Wiltfang, Jens

[["dc.bibliographiccitation.artnumber","114"],["dc.bibliographiccitation.issue","1"],["dc.bibliographiccitation.journal","BMC Neurology"],["dc.bibliographiccitation.volume","22"],["dc.contributor.author","Khadhraoui, Eya"],["dc.contributor.author","Müller, Sebastian J."],["dc.contributor.author","Hansen, Niels"],["dc.contributor.author","Riedel, Christian H."],["dc.contributor.author","Langer, Philip"],["dc.contributor.author","Timäeus, Charles"],["dc.contributor.author","Wiltfang, Jens"],["dc.contributor.author","Bouter, Caroline"],["dc.contributor.author","Lange, Claudia"],["dc.contributor.author","Ernst, Marielle"],["dc.date.accessioned","2022-04-01T10:01:59Z"],["dc.date.accessioned","2022-08-18T12:35:15Z"],["dc.date.available","2022-04-01T10:01:59Z"],["dc.date.available","2022-08-18T12:35:15Z"],["dc.date.issued","2022-03-24"],["dc.date.updated","2022-07-29T12:07:17Z"],["dc.description.abstract","Abstract\r\n \r\n Background\r\n Dementia with Lewy bodies (DLB) is the second most common dementia type in patients older than 65 years. Its atrophy patterns remain unknown. Its similarities to Parkinson's disease and differences from Alzheimer's disease are subjects of current research.\r\n \r\n \r\n Methods\r\n The aim of our study was (i) to form a group of patients with DLB (and a control group) and create a 3D MRI data set (ii) to volumetrically analyze the entire brain in these groups, (iii) to evaluate visual and manual metric measurements of the innominate substance for real-time diagnosis, and (iv) to compare our groups and results with the latest literature. We identified 102 patients with diagnosed DLB in our psychiatric and neurophysiological archives. After exclusion, 63 patients with valid 3D data sets remained. We compared them with a control group of 25 patients of equal age and sex distribution. We evaluated the atrophy patterns in both (1) manually and (2) via Fast Surfers segmentation and volumetric calculations. Subgroup analyses were done of the CSF data and quality of 3D T1 data sets.\r\n \r\n \r\n Results\r\n Concordant with the literature, we detected moderate, symmetric atrophy of the hippocampus, entorhinal cortex and amygdala, as well as asymmetric atrophy of the right parahippocampal gyrus in DLB. The caudate nucleus was unaffected in patients with DLB, while all the other measured territories were slightly too moderately atrophied. The area under the curve analysis of the left hippocampus volume ratio (< 3646mm3) revealed optimal 76% sensitivity and 100% specificity (followed by the right hippocampus and left amygdala). The substantia innominata’s visual score attained a 51% optimal sensitivity and 84% specificity, and the measured distance 51% optimal sensitivity and 68% specificity in differentiating DLB from our control group.\r\n \r\n \r\n Conclusions\r\n In contrast to other studies, we observed a caudate nucleus sparing atrophy of the whole brain in patients with DLB. As the caudate nucleus is known to be the last survivor in dopamine-uptake, this could be the result of an overstimulation or compensation mechanism deserving further investigation. Its relative hypertrophy compared to all other brain regions could enable an imaging based identification of patients with DLB via automated segmentation and combined volumetric analysis of the hippocampus and amygdala."],["dc.description.sponsorship","Georg-August-Universität Göttingen"],["dc.description.sponsorship","Open-Access-Publikationsfonds 2022"],["dc.identifier.citation","BMC Neurology. 2022 Mar 24;22(1):114"],["dc.identifier.doi","10.1186/s12883-022-02642-0"],["dc.identifier.pii","2642"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/105794"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/112938"],["dc.language.iso","en"],["dc.notes.intern","DOI-Import GROB-530"],["dc.publisher","BioMed Central"],["dc.relation.eissn","1471-2377"],["dc.rights","CC BY 4.0"],["dc.rights.holder","The Author(s)"],["dc.rights.uri","https://creativecommons.org/licenses/by/4.0"],["dc.subject","Dementia with Lewy Bodies"],["dc.subject","MRI"],["dc.subject","Atrophy"],["dc.subject","Substantia innominate"],["dc.title","Manual and automated analysis of atrophy patterns in dementia with Lewy bodies on MRI"],["dc.type","journal_article"],["dc.type.internalPublication","yes"],["dc.type.subtype","original_ja"],["dspace.entity.type","Publication"]]

[["dc.bibliographiccitation.artnumber","191"],["dc.bibliographiccitation.issue","1"],["dc.bibliographiccitation.journal","Alzheimer's Research & Therapy"],["dc.bibliographiccitation.volume","13"],["dc.contributor.author","Dyrba, Martin"],["dc.contributor.author","Hanzig, Moritz"],["dc.contributor.author","Altenstein, Slawek"],["dc.contributor.author","Bader, Sebastian"],["dc.contributor.author","Ballarini, Tommaso"],["dc.contributor.author","Brosseron, Frederic"],["dc.contributor.author","Buerger, Katharina"],["dc.contributor.author","Cantré, Daniel"],["dc.contributor.author","Dechent, Peter"],["dc.contributor.author","Dobisch, Laura"],["dc.contributor.author","Düzel, Emrah"],["dc.contributor.author","Ewers, Michael"],["dc.contributor.author","Fliessbach, Klaus"],["dc.contributor.author","Glanz, Wenzel"],["dc.contributor.author","Haynes, John-Dylan"],["dc.contributor.author","Heneka, Michael T."],["dc.contributor.author","Janowitz, Daniel"],["dc.contributor.author","Keles, Deniz B."],["dc.contributor.author","Kilimann, Ingo"],["dc.contributor.author","Laske, Christoph"],["dc.contributor.author","Maier, Franziska"],["dc.contributor.author","Metzger, Coraline D."],["dc.contributor.author","Munk, Matthias H."],["dc.contributor.author","Perneczky, Robert"],["dc.contributor.author","Peters, Oliver"],["dc.contributor.author","Preis, Lukas"],["dc.contributor.author","Priller, Josef"],["dc.contributor.author","Rauchmann, Boris"],["dc.contributor.author","Roy, Nina"],["dc.contributor.author","Scheffler, Klaus"],["dc.contributor.author","Schneider, Anja"],["dc.contributor.author","Schott, Björn H."],["dc.contributor.author","Spottke, Annika"],["dc.contributor.author","Spruth, Eike J."],["dc.contributor.author","Weber, Marc-André"],["dc.contributor.author","Ertl-Wagner, Birgit"],["dc.contributor.author","Wagner, Michael"],["dc.contributor.author","Wiltfang, Jens"],["dc.contributor.author","Jessen, Frank"],["dc.contributor.author","Teipel, Stefan J."],["dc.contributor.authorgroup","for the ADNI, AIBL, DELCODE study groups"],["dc.date.accessioned","2021-12-01T09:23:04Z"],["dc.date.accessioned","2022-08-18T12:39:17Z"],["dc.date.available","2021-12-01T09:23:04Z"],["dc.date.available","2022-08-18T12:39:17Z"],["dc.date.issued","2021-11-23"],["dc.date.updated","2022-07-29T12:17:50Z"],["dc.description.abstract","Abstract\r\n \r\n Background\r\n Although convolutional neural networks (CNNs) achieve high diagnostic accuracy for detecting Alzheimer’s disease (AD) dementia based on magnetic resonance imaging (MRI) scans, they are not yet applied in clinical routine. One important reason for this is a lack of model comprehensibility. Recently developed visualization methods for deriving CNN relevance maps may help to fill this gap as they allow the visualization of key input image features that drive the decision of the model. We investigated whether models with higher accuracy also rely more on discriminative brain regions predefined by prior knowledge.\r\n \r\n \r\n Methods\r\n We trained a CNN for the detection of AD in N = 663 T1-weighted MRI scans of patients with dementia and amnestic mild cognitive impairment (MCI) and verified the accuracy of the models via cross-validation and in three independent samples including in total N = 1655 cases. We evaluated the association of relevance scores and hippocampus volume to validate the clinical utility of this approach. To improve model comprehensibility, we implemented an interactive visualization of 3D CNN relevance maps, thereby allowing intuitive model inspection.\r\n \r\n \r\n Results\r\n Across the three independent datasets, group separation showed high accuracy for AD dementia versus controls (AUC ≥ 0.91) and moderate accuracy for amnestic MCI versus controls (AUC ≈ 0.74). Relevance maps indicated that hippocampal atrophy was considered the most informative factor for AD detection, with additional contributions from atrophy in other cortical and subcortical regions. Relevance scores within the hippocampus were highly correlated with hippocampal volumes (Pearson’s r ≈ −0.86, p < 0.001).\r\n \r\n \r\n Conclusion\r\n The relevance maps highlighted atrophy in regions that we had hypothesized a priori. This strengthens the comprehensibility of the CNN models, which were trained in a purely data-driven manner based on the scans and diagnosis labels. The high hippocampus relevance scores as well as the high performance achieved in independent samples support the validity of the CNN models in the detection of AD-related MRI abnormalities. The presented data-driven and hypothesis-free CNN modeling approach might provide a useful tool to automatically derive discriminative features for complex diagnostic tasks where clear clinical criteria are still missing, for instance for the differential diagnosis between various types of dementia."],["dc.identifier.citation","Alzheimer's Research & Therapy. 2021 Nov 23;13(1):191"],["dc.identifier.doi","10.1186/s13195-021-00924-2"],["dc.identifier.pii","924"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/94551"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/112968"],["dc.language.iso","en"],["dc.notes.intern","DOI-Import GROB-478"],["dc.publisher","BioMed Central"],["dc.relation.eissn","1758-9193"],["dc.rights.holder","The Author(s)"],["dc.subject","Alzheimer’s disease"],["dc.subject","Deep learning"],["dc.subject","Convolutional neural network"],["dc.subject","MRI"],["dc.subject","Layer-wise relevance propagation"],["dc.title","Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease"],["dc.type","journal_article"],["dc.type.internalPublication","yes"],["dspace.entity.type","Publication"]]