Metab. 1987;7(5):649–58. https://doi.org/10.1038/jcbfm.1987.118.CrossRefPubMed

Scarmeas N, Habeck C, Anderson KE, Hilton J, Devanand DP, Pelton GH, et al. Altered PET functional brain responses in cognitively intact elderly persons at risk for Alzheimer disease (carriers of the epsilon4 allele). Am J Geriatr Psychiatry. 2004;12(6):596–605. https://doi.org/10.1176/appi.ajgp.12.6.596.CrossRefPubMedPubMedCentral

Feigin A, Leenders KL, Moeller JR, Missimer J, Kuenig G, Spetsieris P, et al. Metabolic network abnormalities in early Huntington's disease: an [(18)F]FDG PET study. J Nucl Med. 2001;42(11):1591–5.PubMed

Mudali D, Teune LK, Renken RJ, Leenders KL, Roerdink JB. Classification of parkinsonian syndromes from FDG-PET brain data using decision trees with SSM/PCA features. Comput Math Methods Med. 2015;2015:136921. https://doi.org/10.1155/2015/136921. CrossRefPubMedPubMedCentral

Spetsieris PG, Ma Y, Dhawan V, Eidelberg D. Differential diagnosis of parkinsonian syndromes using PCA-based functional imaging features. NeuroImage. 2009;45(4):1241–52. https://doi.org/10.1016/j.neuroimage.2008.12.063.CrossRefPubMed

Spetsieris PG, Eidelberg D. Scaled subprofile modeling of resting state imaging data in Parkinson's disease: methodological issues. NeuroImage. 2011;54(4):2899–914. https://doi.org/10.1016/j.neuroimage.2010.10.025.CrossRefPubMed

Pagani M, Oberg J, De Carli F, Calvo A, Moglia C, Canosa A, et al. Metabolic spatial connectivity in amyotrophic lateral sclerosis as revealed by independent component analysis. Hum Brain Mapp. 2016;37(3):942–53. https://doi.org/10.1002/hbm.23078.CrossRefPubMed

10.

Vapnik VN. The nature of statistical learning theory. New York: Springer New York; 1995.CrossRef

11.

Van Weehaeghe D, Ceccarini J, Delva A, Robberecht W, Van Damme P, Van Laere K. Prospective validation of 18F-FDG brain PET discriminant analysis methods in the diagnosis of amyotrophic lateral sclerosis. J Nucl Med. 2016;57(8):1238–43. https://doi.org/10.2967/jnumed.115.166272.CrossRefPubMed

12.

Vandenberghe R, Nelissen N, Van Laere K, Thurfjell L, Buckley C, Farrar G, et al., editors. Support vector machine-based classification of 18F-flutemetamol scans in Alzheimer's disease, MCI and controls: comparison with visual reads and structural MRI-based classification. In: Alzheimer’s & Dementia: Elsevier; 2011. https://doi.org/10.1016/j.nicl.2015.10.007.

13.

Bicchi I, Emiliani C, Vescovi A, Martino S. The big bluff of amyotrophic lateral sclerosis diagnosis: the role of neurodegenerative disease mimics. Neurodegener Dis. 2015;15(6):313–21. https://doi.org/10.1159/000435917. CrossRefPubMed

14.

Gilbert RM, Fahn S, Mitsumoto H, Rowland LP. Parkinsonism and motor neuron diseases: twenty-seven patients with diverse overlap syndromes. Mov Disord. 2010;25(12):1868–75. https://doi.org/10.1002/mds.23200.CrossRefPubMed

15.

Goldman JS, Quinzii C, Dunning-Broadbent J, Waters C, Mitsumoto H, Brannagan TH 3rd, et al. Multiple system atrophy and amyotrophic lateral sclerosis in a family with hexanucleotide repeat expansions in C9orf72. JAMA Neurol. 2014;71(6):771–4. https://doi.org/10.1001/jamaneurol.2013.5762.CrossRefPubMedPubMedCentral

16.

Scholz SW, Bras J. Genetics underlying atypical parkinsonism and related neurodegenerative disorders. Int J Mol Sci. 2015;16(10):24629–55. https://doi.org/10.3390/ijms161024629.CrossRefPubMedPubMedCentral

17.

Jucker M, Walker LC. Self-propagation of pathogenic protein aggregates in neurodegenerative diseases. Nature. 2013;501(7465):45–51. https://doi.org/10.1038/nature12481.CrossRefPubMedPubMedCentral

18.

McCullagh PP, Nelder JA. Generalized linear models: Chapman and Hall; 1989. https://doi.org/10.1002/bimj.4710290217.

19.

Guyon I, Elisseeff A. An introduction to variable and feature selection. J Mach Learn Res. 2003;3:1157–82.

20.

Jolliffe IT. Principal component analysis. New York: Springer New York; 1986.CrossRef

21.

Hastie T, Friedman J, Tibshirani R. Linear methods for classification. The elements of statistical learning: Springer series in Statistics; 2001. p. 79–113. https://doi.org/10.1007/978-0-387-84858-7.

22.

Zou H, Hastie T. Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology). 2005;67(2):301–20. https://doi.org/10.1111/j.1467-9868.2005.00503.x.CrossRef

23.

Varoquaux G, Kowalski M, Thirion B, editors. Social-sparsity brain decoders: faster spatial sparsity. International Workshop on Pattern Recognition in Neuroimaging (PRNI); 2016: IEEE.

24.

Cortes C, Networks VVS-V. Mach Learn. 1995;20(3):273–97. https://doi.org/10.1023/A:1022627411411.CrossRef

25.

Hofmann M. Support vector machines—kernels and the kernel trick; 2006.

26.

Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods: Cambridge University Press; 2000. https://doi.org/10.1017/CBO9780511801389.

27.

Schrooten M, Smetcoren C, Robberecht W, Van Damme P. Benefit of the Awaji diagnostic algorithm for amyotrophic lateral sclerosis: a prospective study. Ann Neurol. 2011;70(1):79–83. https://doi.org/10.1002/ana.22380.CrossRefPubMed

28.

Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent. J Stat Softw. 2010;33(1):1–22.CrossRef

29.

Robert P, Escoufier Y. A unifying tool for linear multivariate statistical methods: the RV- coefficient. Applied statistics, vol 3: WileyRoyal statistical society; 1976. https://doi.org/10.2307/2347233.

30.

Akdemir UO, Tokcaer AB, Karakus A, Kapucu LO. Brain 18F-FDG PET imaging in the differential diagnosis of parkinsonism. Clin Nucl Med. 2014;39(3):e220–6. https://doi.org/10.1097/RLU.0000000000000315.CrossRefPubMed

31.

Meyer PT, Frings L, Rucker G, Hellwig S. (18)F-FDG PET in Parkinsonism: differential diagnosis and evaluation of cognitive impairment. J Nucl Med. 2017;58(12):1888–98. https://doi.org/10.2967/jnumed.116.186403.CrossRefPubMed

32.

Pagani M, Chio A, Valentini MC, Oberg J, Nobili F, Calvo A, et al. Functional pattern of brain FDG-PET in amyotrophic lateral sclerosis. Neurology. 2014;83(12):1067–74. https://doi.org/10.1212/WNL.0000000000000792.CrossRefPubMed

33.

Baldassarre L, Mourao-Miranda J, Pontil M, editors. Structured sparsity models for brain decoding from fMRI data. In: Second International Workshop on Pattern Recognition in NeuroImaging: IEEE; 2012. https://doi.org/10.1109/PRNI.2012.31.

34.

Michel V, Gramfort A, Varoquaux G, Eger E, Thirion B. Total variation regularization for fMRI-based prediction of behavior. IEEE Trans Med Imaging. 2011;30(7):1328–40. https://doi.org/10.1109/TMI.2011.2113378.CrossRefPubMedPubMedCentral

35.

van Weehaeghe D, Ceccarini J, Willekens SM, de Vocht J, van Damme P. Van Laere K. is there a glucose metabolic signature of spreading TDP-43 pathology in amyotrophic lateral sclerosis? Q J Nucl Med Mol Imaging. 2017. https://doi.org/10.23736/S1824-4785.17.03009-6.

Title: Glucose metabolic brain patterns to discriminate amyotrophic lateral sclerosis from Parkinson plus syndromes
Authors: Martijn Devrome
Donatienne Van Weehaeghe
Joke De Vocht
Philip Van Damme
Koen Van Laere
Michel Koole
Publication date: 01-12-2018
Publisher: Springer Berlin Heidelberg
Published in: EJNMMI Research / Issue 1/2018
Electronic ISSN: 2191-219X
DOI: https://doi.org/10.1186/s13550-018-0458-5

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Glucose metabolic brain patterns to discriminate amyotrophic lateral sclerosis from Parkinson plus syndromes

Abstract

Background

Methods

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Background

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2018

An analysis of SPECT/CT non-visualization of sentinel lymph nodes in renal tumors

Presurgical localization of infected avascular bone segments in chronic complicated posttraumatic osteomyelitis in the lower extremity using dual-tracer PET/CT

18F-fluoromisonidazole predicts evofosfamide uptake in pancreatic tumor model

Evaluation of D-isomers of 4-borono-2-18F-fluoro-phenylalanine and O-11C-methyl-tyrosine as brain tumor imaging agents: a comparative PET study with their L-isomers in rat brain glioma

Sensitive and early detection of mitochondrial dysfunction in the liver of NASH model mice by PET imaging with 18F-BCPP-BF

Mapping heterogeneity in glucose uptake in metastatic melanoma using quantitative 18F-FDG PET/CT analysis