Radiomics-Derived Brain Age Predicts Functional Outcome After Acute Ischemic Stroke

被引：26

作者：

Bretzner, Martin ^{[1
,4
]}

Bonkhoff, Anna K. ^{[1
]}

Schirmer, Markus D. ^{[1
]}

Hong, Sungmin ^{[1
]}

Dalca, Adrian ^{[1
,2
,6
]}

Donahue, Kathleen ^{[1
]}

Giese, Anne-Katrin ^{[1
]}

Etherton, Mark R. ^{[1
]}

Rist, Pamela M. ^{[1
,7
]}

Nardin, Marco ^{[1
]}

Regenhardt, Robert W. ^{[1
]}

Leclerc, Xavier ^{[4
]}

Lopes, Renaud ^{[4
]}

Gautherot, Morgan ^{[5
]}

Wang, Clinton ^{[1
,6
,28
]}

Benavente, Oscar R. ^{[8
]}

Cole, John W. ^{[21
]}

Donatti, Amanda ^{[11
,12
]}

Griessenauer, Christoph ^{[13
,15
]}

Heitsch, Laura ^{[16
,17
,18
]}

Holmegaard, Lukas ^{[19
,20
]}

Jood, Katarina ^{[19
,20
]}

Jimenez-Conde, Jordi ^{[9
,10
]}

Kittner, Steven J. ^{[9
,10
]}

Lemmens, Robin ^{[22
,23
,24
]}

Levi, Christopher R. ^{[25
,26
]}

McArdle, Patrick F. ^{[27
]}

McDonough, Caitrin W. ^{[29
]}

Meschia, James F. ^{[30
]}

Phuah, Chia-Ling ^{[17
,18
]}

Rolfs, Arndt ^{[31
]}

Ropele, Stefan ^{[32
]}

Rosand, Jonathan ^{[3
,33
,34
]}

Roquer, Jaume ^{[35
,36
]}

Rundek, Tatjana ^{[35
,36
]}

Sacco, Ralph L. ^{[32
,35
,36
]}

Schmidt, Reinhold

Sharma, Pankaj ^{[37
]}

Slowik, Agnieszka ^{[38
]}

Sousa, Alessandro ^{[11
,12
]}

Stanne, Tara M. ^{[19
,20
]}

Strbian, Daniel ^{[39
]}

Tatlisumak, Turgut ^{[19
,20
]}

Thijs, Vincent ^{[40
,41
]}

Vagal, Achala ^{[42
]}

Wasselius, Johan ^{[44
]}

Woo, Daniel ^{[43
]}

Wu, Ona ^{[2
]}

Zand, Ramin ^{[14
]}

Worrall, Bradford B. ^{[47
,48
]}

机构：

[1] Harvard Med Sch, Massachusetts Gen Hosp, J Philip Kistler Stroke Res Ctr, Boston, MA 02115 USA

[2] Harvard Med Sch, Massachusetts Gen Hosp, AA Martinos Ctr Biomed Imaging, Boston, MA USA

[3] Harvard Med Sch, Massachusetts Gen Hosp, Henry & Allison McCance Ctr Brain Hlth, Boston, MA USA

[4] Lille Univ, Inserm, CHU Lille, Lille Neurosci & Cognit,U1172, Lille, France

[5] Lille Univ, Inst Pasteur Lille, CNRS, Inserm,CHU Lille,US 41,UMS 2014 PLBS, Lille, France

[6] MIT, Comp Sci & Artificial Intelligence Lab, Cambridge, MA USA

[7] Brigham & Womens Hosp, Dept Med, Div Prevent Med, Boston, MA USA

[8] Univ British Columbia, Dept Med, Div Neurol, Vancouver, BC, Canada

[9] Univ Maryland, Dept Neurol, Sch Med, Baltimore, MD USA

[10] Vet Affairs Maryland Hlth Care Syst, Baltimore, MD USA

[11] Univ Campinas UNICAMP, Sch Med Sci, Campinas, Brazil

[12] Brazilian Inst Neurosci & Neurotechnol BRAINN, Campinas, SP, Brazil

[13] Geisinger, Dept Neurosurg, Danville, PA USA

[14] Geisinger, Dept Neurol, Danville, PA USA

[15] Paracelsus Med Univ, Christian Doppler Klin, Dept Neurosurg, Salzburg, Austria

[16] Washington Univ, Div Emergency Med, Sch Med, St Louis, MO USA

[17] Washington Univ, Dept Neurol, Sch Med, St Louis, MO USA

[18] Barnes Jewish Hosp, St Louis, MO USA

[19] Univ Gothenburg, Sahlgrenska Acad, Inst Neurosci & Physiol, Dept Clin Neurosci, Gothenburg, Sweden

[20] Sahlgrens Univ Hosp, Dept Neurol, Gothenburg, Sweden

[21] Univ Autonoma Barcelona, IMIM Hosp Mar Inst Hosp Mar Invest Med, Neurovasc Res Grp, Dept Neurol, Barcelona, Spain

[22] Univ Leuven, Dept Neurosci, Expt Neurol, KU Leuven, Leuven, Belgium

[23] Univ Leuven, Leuven Res Inst Neurosci & Dis LIND, KU Leuven, Leuven, Belgium

[24] Univ Hosp Leuven, VIB Vesalius Res Ctr, Dept Neurol, Lab Neurobiol, Leuven, Belgium

[25] Univ Newcastle, Sch Med & Publ Hlth, Newcastle, NSW, Australia

[26] JohnHunter Hosp, Dept Neurol, Newcastle, NSW, Australia

[27] Univ Maryland, Dept Med, Div Endocrinol Diabet & Nutr, Sch Med, Baltimore, MD USA

[28] Univ Florida, Dept Pharmacotherapy & Translat Res, Gainesville, FL USA

[29] Univ Florida, Ctr Pharmacogen, Gainesville, FL USA

[30] Mayo Clin, Dept Neurol, Jacksonville, FL USA

[31] Univ Med Rostock, Klin & Poliklin Neurol, Rostock, Germany

[32] Med Univ Graz, Dept Neurol, Clin Div Neurogeriatr, Graz, Austria

[33] Massachusetts Gen Hosp, Ctr Genom Med, Boston, MA USA

[34] Broad Inst, Cambridge, MA USA

[35] Univ Miami, Miller Sch Med, Dept Neurol, Miami, FL, Uruguay

[36] Univ Miami, Miller Sch Med, Evelyn F McKnight Brain Inst, Miami, FL, Uruguay

[37] Royal Holloway Univ London ICR2UL, Inst Cardiovasc Res, UK St Peters & Ashford Hosp, Egham, Surrey, England

[38] Jagiellonian Univ, Dept Neurol, Med Coll, Krakow, Poland

[39] Univ Helsinki, Dept Neurol, Div Neurocrit Care & Emergency Neurol, Cent Hosp, Helsinki, Finland

[40] Florey Inst Neurosci & Mental Hlth, Stroke Div, Heidelberg, Germany

[41] Austin Hlth, Dept Neurol, Heidelberg, Australia

[42] Univ Cincinnati, Coll Med, Dept Radiol, Cincinnati, OH USA

[43] Univ Cincinnati, Coll Med, Dept Neurol & Rehabil Med, Cincinnati, OH USA

[44] Lund Univ, Dept Clin Sci Lund, Radiol, Lund, Sweden

[45] Lund Univ, Neurol, Lund, Sweden

[46] Skane Univ Hosp, Dept Radiol, Neuroradiol, Malmo, Sweden

[47] Univ Virginia, Dept Neurol, Charlottesville, VA USA

[48] Univ Virginia, Dept Publ Hlth Sci, Charlottesville, VA USA

[49] Univ Technol Sydney, Sydney, Australia

[50] Skane Univ Hosp, Sect Neurol, Lund, Sweden

来源：

NEUROLOGY | 2023年 / 100卷 / 08期

关键词：

ADULTS;

D O I：

10.1212/WNL.0000000000201596

中图分类号：

R74 [神经病学与精神病学];

学科分类号：

摘要：

Background and ObjectivesWhile chronological age is one of the most influential determinants of poststroke outcomes, little is known of the impact of neuroimaging-derived biological "brain age." We hypothesized that radiomics analyses of T2-FLAIR images texture would provide brain age estimates and that advanced brain age of patients with stroke will be associated with cardiovascular risk factors and worse functional outcomes.MethodsWe extracted radiomics from T2-FLAIR images acquired during acute stroke clinical evaluation. Brain age was determined from brain parenchyma radiomics using an ElasticNet linear regression model. Subsequently, relative brain age (RBA), which expresses brain age in comparison with chronological age-matched peers, was estimated. Finally, we built a linear regression model of RBA using clinical cardiovascular characteristics as inputs and a logistic regression model of favorable functional outcomes taking RBA as input.ResultsWe reviewed 4,163 patients from a large multisite ischemic stroke cohort (mean age = 62.8 years, 42.0% female patients). T2-FLAIR radiomics predicted chronological ages (mean absolute error = 6.9 years, r = 0.81). After adjustment for covariates, RBA was higher and therefore described older-appearing brains in patients with hypertension, diabetes mellitus, a history of smoking, and a history of a prior stroke. In multivariate analyses, age, RBA, NIHSS, and a history of prior stroke were all significantly associated with functional outcome (respective adjusted odds ratios: 0.58, 0.76, 0.48, 0.55; all p-values < 0.001). Moreover, the negative effect of RBA on outcome was especially pronounced in minor strokes.DiscussionT2-FLAIR radiomics can be used to predict brain age and derive RBA. Older-appearing brains, characterized by a higher RBA, reflect cardiovascular risk factor accumulation and are linked to worse outcomes after stroke.

引用

页码：E822 / E833

页数：12

共 35 条

[1] Outcome after acute ischemic stroke is linked to sex-specific lesion patterns [J].

Bonkhoff, Anna K. ;

Schirmer, Markus D. ;

Bretzner, Martin ;

Hong, Sungmin ;

Regenhardt, Robert W. ;

Brudfors, Mikael ;

Donahue, Kathleen L. ;

Nardin, Marco J. ;

Dalca, Adrian, V ;

Giese, Anne-Katrin ;

Etherton, Mark R. ;

Hancock, Brandon L. ;

Mocking, Steven J. T. ;

McIntosh, Elissa C. ;

Attia, John ;

Benavente, Oscar R. ;

Bevan, Stephen ;

Cole, John W. ;

Donatti, Amanda ;

Griessenauer, Christoph J. ;

Heitsch, Laura ;

Holmegaard, Lukas ;

Jood, Katarina ;

Jimenez-Conde, Jordi ;

Kittner, Steven J. ;

Lemmens, Robin ;

Levi, Christopher R. ;

McDonough, Caitrin W. ;

Meschia, James F. ;

Phuah, Chia-Ling ;

Rolfs, Arndt ;

Ropele, Stefan ;

Rosand, Jonathan ;

Roquer, Jaume ;

Rundek, Tatjana ;

Sacco, Ralph L. ;

Schmidt, Reinhold ;

Sharma, Pankaj ;

Slowik, Agnieszka ;

Soderholm, Martin ;

Sousa, Alessandro ;

Stanne, Tara M. ;

Strbian, Daniel ;

Tatlisumak, Turgut ;

Thijs, Vincent ;

Vagal, Achala ;

Wasselius, Johan ;

Woo, Daniel ;

Zand, Ramin ;

McArdle, Patrick F. .

NATURE COMMUNICATIONS, 2021, 12 (01)

[2] MRI Radiomic Signature of White Matter Hyperintensities Is Associated With Clinical Phenotypes [J].

Bretzner, Martin ;

Bonkhoff, Anna K. ;

Schirmer, Markus D. ;

Hong, Sungmin ;

Dalca, Adrian, V ;

Donahue, Kathleen L. ;

Giese, Anne-Katrin ;

Etherton, Mark R. ;

Rist, Pamela M. ;

Nardin, Marco ;

Marinescu, Razvan ;

Wang, Clinton ;

Regenhardt, Robert W. ;

Leclerc, Xavier ;

Lopes, Renaud ;

Benavente, Oscar R. ;

Cole, John W. ;

Donatti, Amanda ;

Griessenauer, Christoph J. ;

Heitsch, Laura ;

Holmegaard, Lukas ;

Jood, Katarina ;

Jimenez-Conde, Jordi ;

Kittner, Steven J. ;

Lemmens, Robin ;

Levi, Christopher R. ;

McArdle, Patrick F. ;

McDonough, Caitrin W. ;

Meschia, James F. ;

Phuah, Chia-Ling ;

Rolfs, Arndt ;

Ropele, Stefan ;

Rosand, Jonathan ;

Roquer, Jaume ;

Rundek, Tatjana ;

Sacco, Ralph L. ;

Schmidt, Reinhold ;

Sharma, Pankaj ;

Slowik, Agnieszka ;

Sousa, Alessandro ;

Stanne, Tara M. ;

Strbian, Daniel ;

Tatlisumak, Turgut ;

Thijs, Vincent ;

Vagal, Achala ;

Wasselius, Johan ;

Woo, Daniel ;

Wu, Ona ;

Zand, Ramin ;

Worrall, Bradford B. .

FRONTIERS IN NEUROSCIENCE, 2021, 15

[3]

Cole JH, 2020, NEUROBIOL AGING, V92, P34, DOI [10.1016/j.neurobiolaging.2020.03.014, 10.1016/j.neurobiolaging.2020.03.014]

[4] Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker [J].

Cole, James H. ;

Poudel, Rudra P. K. ;

Tsagkrasoulis, Dimosthenis ;

Caan, Matthan W. A. ;

Steves, Claire ;

Spector, Tim D. ;

Montana, Giovanni .

NEUROIMAGE, 2017, 163 :115-124

[5] Multimodal brain-age prediction and cardiovascular risk: The Whitehall II MRI sub-study [J].

De Lange, Ann-Marie G. ;

Anaturk, Melis ;

Suri, Sana ;

Kaufmann, Tobias ;

Cole, James H. ;

Griffanti, Ludovica ;

Zsoldos, Eniko ;

Jensen, Daria E. A. ;

Filippini, Nicola ;

Singh-Manoux, Archana ;

Kivimaki, Mika ;

Westlye, Lars T. ;

Ebmeier, Klaus P. .

NEUROIMAGE, 2020, 222

[6] Thinking About the Future: A Review of Prognostic Scales Used in Acute Stroke [J].

Drozdowska, Bogna A. ;

Singh, Sarjit ;

Quinn, Terence J. .

FRONTIERS IN NEUROLOGY, 2019, 10

[7] Multi-atlas image registration of clinical data with automated quality assessment using ventricle segmentation [J].

Dubost, Florian ;

de Bruijne, Marleen ;

Nardin, Marco ;

Dalca, Adrian, V ;

Donahue, Kathleen L. ;

Giese, Anne-Katrin ;

Etherton, Mark R. ;

Wu, Ona ;

de Groot, Marius ;

Niessen, Wiro ;

Vernooij, Meike ;

Rost, Natalia S. ;

Schirmer, Markus D. .

MEDICAL IMAGE ANALYSIS, 2020, 63

[8] Predicted Brain Age After Stroke [J].

Egorova, Natalia ;

Liem, Franziskus ;

Hachinski, Vladimir ;

Brodtmann, Amy .

FRONTIERS IN AGING NEUROSCIENCE, 2019, 11

[9] Ten Years of BrainAGE as a Neuroimaging Biomarker of Brain Aging: What Insights Have We Gained? [J].

Franke, Katja ;

Gaser, Christian .

FRONTIERS IN NEUROLOGY, 2019, 10

[10] Advanced BrainAGE in older adults with type 2 diabetes mellitus [J].

Franke, Katja ;

Gaser, Christian ;

Manor, Brad ;

Novak, Vera .

FRONTIERS IN AGING NEUROSCIENCE, 2013, 5

← 1 2 3 4 →