To identify progressive supranuclear palsy (PSP), we combined voxel-based morphometry (VBM) and support vector machine (SVM) classification using disease-specific features in multicentric magnetic resonance imaging (MRI) data. Structural brain differences were investigated at four centers between 20 patients with PSP and 20 age-matched healthy controls with T1-weighted MRI at 3T. To pave the way for future application in personalized medicine, we applied SVM classification to identify PSP on an individual level besides group analyses based on VBM. We found a major decline in gray matter density in the brainstem, insula, and striatum, and also in frontomedian regions, which is in line with current literature. Moreover, SVM classification yielded high accuracy rates above 80% for disease identification in imaging data. Focusing analyses on disease-specific regions-of-interest (ROI) led to higher accuracy rates compared to a whole-brain approach. Using a polynomial kernel (instead of a linear kernel) led to an increased sensitivity and a higher specificity of disease detection. Our study supports the application of MRI for individual diagnosis of PSP, if combined with SVM approaches. We demonstrate that SVM classification provides high accuracy rates in multicentric data-a prerequisite for potential application in diagnostic routine.

Department of Neurology and Center of Clinical Neuroscience 1st Faculty of Medicine Charles University and General University Hospital Prague Czechia

Department of Neurology Saarland University Homburg Homburg Germany

Department of Neurology University of Ulm Ulm Germany

Department of Neurology University of UlmUlm Germany; Department of Neurology University of UlmUlm Germany

Institute for Clinical and Experimental Medicine Prague Czechia

Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany

Zobrazit více v PubMed

Ashburner J., Friston K. J. (2005). Unified segmentation. Neuroimage 26, 839–851. 10.1016/j.neuroimage.2005.02.018 PubMed DOI

Belmokhtar N., Benamrane N. (2012). Classification of Alzheimer's Disease from 3 D structural MRI data. Int. J. Compt. Appl. 47, 40–44. 10.5120/7171-9798 DOI

Boxer A. L., Geschwind M. D., Belfor N., Gorno-Tempini M. L., Schauer G. F., Miller B. L., et al. . (2006). Patterns of brain atrophy that differentiate corticobasal degeneration syndrome from progressive supranuclear palsy. Arch. Neurol. 63, 81–86. 10.1001/archneur.63.1.81 PubMed DOI

Brenneis C., Seppi K., Schocke M., Benke T., Wenning G. K., Poewe W. (2004). Voxel based morphometry reveals a distinct pattern of frontal atrophy in progressive supranuclear palsy. J. Neurol. Neurosurg. Psychiatr. 75, 246–249. 10.1136/jnnp.2003.015297 PubMed DOI PMC

Chang C.-C., Lin C.-J. (2011). LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2:27 10.1145/1961189.1961199 DOI

Cordato N. J., Duggins A. J., Halliday G. M., Morris J. G., Pantelis C. (2005). Clinical deficits correlate with regional cerebral atrophy in progressive supranuclear palsy. Brain 128, 1259–1266. 10.1093/brain/awh508 PubMed DOI

Dukart J., Mueller K., Barthel H., Villringer A., Sabri O., Schroeter M. L., et al. . (2013). Meta-analysis based SVM classification enables accurate detection of Alzheimer's disease across different clinical centers using FDG-PET and MRI. Psychiatry Res. 212, 230–236. 10.1016/j.pscychresns.2012.04.007 PubMed DOI

Dukart J., Mueller K., Horstmann A., Barthel H., Möller H. E., Villringer A., et al. . (2011). Combined evaluation of FDG-PET and MRI improves detection and differentiation of dementia. PLoS ONE 6:e18111. 10.1371/journal.pone.0018111 PubMed DOI PMC

Focke N. K., Helms G., Scheewe S., Pantel P. M., Bachmann C. G., Dechent P., et al. . (2011). Individual voxel-based subtype prediction can differentiate progressive supranuclear palsy from idiopathic Parkinson syndrome and healthy controls. Hum. Brain Mapp. 32, 1905–1915. 10.1002/hbm.21161 PubMed DOI PMC

Ghosh B. C., Calder A. J., Peers P. V., Lawrence A. D., Acosta-Cabronero J., Pereira J. M., et al. . (2012). Social cognitive deficits and their neural correlates in progressive supranuclear palsy. Brain 135, 2089–2102. 10.1093/brain/aws128 PubMed DOI PMC

Huppertz H.-J., Möller L., Südmeyer M., Hilker R., Hattingen E., Egger K., et al. . (2016). Differentiation of neurodegenerative parkinsonian syndromes by volumetric magnetic resonance imaging analysis and support vector machine classification. Mov. Disord. 31, 1506–1517 10.1002/mds.26715 PubMed DOI

Keith-Rokosh J., Ang L. C. (2008). Progressive supranuclear palsy: a review of co-existing neurodegeneration. Can. J. Neurol. Sci. 35, 602–608. 10.1017/S0317167100009392 PubMed DOI

Messina D., Cerasa A., Condino F., Arabia G., Novellino F., Nicoletti G., et al. . (2011). Patterns of brain atrophy in Parkinson's disease, progressive supranuclear palsy and multiple system atrophy. Parkinsonism Relat. Disord. 17, 172–176. 10.1016/j.parkreldis.2010.12.010 PubMed DOI

Nichols T., Hayasaka S. (2003). Controlling the familywise error rate in functional neuroimaging: a comparative review. Stat. Methods Med. Res. 12, 419–446. 10.1191/0962280203sm341ra PubMed DOI

Padovani A., Borroni B., Brambati S. M., Agosti C., Broli M., Alonso R., et al. . (2006). Diffusion tensor imaging and voxel based morphometry study in early progressive supranuclear palsy. J. Neurol. Neurosurg. Psychiatr. 77, 457–463. 10.1136/jnnp.2005.075713 PubMed DOI PMC

Platt J. (1998). Sequential Minimal Optimization: a Fast algorithm for training support vector machines. CiteSeerX 10.1.1.43.4376.

Price S., Paviour D., Scahill R., Stevens J., Rossor M., Lees A., et al. . (2004). Voxel-based morphometry detects patterns of atrophy that help differentiate progressive supranuclear palsy and Parkinson's disease. Neuroimage 23, 663–669. 10.1016/j.neuroimage.2004.06.013 PubMed DOI

Salvatore C., Cerasa A., Castiglioni I., Gallivanone F., Augimeri A., Lopez M., et al. . (2014). Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear Palsy. J. Neurosci. Methods 222, 230–237. 10.1016/j.jneumeth.2013.11.016 PubMed DOI

Schroeter M. L., Raczka K., Neumann J., von Cramon D. Y. (2008). Neural networks in frontotemporal dementia–a meta-analysis. Neurobiol. Aging 29, 418–426. 10.1016/j.neurobiolaging.2006.10.023 PubMed DOI

Schroeter M. L., Raczka K., Neumann J., Yves von Cramon D. (2007). Towards a nosology for frontotemporal lobar degenerations-a meta-analysis involving 267 subjects. Neuroimage 36, 497–510. 10.1016/j.neuroimage.2007.03.024 PubMed DOI

Schroeter M. L., Stein T., Maslowski N., Neumann J. (2009). Neural correlates of Alzheimer's disease and mild cognitive impairment: a systematic and quantitative meta-analysis involving 1351 patients. Neuroimage 47, 1196–1206. 10.1016/j.neuroimage.2009.05.037 PubMed DOI PMC

Shao N., Yang J., Li J., Shang H. F. (2014). Voxelwise meta-analysis of gray matter anomalies in progressive supranuclear palsy and Parkinson's disease using anatomic likelihood estimation. Front. Hum. Neurosci. 8:63. 10.3389/fnhum.2014.00063 PubMed DOI PMC

Shi H. C., Zhong J. G., Pan P. L., Xiao P. R., Shen Y., Wu L. J., et al. . (2013). Gray matter atrophy in progressive supranuclear palsy: meta-analysis of voxel-based morphometry studies. Neurol. Sci. 34, 1049–1055. 10.1007/s10072-013-1406-9 PubMed DOI

Williams D. R., Lees A. J. (2009). Progressive supranuclear palsy: clinicopathological concepts and diagnostic challenges. Lancet Neurol. 8, 270–279. 10.1016/S1474-4422(09)70042-0 PubMed DOI

Yu F., Barron D. S., Tantiwongkosi B., Fox P. (2015). Patterns of gray matter atrophy in atypical parkinsonism syndromes: a VBM meta-analysis. Brain Behav. 5:e00329. 10.1002/brb3.329 PubMed DOI PMC

Structural parameters are superior to eigenvector centrality in detecting progressive supranuclear palsy with machine learning & multimodal MRI

Disentangling brain functional network remodeling in corticobasal syndrome - A multimodal MRI study