Panteleimon Giannakopoulos1,2, Marie-Louise Montandon2,3, François R Herrmann3, Dennis Hedderich4, Christian Gaser5, Elias Kellner6, Cristelle Rodriguez1,2, Sven Haller7,8,9,10. 1. Department of Psychiatry, University of Geneva, Geneva, Switzerland. 2. Medical Direction, University of Geneva Hospitals, Geneva, Switzerland. 3. Department of Rehabilitation and Geriatrics, Geneva University Hospitals and University of Geneva, Geneva, Switzerland. 4. Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany. 5. Departments of Psychiatry and Neurology, Jena University Hospital, Jena, Germany. 6. Medical Physics, Department of Radiology, Medical Physics, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany. 7. CIMC - Centre d'Imagerie Médicale de Cornavin, Geneva, Switzerland. Sven.haller@me.com. 8. Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden. Sven.haller@me.com. 9. Faculty of Medicine of the University of Geneva, Geneva, Switzerland. Sven.haller@me.com. 10. Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China. Sven.haller@me.com.
Abstract
OBJECTIVES: Established visual brain MRI markers for dementia include hippocampal atrophy (mesio-temporal atrophy MTA), white matter lesions (Fazekas score), and number of cerebral microbleeds (CMBs). We assessed whether novel quantitative, artificial intelligence (AI)-based volumetric scores provide additional value in predicting subsequent cognitive decline in elderly controls. METHODS: A prospective study including 80 individuals (46 females, mean age 73.4 ± 3.5 years). 3T MR imaging was performed at baseline. Extensive neuropsychological assessment was performed at baseline and at 4.5-year follow-up. AI-based volumetric scores were derived from 3DT1: Alzheimer Disease Resemblance Atrophy Index (AD-RAI), Brain Age Gap Estimate (BrainAGE), and normal pressure hydrocephalus (NPH) index. Analyses included regression models between cognitive scores and imaging markers. RESULTS: AD-RAI score at baseline was associated with Corsi (visuospatial memory) decline (10.6% of cognitive variability in multiple regression models). After inclusion of MTA, CMB, and Fazekas scores simultaneously, the AD-RAI score remained as the sole valid predictor of the cognitive outcome explaining 16.7% of its variability. Its percentage reached 21.4% when amyloid positivity was considered an additional explanatory factor. BrainAGE score was associated with Trail Making B (executive functions) decrease (8.5% of cognitive variability). Among the conventional MRI markers, only the Fazekas score at baseline was positively related to the cognitive outcome (8.7% of cognitive variability). The addition of the BrainAGE score as an independent variable significantly increased the percentage of cognitive variability explained by the regression model (from 8.7 to 14%). The addition of amyloid positivity led to a further increase in this percentage reaching 21.8%. CONCLUSIONS: The AI-based AD-RAI index and BrainAGE scores have limited but significant added value in predicting the subsequent cognitive decline in elderly controls when compared to the established visual MRI markers of brain aging, notably MTA, Fazekas score, and number of CMBs. KEY POINTS: • AD-RAI score at baseline was associated with Corsi score (visuospatial memory) decline. • BrainAGE score was associated with Trail Making B (executive functions) decrease. • AD-RAI index and BrainAGE scores have limited but significant added value in predicting the subsequent cognitive decline in elderly controls when compared to the established visual MRI markers of brain aging, notably MTA, Fazekas score, and number of CMBs.
OBJECTIVES: Established visual brain MRI markers for dementia include hippocampal atrophy (mesio-temporal atrophy MTA), white matter lesions (Fazekas score), and number of cerebral microbleeds (CMBs). We assessed whether novel quantitative, artificial intelligence (AI)-based volumetric scores provide additional value in predicting subsequent cognitive decline in elderly controls. METHODS: A prospective study including 80 individuals (46 females, mean age 73.4 ± 3.5 years). 3T MR imaging was performed at baseline. Extensive neuropsychological assessment was performed at baseline and at 4.5-year follow-up. AI-based volumetric scores were derived from 3DT1: Alzheimer Disease Resemblance Atrophy Index (AD-RAI), Brain Age Gap Estimate (BrainAGE), and normal pressure hydrocephalus (NPH) index. Analyses included regression models between cognitive scores and imaging markers. RESULTS: AD-RAI score at baseline was associated with Corsi (visuospatial memory) decline (10.6% of cognitive variability in multiple regression models). After inclusion of MTA, CMB, and Fazekas scores simultaneously, the AD-RAI score remained as the sole valid predictor of the cognitive outcome explaining 16.7% of its variability. Its percentage reached 21.4% when amyloid positivity was considered an additional explanatory factor. BrainAGE score was associated with Trail Making B (executive functions) decrease (8.5% of cognitive variability). Among the conventional MRI markers, only the Fazekas score at baseline was positively related to the cognitive outcome (8.7% of cognitive variability). The addition of the BrainAGE score as an independent variable significantly increased the percentage of cognitive variability explained by the regression model (from 8.7 to 14%). The addition of amyloid positivity led to a further increase in this percentage reaching 21.8%. CONCLUSIONS: The AI-based AD-RAI index and BrainAGE scores have limited but significant added value in predicting the subsequent cognitive decline in elderly controls when compared to the established visual MRI markers of brain aging, notably MTA, Fazekas score, and number of CMBs. KEY POINTS: • AD-RAI score at baseline was associated with Corsi score (visuospatial memory) decline. • BrainAGE score was associated with Trail Making B (executive functions) decrease. • AD-RAI index and BrainAGE scores have limited but significant added value in predicting the subsequent cognitive decline in elderly controls when compared to the established visual MRI markers of brain aging, notably MTA, Fazekas score, and number of CMBs.
Authors: José R Romero; Sarah R Preis; Alexa Beiser; Jayandra J Himali; Ashkan Shoamanesh; Philip A Wolf; Carlos S Kase; Ramachandran S Vasan; Charles DeCarli; Sudha Seshadri Journal: Stroke Date: 2017-01-31 Impact factor: 7.914
Authors: Mara Ten Kate; Frederik Barkhof; Marina Boccardi; Pieter Jelle Visser; Clifford R Jack; Karl-Olof Lovblad; Giovanni B Frisoni; Philip Scheltens Journal: Neurobiol Aging Date: 2017-04 Impact factor: 4.673
Authors: A Verdelho; S Madureira; C Moleiro; J M Ferro; C O Santos; T Erkinjuntti; L Pantoni; F Fazekas; M Visser; G Waldemar; A Wallin; M Hennerici; D Inzitari Journal: Neurology Date: 2010-07-13 Impact factor: 9.910
Authors: Saloua Akoudad; Frank J Wolters; Anand Viswanathan; Renée F de Bruijn; Aad van der Lugt; Albert Hofman; Peter J Koudstaal; M Arfan Ikram; Meike W Vernooij Journal: JAMA Neurol Date: 2016-08-01 Impact factor: 18.302
Authors: Jie Ding; Sigurður Sigurðsson; Pálmi V Jónsson; Gudny Eiriksdottir; Osorio Meirelles; Olafur Kjartansson; Oscar L Lopez; Mark A van Buchem; Vilmundur Gudnason; Lenore J Launer Journal: Neurology Date: 2017-05-03 Impact factor: 9.910
Authors: Mara Ten Kate; Silvia Ingala; Adam J Schwarz; Nick C Fox; Gaël Chételat; Bart N M van Berckel; Michael Ewers; Christopher Foley; Juan Domingo Gispert; Derek Hill; Michael C Irizarry; Adriaan A Lammertsma; José Luis Molinuevo; Craig Ritchie; Philip Scheltens; Mark E Schmidt; Pieter Jelle Visser; Adam Waldman; Joanna Wardlaw; Sven Haller; Frederik Barkhof Journal: Alzheimers Res Ther Date: 2018-10-30 Impact factor: 6.982