Introduction Structural brain imaging is paramount for the diagnosis of behavioural variant of frontotemporal dementia (bvFTD), but it has low sensitivity leading to erroneous or late diagnosis. Methods A total of 515 subjects from two different bvFTD cohorts (training and independent validation cohorts) were used to perform voxel-wise morphometric analysis to identify regions with significant differences between bvFTD and controls. A random forest classifier was used to individually predict bvFTD from deformation-based morphometry differences in isolation and together with semantic fluency. Tenfold cross validation was used to assess the performance of the classifier within the training cohort. A second held-out cohort of genetically confirmed bvFTD cases was used for additional validation. Results Average 10-fold cross-validation accuracy was 89% (82% sensitivity, 93% specificity) using only MRI and 94% (89% sensitivity, 98% specificity) with the addition of semantic fluency. In the separate validation cohort of definite bvFTD, accuracy was 88% (81% sensitivity, 92% specificity) with MRI and 91% (79% sensitivity, 96% specificity) with added semantic fluency scores. Conclusion Our results show that structural MRI and semantic fluency can accurately predict bvFTD at the individual subject level within a completely independent validation cohort coming from a different and independent database.
MRI data-driven algorithm for the diagnosis of behavioural variant frontotemporal dementia / Manera, A. L.; Dadar, M.; Van Swieten, J. C.; Borroni, B.; Sanchez-Valle, R.; Moreno, F.; Laforce, R.; Graff, C.; Synofzik, M.; Galimberti, D.; Rowe, J. B.; Masellis, M.; Tartaglia, M. C.; Finger, E.; Vandenberghe, R.; de Mendonca, A.; Tagliavini, F.; Santana, I.; Butler, C. R.; Gerhard, A.; Danek, A.; Levin, J.; Otto, M.; Frisoni, G.; Ghidoni, R.; Sorbi, S.; Rohrer, J. D.; Ducharme, S.; Louis Collins, D.; Rosen, H.; Dickerson, B. C.; Domoto-Reilly, K.; Knopman, D.; Boeve, B. F.; Boxer, A. L.; Kornak, J.; Miller, B. L.; Seeley, W. W.; Gorno-Tempini, M. -L.; Mcginnis, S.; Mandelli, M. L.; Afonso, S.; Almeida, M. R.; Anderl-Straub, S.; Andersson, C.; Antonell, A.; Archetti, S.; Arighi, A.; Balasa, M.; Barandiaran, M.; Bargallo, N.; Bartha, R.; Bender, B.; Benussi, A.; Benussi, L.; Bessi, V.; Binetti, G.; Black, S.; Bocchetta, M.; Borrego-Ecija, S.; Bras, J.; Bruffaerts, R.; Caroppo, P.; Cash, D.; Castelo-Branco, M.; Convery, R.; Cope, T.; Cosseddu, M.; de Arriba, M.; Di Fede, G.; Diaz, Z.; Duro, D.; Fenoglio, C.; Ferrari, C.; Ferreira, C.; Ferreira, C. B.; Flanagan, T.; Fox, N.; Freedman, M.; Fumagalli, G.; Gabilondo, A.; Gasparotti, R.; Gauthier, S.; Gazzina, S.; Giaccone, G.; Gorostidi, A.; Greaves, C.; Guerreiro, R.; Heller, C.; Hoegen, T.; Indakoetxea, B.; Jelic, V.; Jiskoot, L.; Karnath, H. -O.; Keren, R.; Leitao, M. J.; Llado, A.; Lombardi, G.; Loosli, S.; Maruta, C.; Mead, S.; Meeter, L.; Miltenberger, G.; van Minkelen, R.; Mitchell, S.; Moore, K. M.; Nacmias, B.; Neason, M.; Nicholas, J.; Oijerstedt, L.; Olives, J.; Ourselin, S.; Padovani, A.; Panman, J.; Papma, J.; Peakman, G.; Piaceri, I.; Pievani, M.; Pijnenburg, Y.; Polito, C.; Premi, E.; Prioni, S.; Prix, C.; Rademakers, R.; Redaelli, V.; Rittman, T.; Rogaeva, E.; Rosa-Neto, P.; Rossi, G.; Rossor, M.; Santiago, B.; Scarpini, E.; Schonecker, S.; Semler, E.; Shafei, R.; Shoesmith, C.; Tabuas-Pereira, M.; Tainta, M.; Taipa, R.; Tang-Wai, D.; Thomas, D. L.; Thonberg, H.; Timberlake, C.; Tiraboschi, P.; Todd, E.; Vandamme, P.; Vandenbulcke, M.; Veldsman, M.; Verdelho, A.; Villanua, J.; Warren, J.; Wilke, C.; Woollacott, I.; Wlasich, E.; Zetterberg, H.; Zulaica, M.. - In: JOURNAL OF NEUROLOGY, NEUROSURGERY AND PSYCHIATRY. - ISSN 0022-3050. - 92:6(2021), pp. 608-616. [10.1136/jnnp-2020-324106]
MRI data-driven algorithm for the diagnosis of behavioural variant frontotemporal dementia
Gorno-Tempini M. -L.;Fumagalli G.;
2021-01-01
Abstract
Introduction Structural brain imaging is paramount for the diagnosis of behavioural variant of frontotemporal dementia (bvFTD), but it has low sensitivity leading to erroneous or late diagnosis. Methods A total of 515 subjects from two different bvFTD cohorts (training and independent validation cohorts) were used to perform voxel-wise morphometric analysis to identify regions with significant differences between bvFTD and controls. A random forest classifier was used to individually predict bvFTD from deformation-based morphometry differences in isolation and together with semantic fluency. Tenfold cross validation was used to assess the performance of the classifier within the training cohort. A second held-out cohort of genetically confirmed bvFTD cases was used for additional validation. Results Average 10-fold cross-validation accuracy was 89% (82% sensitivity, 93% specificity) using only MRI and 94% (89% sensitivity, 98% specificity) with the addition of semantic fluency. In the separate validation cohort of definite bvFTD, accuracy was 88% (81% sensitivity, 92% specificity) with MRI and 91% (79% sensitivity, 96% specificity) with added semantic fluency scores. Conclusion Our results show that structural MRI and semantic fluency can accurately predict bvFTD at the individual subject level within a completely independent validation cohort coming from a different and independent database.File | Dimensione | Formato | |
---|---|---|---|
2021 Manera et al.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.3 MB
Formato
Adobe PDF
|
1.3 MB | Adobe PDF | Visualizza/Apri |
Rohrer_MRI data-driven algorithm for the diagnosis of behavioural variant frontotemporal dementia_AAM.pdf
accesso aperto
Tipologia:
Post-print referato (Refereed author’s manuscript)
Licenza:
Creative commons
Dimensione
715.82 kB
Formato
Adobe PDF
|
715.82 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione