Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

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

F. Albrecht, K. Mueller, T. Ballarini, K. Fassbender, J. Wiltfang, FTLD-Consortium, M. Otto, R. Jech, ML. Schroeter

. 2024 ; 10 (15) : e34910. [pub] 20240725

Status neindexováno Jazyk angličtina Země Anglie, Velká Británie

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc24018019

Progressive supranuclear palsy (PSP) is an atypical Parkinsonian syndrome characterized initially by falls and eye movement impairment. This multimodal imaging study aimed at eliciting structural and functional disease-specific brain alterations. T1-weighted and resting-state functional MRI were applied in multi-centric cohorts of PSP and matched healthy controls. Midbrain, cerebellum, and cerebellar peduncles showed severely low gray/white matter volume, whereas thinner cortical gray matter was observed in cingulate cortex, medial and temporal gyri, and insula. Eigenvector centrality analyses revealed regionally specific alterations. Multivariate pattern recognition classified patients correctly based on gray and white matter segmentations with up to 98 % accuracy. Highest accuracies were obtained when restricting feature selection to the midbrain. Eigenvector centrality indices yielded an accuracy around 70 % in this comparison; however, this result did not reach significance. In sum, the study reveals multimodal, widespread brain changes in addition to the well-known midbrain atrophy in PSP. Alterations in brain structure seem to be superior to eigenvector centrality parameters, in particular for prediction with machine learning approaches.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc24018019
003      
CZ-PrNML
005      
20241016081810.0
007      
ta
008      
241008s2024 enk f 000 0|eng||
009      
AR
024    7_
$a 10.1016/j.heliyon.2024.e34910 $2 doi
035    __
$a (PubMed)39170550
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a enk
100    1_
$a Albrecht, Franziska $u Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany $u Division of Physiotherapy, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden $u Women's Health and Allied Health Professionals Theme, Medical Unit Occupational Therapy & Physiotherapy, Karolinska University Hospital, Stockholm, Sweden
245    10
$a Structural parameters are superior to eigenvector centrality in detecting progressive supranuclear palsy with machine learning & multimodal MRI / $c F. Albrecht, K. Mueller, T. Ballarini, K. Fassbender, J. Wiltfang, FTLD-Consortium, M. Otto, R. Jech, ML. Schroeter
520    9_
$a Progressive supranuclear palsy (PSP) is an atypical Parkinsonian syndrome characterized initially by falls and eye movement impairment. This multimodal imaging study aimed at eliciting structural and functional disease-specific brain alterations. T1-weighted and resting-state functional MRI were applied in multi-centric cohorts of PSP and matched healthy controls. Midbrain, cerebellum, and cerebellar peduncles showed severely low gray/white matter volume, whereas thinner cortical gray matter was observed in cingulate cortex, medial and temporal gyri, and insula. Eigenvector centrality analyses revealed regionally specific alterations. Multivariate pattern recognition classified patients correctly based on gray and white matter segmentations with up to 98 % accuracy. Highest accuracies were obtained when restricting feature selection to the midbrain. Eigenvector centrality indices yielded an accuracy around 70 % in this comparison; however, this result did not reach significance. In sum, the study reveals multimodal, widespread brain changes in addition to the well-known midbrain atrophy in PSP. Alterations in brain structure seem to be superior to eigenvector centrality parameters, in particular for prediction with machine learning approaches.
590    __
$a NEINDEXOVÁNO
655    _2
$a časopisecké články $7 D016428
700    1_
$a Mueller, Karsten $u Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany $u Department of Neurology, Charles University, First Faculty of Medicine and General University Hospital, Prague, Czech Republic
700    1_
$a Ballarini, Tommaso $u Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany
700    1_
$a Fassbender, Klaus $u Department of Neurology, Saarland University, Germany
700    1_
$a Wiltfang, Jens $u University Medical Center Göttingen, Germany $u German Center for Neurodegenerative Diseases (DZNE), Göttingen, Germany
700    1_
$a Otto, Markus $u Department of Neurology, University of Ulm, Ulm, Germany $u Department of Neurology, Martin Luther University Halle-Wittenberg, Halle (Saale), Germany
700    1_
$a Jech, Robert $u Department of Neurology, Charles University, First Faculty of Medicine and General University Hospital, Prague, Czech Republic
700    1_
$a Schroeter, Mattias L $u Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany $u Clinic of Cognitive Neurology, University of Leipzig, Germany
710    2_
$a FTLD-Consortium
773    0_
$w MED00190064 $t Heliyon $x 2405-8440 $g Roč. 10, č. 15 (2024), s. e34910
856    41
$u https://pubmed.ncbi.nlm.nih.gov/39170550 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20241008 $b ABA008
991    __
$a 20241016081806 $b ABA008
999    __
$a ok $b bmc $g 2196437 $s 1229970
BAS    __
$a 3
BAS    __
$a PreBMC-PubMed-not-MEDLINE
BMC    __
$a 2024 $b 10 $c 15 $d e34910 $e 20240725 $i 2405-8440 $m Heliyon $n Heliyon $x MED00190064
LZP    __
$a Pubmed-20241008

Najít záznam

Citační ukazatele

Možnosti archivace