000273979 001__ 273979
000273979 005__ 20250115165650.0
000273979 0247_ $$2doi$$a10.1016/j.compbiomed.2024.109518
000273979 0247_ $$2pmid$$apmid:39662313
000273979 0247_ $$2ISSN$$a0010-4825
000273979 0247_ $$2ISSN$$a1879-0534
000273979 037__ $$aDZNE-2024-01428
000273979 041__ $$aEnglish
000273979 082__ $$a570
000273979 1001_ $$aVolkmann, Heiko$$b0
000273979 245__ $$aMRI classification of progressive supranuclear palsy, Parkinson disease and controls using deep learning and machine learning algorithms for the identification of regions and tracts of interest as potential biomarkers.
000273979 260__ $$aAmsterdam [u.a.]$$bElsevier Science$$c2025
000273979 3367_ $$2DRIVER$$aarticle
000273979 3367_ $$2DataCite$$aOutput Types/Journal article
000273979 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1736938985_31493
000273979 3367_ $$2BibTeX$$aARTICLE
000273979 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000273979 3367_ $$00$$2EndNote$$aJournal Article
000273979 520__ $$aQuantitative magnetic resonance imaging (MRI) analysis has shown promise in differentiating neurodegenerative Parkinsonian syndromes and has significantly advanced our understanding of diseases like progressive supranuclear palsy (PSP) in recent years.The aim of this study was to develop, implement and compare MRI analysis algorithms based on artificial intelligence (AI) that can differentiate PSP not only from healthy controls but also from Parkinson disease (PD), by analyzing changes in brain structure and microstructure. Specifically, this study focused on identifying regions of interest (ROIs) and tracts of interest (TOIs) that are crucial for the algorithms to provide clinically relevant performance indices for the distinction between disease variants.MR data comprised diffusion tensor imaging (DTI - tractwise fractional anisotropy statistics (TFAS)) and T1-weighted (T1-w) data (texture analysis of the corpus callosum (CC)). One subject sample with 74 PSP patients and 63 controls was recorded at 3.0T at multiple sites. The other sample came from a single site, consisting of 66 PSP patients, 66 PD patients, and 44 controls, recorded at 1.5T. Four different machine learning algorithms (ML) and a deep learning (DL) neural network approach using Tensor Flow were implemented for the study. The training of the algorithms was performed on 80 % of the data, which included the entire single-site data and parts of the multiple-site data. The validation process was conducted on the remaining data, thereby consistently separating training and validation data.A random forest algorithm and a DL neural network classified PSP and healthy controls with accuracies of 92 % and 95 %, respectively. Particularly, DTI derived measures for the pons, midbrain tegmentum, superior cerebral peduncle, putamen, and CC contributed to high accuracies. Furthermore, DL neural network classification of PSP and PD with 86 % accuracy showed the importance of 19 structures. The four most important features were DTI derived measures for prefrontal white matter, the fasciculus frontooccipitalis, the midbrain tegmentum, and the CC area II. This DL network achieved a sensitivity of 88 % and specificity of 85 %, resulting in a Youden-index of 0.72.The primary goal of the present study was to compare multiple ML-methods and a DL approach to identify the least necessary set of brain structures to classify PSP vs. controls and PSP vs. PD by ranking them in a hierarchical order of importance. That way, this study demonstrated the potential of AI approaches to MRI as possible diagnostic and scientific tools to differentiate variants of neurodegenerative Parkinsonism.
000273979 536__ $$0G:(DE-HGF)POF4-353$$a353 - Clinical and Health Care Research (POF4-353)$$cPOF4-353$$fPOF IV$$x0
000273979 588__ $$aDataset connected to CrossRef, PubMed, , Journals: pub.dzne.de
000273979 650_7 $$2Other$$aDeep learning
000273979 650_7 $$2Other$$aDiffusion tensor imaging (DTI)
000273979 650_7 $$2Other$$aMachine learning
000273979 650_7 $$2Other$$aMagnetic resonance imaging (MRI)
000273979 650_7 $$2Other$$aNeuropathology
000273979 650_7 $$2Other$$aProgressive supranuclear palsy
000273979 650_7 $$2Other$$atau protein
000273979 693__ $$0EXP:(DE-2719)DESCRIBE-PSP-20160101$$5EXP:(DE-2719)DESCRIBE-PSP-20160101$$eDZNE Clinical Registry Study of Neurodegenerative Diseases in Patients with Progressive Supranuclear Paresis (PSP)$$x0
000273979 7001_ $$0P:(DE-2719)2811373$$aHöglinger, Günter U$$b1$$udzne
000273979 7001_ $$aGrön, Georg$$b2
000273979 7001_ $$0P:(DE-2719)9002368$$aBarlescu, Lavinia$$b3$$udzne
000273979 7001_ $$agroup, DESCRIBE-PSP study$$b4$$eCollaboration Author
000273979 7001_ $$aMüller, Hans-Peter$$b5
000273979 7001_ $$0P:(DE-2719)9001967$$aKassubek, Jan$$b6$$udzne
000273979 773__ $$0PERI:(DE-600)1496984-1$$a10.1016/j.compbiomed.2024.109518$$gVol. 185, p. 109518 -$$p109518$$tComputers in biology and medicine$$v185$$x0010-4825$$y2025
000273979 8564_ $$uhttps://pub.dzne.de/record/273979/files/DZNE-2024-01428%20SUP.pdf
000273979 8564_ $$uhttps://pub.dzne.de/record/273979/files/DZNE-2024-01428.pdf$$yOpenAccess
000273979 8564_ $$uhttps://pub.dzne.de/record/273979/files/DZNE-2024-01428%20SUP.pdf?subformat=pdfa$$xpdfa
000273979 8564_ $$uhttps://pub.dzne.de/record/273979/files/DZNE-2024-01428.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000273979 909CO $$ooai:pub.dzne.de:273979$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
000273979 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2811373$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b1$$kDZNE
000273979 9101_ $$0I:(DE-HGF)0$$6P:(DE-2719)9002368$$aExternal Institute$$b3$$kExtern
000273979 9101_ $$0I:(DE-HGF)0$$6P:(DE-2719)9001967$$aExternal Institute$$b6$$kExtern
000273979 9131_ $$0G:(DE-HGF)POF4-353$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vClinical and Health Care Research$$x0
000273979 9141_ $$y2025
000273979 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bCOMPUT BIOL MED : 2022$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000273979 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bCOMPUT BIOL MED : 2022$$d2023-08-25
000273979 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-08-25
000273979 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000273979 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2023-08-25$$wger
000273979 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-08-25
000273979 9201_ $$0I:(DE-2719)1111015$$kClinical Research (Munich)$$lClinical Research (Munich)$$x0
000273979 980__ $$ajournal
000273979 980__ $$aVDB
000273979 980__ $$aUNRESTRICTED
000273979 980__ $$aI:(DE-2719)1111015
000273979 9801_ $$aFullTexts