Juha R Koikkalainen1, Hanneke F M Rhodius-Meester2, Kristian S Frederiksen3, Marie Bruun3, Steen G Hasselbalch3, Marta Baroni4, Patrizia Mecocci4, Ritva Vanninen5,6, Anne Remes6, Hilkka Soininen6, Mark van Gils7, Wiesje M van der Flier2,8, Philip Scheltens2, Frederik Barkhof2,9,10, Timo Erkinjuntti11, Jyrki M P Lötjönen12. 1. Combinostics Ltd., Hatanpään valtatie 24, 33100, Tampere, Finland. 2. Alzheimer Center, Department of Neurology, VU University Medical Centre, Amsterdam Neuroscience, Amsterdam, the Netherlands. 3. Danish Dementia Research Centre, Department of Neurology, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark. 4. Institute of Gerontology and Geriatrics, University of Perugia, Perugia, Italy. 5. Institute of Clinical Medicine, Radiology, University of Eastern Finland, Kuopio, Finland. 6. Department of Clinical Radiology, Kuopio University Hospital, Kuopio, Finland. 7. VTT Technical Research Center of Finland Ltd, Tampere, Finland. 8. Department of Epidemiology and Biostatistics, VU University Medical Centre, Amsterdam, the Netherlands. 9. Institute of Neurology, University College London, London, UK. 10. Institute of Healthcare Engineering, University College London, London, UK. 11. Clinical Neurosciences, Neurology, University of Helsinki and Helsinki University Hospital, Helsinki, Finland. 12. Combinostics Ltd., Hatanpään valtatie 24, 33100, Tampere, Finland. jyrki.lotjonen@combinostics.com.
Abstract
OBJECTIVES: The aims of this study were to examine whether visual MRI rating scales used in diagnostics of cognitive disorders can be estimated computationally and to compare the visual rating scales with their computed counterparts in differential diagnostics. METHODS: A set of volumetry and voxel-based morphometry imaging biomarkers was extracted from T1-weighted and FLAIR images. A regression model was developed for estimating visual rating scale values from a combination of imaging biomarkers. We studied three visual rating scales: medial temporal lobe atrophy (MTA), global cortical atrophy (GCA), and white matter hyperintensities (WMHs) measured by the Fazekas scale. Images and visual ratings from the Amsterdam Dementia Cohort (ADC) (N = 513) were used to develop the models and cross-validate them. The PredictND (N = 672) and ADNI (N = 752) cohorts were used for independent validation to test generalizability. RESULTS: The correlation coefficients between visual and computed rating scale values were 0.83/0.78 (MTA-left), 0.83/0.79 (MTA-right), 0.64/0.64 (GCA), and 0.76/0.75 (Fazekas) in ADC/PredictND cohorts. When performance in differential diagnostics was studied for the main types of dementia, the highest balanced accuracy, 0.75-0.86, was observed for separating different dementias from cognitively normal subjects using computed GCA. The lowest accuracy of about 0.5 for all the visual and computed scales was observed for the differentiation between Alzheimer's disease and frontotemporal lobar degeneration. Computed scales produced higher balanced accuracies than visual scales for MTA and GCA (statistically significant). CONCLUSIONS: MTA, GCA, and WMHs can be reliably estimated automatically helping to provide consistent imaging biomarkers for diagnosing cognitive disorders, even among less experienced readers. KEY POINTS: • Visual rating scales used in diagnostics of cognitive disorders can be estimated computationally from MRI images with intraclass correlations ranging from 0.64 (GCA) to 0.84 (MTA). • Computed scales provided high diagnostic accuracy with single-subject data (area under the receiver operating curve range, 0.84-0.94).
OBJECTIVES: The aims of this study were to examine whether visual MRI rating scales used in diagnostics of cognitive disorders can be estimated computationally and to compare the visual rating scales with their computed counterparts in differential diagnostics. METHODS: A set of volumetry and voxel-based morphometry imaging biomarkers was extracted from T1-weighted and FLAIR images. A regression model was developed for estimating visual rating scale values from a combination of imaging biomarkers. We studied three visual rating scales: medial temporal lobe atrophy (MTA), global cortical atrophy (GCA), and white matter hyperintensities (WMHs) measured by the Fazekas scale. Images and visual ratings from the Amsterdam Dementia Cohort (ADC) (N = 513) were used to develop the models and cross-validate them. The PredictND (N = 672) and ADNI (N = 752) cohorts were used for independent validation to test generalizability. RESULTS: The correlation coefficients between visual and computed rating scale values were 0.83/0.78 (MTA-left), 0.83/0.79 (MTA-right), 0.64/0.64 (GCA), and 0.76/0.75 (Fazekas) in ADC/PredictND cohorts. When performance in differential diagnostics was studied for the main types of dementia, the highest balanced accuracy, 0.75-0.86, was observed for separating different dementias from cognitively normal subjects using computed GCA. The lowest accuracy of about 0.5 for all the visual and computed scales was observed for the differentiation between Alzheimer's disease and frontotemporal lobar degeneration. Computed scales produced higher balanced accuracies than visual scales for MTA and GCA (statistically significant). CONCLUSIONS: MTA, GCA, and WMHs can be reliably estimated automatically helping to provide consistent imaging biomarkers for diagnosing cognitive disorders, even among less experienced readers. KEY POINTS: • Visual rating scales used in diagnostics of cognitive disorders can be estimated computationally from MRI images with intraclass correlations ranging from 0.64 (GCA) to 0.84 (MTA). • Computed scales provided high diagnostic accuracy with single-subject data (area under the receiver operating curve range, 0.84-0.94).
Entities:
Keywords:
Atrophy; Cognition disorders; Magnetic resonance imaging
Authors: L A van de Pol; A Hensel; W M van der Flier; P-J Visser; Y A L Pijnenburg; F Barkhof; H Josef Gertz; P Scheltens Journal: J Neurol Neurosurg Psychiatry Date: 2005-11-23 Impact factor: 10.154
Authors: Lorena Bresciani; Roberta Rossi; Cristina Testa; Cristina Geroldi; Samantha Galluzzi; Mikko P Laakso; Alberto Beltramello; Hilkka Soininen; Giovanni B Frisoni Journal: Aging Clin Exp Res Date: 2005-02 Impact factor: 3.636
Authors: Elisabeth C W van Straaten; Franz Fazekas; Egill Rostrup; Philip Scheltens; Reinhold Schmidt; Leonardo Pantoni; Domenico Inzitari; Gunhild Waldemar; Timo Erkinjuntti; Riita Mäntylä; Lars-Olof Wahlund; Frederik Barkhof Journal: Stroke Date: 2006-01-26 Impact factor: 7.914
Authors: Randy L Buckner; Denise Head; Jamie Parker; Anthony F Fotenos; Daniel Marcus; John C Morris; Abraham Z Snyder Journal: Neuroimage Date: 2004-10 Impact factor: 6.556
Authors: John T O'Brien; Timo Erkinjuntti; Barry Reisberg; Gustavo Roman; Tohru Sawada; Leonardo Pantoni; John V Bowler; Clive Ballard; Charles DeCarli; Philip B Gorelick; Kenneth Rockwood; Alistair Burns; Serge Gauthier; Steven T DeKosky Journal: Lancet Neurol Date: 2003-02 Impact factor: 44.182
Authors: Leonardo Pantoni; Anna Maria Basile; Giovanni Pracucci; Kjell Asplund; Julien Bogousslavsky; Hugues Chabriat; Timo Erkinjuntti; Franz Fazekas; José M Ferro; Michael Hennerici; John O'brien; Philip Scheltens; Marieke C Visser; Lars-Olof Wahlund; Gunhild Waldemar; Anders Wallin; Domenico Inzitari Journal: Neuroepidemiology Date: 2005 Impact factor: 3.282
Authors: Bruno Dubois; Howard H Feldman; Claudia Jacova; Steven T Dekosky; Pascale Barberger-Gateau; Jeffrey Cummings; André Delacourte; Douglas Galasko; Serge Gauthier; Gregory Jicha; Kenichi Meguro; John O'brien; Florence Pasquier; Philippe Robert; Martin Rossor; Steven Salloway; Yaakov Stern; Pieter J Visser; Philip Scheltens Journal: Lancet Neurol Date: 2007-08 Impact factor: 44.182
Authors: Silvia Ingala; Ingrid S van Maurik; Daniele Altomare; Raphael Wurm; Ellen Dicks; Ronald A van Schijndel; Marissa Zwan; Femke Bouwman; Niki Schoonenboom; Leo Boelaarts; Gerwin Roks; Rob van Marum; Barbera van Harten; Inge van Uden; Jules Claus; Viktor Wottschel; Hugo Vrenken; Mike P Wattjes; Wiesje M van der Flier; Frederik Barkhof Journal: Eur Radiol Date: 2022-05-31 Impact factor: 5.315
Authors: Gustav Mårtensson; Claes Håkansson; Joana B Pereira; Sebastian Palmqvist; Oskar Hansson; Danielle van Westen; Eric Westman Journal: Neuroimage Clin Date: 2020-06-10 Impact factor: 4.881
Authors: Hanneke F M Rhodius-Meester; Ingrid S van Maurik; Juha Koikkalainen; Antti Tolonen; Kristian S Frederiksen; Steen G Hasselbalch; Hilkka Soininen; Sanna-Kaisa Herukka; Anne M Remes; Charlotte E Teunissen; Frederik Barkhof; Yolande A L Pijnenburg; Philip Scheltens; Jyrki Lötjönen; Wiesje M van der Flier Journal: PLoS One Date: 2020-01-15 Impact factor: 3.240
Authors: Sini Toppala; Laura L Ekblad; Jyrki Lötjönen; Semi Helin; Saija Hurme; Jarkko Johansson; Antti Jula; Mira Karrasch; Juha Koikkalainen; Hanna Laine; Riitta Parkkola; Matti Viitanen; Juha O Rinne Journal: J Alzheimers Dis Date: 2019 Impact factor: 4.472
Authors: Claes Håkansson; Ashkan Tamaddon; Henrik Andersson; Gustav Torisson; Gustav Mårtensson; My Truong; Mårten Annertz; Elisabet Londos; Isabella M Björkman-Burtscher; Oskar Hansson; Danielle van Westen Journal: Eur Radiol Date: 2021-07-30 Impact factor: 5.315
Authors: Hugh G Pemberton; Lara A M Zaki; Olivia Goodkin; Ravi K Das; Rebecca M E Steketee; Frederik Barkhof; Meike W Vernooij Journal: Neuroradiology Date: 2021-09-03 Impact factor: 2.804
Authors: Aku L Kaipainen; Johanna Pitkänen; Fanni Haapalinna; Olli Jääskeläinen; Hanna Jokinen; Susanna Melkas; Timo Erkinjuntti; Ritva Vanninen; Anne M Koivisto; Jyrki Lötjönen; Juha Koikkalainen; Sanna-Kaisa Herukka; Valtteri Julkunen Journal: Neuroradiology Date: 2021-08-14 Impact factor: 2.804