Metabolic brain pattern in dementia with Lewy bodies: Relationship to Alzheimer’s disease topography

Perovnik, Matej; Tomše, Petra; Jamšek, Jan; Tang, Chris C.; Eidelberg, David; Trošt, Maja

doi:10.1016/j.nicl.2022.103080

Cited by 14 publications

(21 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the ROI-based classifier needed 40 features to reach the maximal classification accuracy, we have also shown that similar performance to visual reading can be made using only the expression of four characteristic metabolic brain patterns. In addition, previous studies have shown that pattern expression scores correlate with measurements of cognitive impairment in AD and DLB ( Perovnik et al, 2022a , b ), and higher expression values are predictive of conversion from MCI to AD ( Blazhenets et al, 2019 ). In contrast to the ROI-based approach, pattern expression values can be more easily interpreted by a physician who would want to use the multi-class SVM as a supportive tool to aid the differential diagnosis.…”

Section: Discussionmentioning

confidence: 91%

“…Patients with FTD were diagnosed with possible FTD according to the International Behavioral Variant FTD Consortium criteria ( Rascovsky et al, 2011 ) and had their diagnosis confirmed at a follow-up visit conducted at least 12 months after the onset of symptoms. AD and DLB cohorts and their FDG PET scans included in this study have appeared previously ( Perovnik et al, 2022a , b ). NCs completed clinical, neuropsychological, and FDG PET brain imaging for purposes of an earlier research project ( Tomše et al, 2017 ).…”

Section: Methodsmentioning

confidence: 99%

“…We calculated the expression of previously identified and validated specific metabolic patterns related to AD ( Perovnik et al, 2022a ), DLB ( Perovnik et al, 2022b ), and FTD ( Rus et al, 2021 ). We also calculated expression levels for the normal metabolic DMN expression as described previously ( Spetsieris et al, 2015 ).…”

Section: Methodsmentioning

confidence: 99%

“…Multivariate analysis approaches, such as scaled subprofile model/principal component analysis (SSM/PCA) applied to FDG PET images, can reveal characteristic metabolic brain patterns, which expressions can be prospectively quantified on a single case basis ( Spetsieris and Eidelberg, 2011 ). AD-related pattern (ADRP; Perovnik et al, 2022a ), DLB-related pattern (DLBRP; Perovnik et al, 2022b ) and FTD-related pattern (FTDRP; Rus et al, 2021 ) have been identified and validated in different clinical cohorts in the past. Similarly, a pattern of default mode network (DMN)—a dominant resting-state network in healthy individuals, which is affected also in the pathogenesis of neurodegenerative dementias—has been characterized with FDG PET ( Spetsieris et al, 2015 ).…”

Section: Introductionmentioning

confidence: 99%

“…Similarly, a pattern of default mode network (DMN)—a dominant resting-state network in healthy individuals, which is affected also in the pathogenesis of neurodegenerative dementias—has been characterized with FDG PET ( Spetsieris et al, 2015 ). Based on the expression of metabolic brain patterns, we can very accurately distinguish between patients with dementia and normal controls (NCs; Perovnik et al, 2022a , b ). However, it was also observed that the information of a single pattern’s expression score may not be sufficient to distinguish between different neurodegenerative dementias accurately ( Katako et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automated differential diagnosis of dementia syndromes using FDG PET and machine learning

Perovnik

Nguyen

et al. 2022

Front. Aging Neurosci.

Self Cite

View full text Add to dashboard Cite

BackgroundMetabolic brain imaging with 2-[18F]fluoro-2-deoxy-D-glucose positron emission tomography (FDG PET) is a supportive diagnostic and differential diagnostic tool for neurodegenerative dementias. In the clinic, scans are usually visually interpreted. However, computer-aided approaches can improve diagnostic accuracy. We aimed to build two machine learning classifiers, based on two sets of FDG PET-derived features, for differential diagnosis of common dementia syndromes.MethodsWe analyzed FDG PET scans from three dementia cohorts [63 dementia due to Alzheimer’s disease (AD), 79 dementia with Lewy bodies (DLB) and 23 frontotemporal dementia (FTD)], and 41 normal controls (NCs). Patients’ clinical diagnosis at follow-up (25 ± 20 months after scanning) or cerebrospinal fluid biomarkers for Alzheimer’s disease was considered a gold standard. FDG PET scans were first visually evaluated. Scans were pre-processed, and two sets of features extracted: (1) the expressions of previously identified metabolic brain patterns, and (2) the mean uptake value in 95 regions of interest (ROIs). Two multi-class support vector machine (SVM) classifiers were tested and their diagnostic performance assessed and compared to visual reading. Class-specific regional feature importance was assessed with Shapley Additive Explanations.ResultsPattern- and ROI-based classifier achieved higher overall accuracy than expert readers (78% and 80% respectively, vs. 71%). Both SVM classifiers performed similarly to one another and to expert readers in AD (F1 = 0.74, 0.78, and 0.78) and DLB (F1 = 0.81, 0.81, and 0.78). SVM classifiers outperformed expert readers in FTD (F1 = 0.87, 0.83, and 0.63), but not in NC (F1 = 0.71, 0.75, and 0.92). Visualization of the SVM model showed bilateral temporal cortices and cerebellum to be the most important features for AD; occipital cortices, hippocampi and parahippocampi, amygdala, and middle temporal lobes for DLB; bilateral frontal cortices, middle and anterior cingulum for FTD; and bilateral angular gyri, pons, and vermis for NC.ConclusionMulti-class SVM classifiers based on the expression of characteristic metabolic brain patterns or ROI glucose uptake, performed better than experts in the differential diagnosis of common dementias using FDG PET scans. Experts performed better in the recognition of normal scans and a combined approach may yield optimal results in the clinical setting.

show abstract

Section: Discussionmentioning

confidence: 91%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automated differential diagnosis of dementia syndromes using FDG PET and machine learning

Perovnik

Nguyen

et al. 2022

Front. Aging Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

A Network Imaging Biomarker of X‐Linked Dystonia‐Parkinsonism

Niethammer

Tang

Jamora

et al. 2023

Annals of Neurology

Self Cite

View full text Add to dashboard Cite

ObjectiveThe purpose of this study was to characterize a metabolic brain network associated with X‐linked dystonia‐parkinsonism (XDP).MethodsThirty right‐handed Filipino men with XDP (age = 44.4 ± 8.5 years) and 30 XDP‐causing mutation negative healthy men from the same population (age = 37.4 ± 10.5 years) underwent [18F]‐fluorodeoxyglucose positron emission tomography. Scans were analyzed using spatial covariance mapping to identify a significant XDP‐related metabolic pattern (XDPRP). Patients were rated clinically at the time of imaging according to the XDP‐Movement Disorder Society of the Philippines (MDSP) scale.ResultsWe identified a significant XDPRP topography from 15 randomly selected subjects with XDP and 15 control subjects. This pattern was characterized by bilateral metabolic reductions in caudate/putamen, frontal operculum, and cingulate cortex, with relative increases in the bilateral somatosensory cortex and cerebellar vermis. Age‐corrected expression of XDPRP was significantly elevated (p < 0.0001) in XDP compared to controls in the derivation set and in the remaining 15 patients (testing set). We validated the XDPRP topography by identifying a similar pattern in the original testing set (r = 0.90, p < 0.0001; voxel‐wise correlation between both patterns). Significant correlations between XDPRP expression and clinical ratings for parkinsonism—but not dystonia—were observed in both XDP groups. Further network analysis revealed abnormalities of information transfer through the XDPRP space, with loss of normal connectivity and gain of abnormal functional connections linking network nodes with outside brain regions.InterpretationXDP is associated with a characteristic metabolic network associated with abnormal functional connectivity among the basal ganglia, thalamus, motor regions, and cerebellum. Clinical signs may relate to faulty information transfer through the network to outside brain regions. ANN NEUROL 2023

show abstract

Disease specific and nonspecific metabolic brain networks in behavioral variant of frontotemporal dementia

Rus

Perovnik

et al. 2022

Human Brain Mapping

Self Cite

View full text Add to dashboard Cite

Behavioral variant of frontotemporal dementia (bvFTD) is common among young‐onset dementia patients. While bvFTD‐specific multivariate metabolic brain pattern (bFDRP) has been identified previously, little is known about its temporal evolution, internal structure, effect of atrophy, and its relationship with nonspecific resting‐state networks such as default mode network (DMN). In this multicenter study, we explored FDG‐PET brain scans of 111 bvFTD, 26 Alzheimer's disease, 16 Creutzfeldt‐Jakob's disease, 24 semantic variant primary progressive aphasia (PPA), 18 nonfluent variant PPA and 77 healthy control subjects (HC) from Slovenia, USA, and Germany. bFDRP was identified in a cohort of 20 bvFTD patients and age‐matched HC using scaled subprofile model/principle component analysis and validated in three independent cohorts. It was characterized by hypometabolism in frontal cortex, insula, anterior/middle cingulate, caudate, thalamus, and temporal poles. Its expression in bvFTD patients was significantly higher compared to HC and other dementia syndromes ( p < .0004), correlated with cognitive decline ( p = .0001), and increased over time in longitudinal cohort ( p = .0007). Analysis of internal network organization by graph‐theory methods revealed prominent network disruption in bvFTD patients. We have further found a specific atrophy‐related pattern grossly corresponding to bFDRP; however, its contribution to the metabolic pattern was minimal. Finally, despite the overlap between bFDRP and FDG‐PET‐derived DMN, we demonstrated a predominant role of the specific bFDRP. Taken together, we validated the bFDRP network as a diagnostic/prognostic biomarker specific for bvFTD, provided a unique insight into its highly reproducible internal structure, and proved that bFDRP is unaffected by structural atrophy and independent of normal resting state networks loss.

show abstract

Metabolic brain pattern in dementia with Lewy bodies: Relationship to Alzheimer’s disease topography

Cited by 14 publications

References 61 publications

Automated differential diagnosis of dementia syndromes using FDG PET and machine learning

Automated differential diagnosis of dementia syndromes using FDG PET and machine learning

A Network Imaging Biomarker of X‐Linked Dystonia‐Parkinsonism

Disease specific and nonspecific metabolic brain networks in behavioral variant of frontotemporal dementia

Contact Info

Product

Resources

About