White Matter Hyperintensities in Alzheimer’s Disease: A Lesion Probability Mapping Study

Damulina, Anna; Pirpamer, Lukas; Seiler, Stephan; Benke, Thomas; Dal‐Bianco, Peter; Ransmayr, Gerhard; Struhal, Walter; Hofer, Edith; Langkammer, Christian; Duering, Marco; Fazekas, Franz; Schmidt, Reinhold

doi:10.3233/jad-180982

Cited by 33 publications

(30 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…White matter hyperintensities (WMH) are commonly seen in brain MRI in older people and beside their underlying heterogeneous histopathology, they represent radiological correlates of cognitive and functional impairment (Prins and Scheltens, 2015). In a previous study, we found WMHs preferentially in a bilateral periventricular location, partly overlapping with the regions identified here by the Graz + -based models (Damulina et al, 2019). Furthermore, other plausible contributors are increased brain iron deposition in the deep gray matter (basal ganglia) of AD patients (Damulina et al, 2020) or cumulative gadolinium deposition of macrocyclic contrast agents (Kanda et al, 2014).…”

Section: Discussionsupporting

confidence: 86%

Interpretable Brain Disease Classification and Relevance-Guided Deep Learning

Tinauer

Heber

Pirpamer

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Deep neural networks are increasingly used for neurological disease classification by MRI, but the networks' decisions are not easily interpretable by humans. Heat mapping by deep Taylor decomposition revealed that (potentially misleading) image features even outside of the brain tissue are crucial for the classifier's decision. We propose a regularization technique to train convolutional neural network (CNN) classifiers utilizing relevance-guided heat maps calculated online during training. The method was applied using T1-weighted MR images from 128 subjects with Alzheimer's disease (mean age=71.9+-8.5 years) and 290 control subjects (mean age=71.3+-6.4 years). The developed relevance-guided framework achieves higher classification accuracies than conventional CNNs but more importantly, it relies on less but more relevant and physiological plausible voxels within brain tissue. Additionally, preprocessing effects from skull stripping and registration are mitigated, rendering this practically useful in deep learning neuroimaging studies. Understanding the decision mechanisms underlying CNNs, these results challenge the notion that unprocessed T1-weighted brain MR images in standard CNNs yield higher classification accuracy in Alzheimer's disease than solely atrophy.

show abstract

Section: Discussionsupporting

confidence: 86%

Interpretable Brain Disease Classification and Relevance-Guided Deep Learning

Tinauer

Heber

Pirpamer

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…1. From the initial search, 162 articles were retrieved with 38 of them being analyzed 19,21–57 . All included studies were prospective; five had an intraindividual study design with two 21,24,31,40 or three study groups 19 that were examined separately.…”

Section: Resultsmentioning

confidence: 99%

White Matter Hyperintensities Quantification in Healthy Adults: A Systematic Review and Meta‐Analysis

Melazzini

Vitali

Olivieri

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Although white matter hyperintensities (WMH) volumetric assessment is now customary in research studies, inconsistent WMH measures among homogenous populations may prevent the clinical usability of this biomarker. Purpose To determine whether a point estimate and reference standard for WMH volume in the healthy aging population could be determined. Study Type Systematic review and meta‐analysis. Population In all, 9716 adult subjects from 38 studies reporting WMH volume were retrieved following a systematic search on EMBASE. Field Strength/Sequence 1.0T, 1.5T, or 3.0T/fluid‐attenuated inversion recovery (FLAIR) and/or proton density/T2‐weighted fast spin echo sequences or gradient echo T1‐weighted sequences. Assessment After a literature search, sample size, demographics, magnetic field strength, MRI sequences, level of automation in WMH assessment, study population, and WMH volume were extracted. Statistical Tests The pooled WMH volume with 95% confidence interval (CI) was calculated using the random‐effect model. The I2 statistic was calculated as a measure of heterogeneity across studies. Meta‐regression analysis of WMH volume on age was performed. Results Of the 38 studies analyzed, 17 reported WMH volume as the mean and standard deviation (SD) and were included in the meta‐analysis. Mean and SD of age was 66.11 ± 10.92 years (percentage of men 50.45% ± 21.48%). Heterogeneity was very high (I2 = 99%). The pooled WMH volume was 4.70 cm3 (95% CI: 3.88–5.53 cm3). At meta‐regression analysis, WMH volume was positively associated with subjects' age (β = 0.358 cm3 per year, P < 0.05, R2 = 0.27). Data Conclusion The lack of standardization in the definition of WMH together with the high technical variability in assessment may explain a large component of the observed heterogeneity. Currently, volumes of WMH in healthy subjects are not comparable between studies and an estimate and reference interval could not be determined. Level of Evidence 1 Technical Efficacy Stage 1

show abstract

“…They are associated with vascular risk factors (VRF), for example, hypertension or diabetes, 1 and with worse cognitive performance, particularly executive functions and processing speed. [2][3][4] In patients with Alzheimer's disease (AD), WMH volume appears to be larger than in cognitively unimpaired older adults, 5 particularly in periventricular [6][7][8] and posterior regions. These include parietooccipital regions 9,10 and the splenium of the corpus callosum (S-CC).…”

Section: Introductionmentioning

confidence: 99%

White matter hyperintensity topography in Alzheimer's disease and links to cognition

Garnier‐Crussard

Bougacha

Wirth

et al. 2021

Alzheimer's & Dementia

101

View full text Add to dashboard Cite

Introduction White matter hyperintensities (WMH) are often described in Alzheimer's disease (AD), but their topography and specific relationships with cognition remain unclear. Methods Regional WMH were estimated in 54 cognitively impaired amyloid beta–positive AD (Aβpos‐AD), compared to 40 cognitively unimpaired amyloid beta–negative older controls (Aβneg‐controls) matched for vascular risk factors. The cross‐sectional association between regional WMH volume and cognition was assessed within each group, controlling for cerebral amyloid burden, global cortical atrophy, and hippocampal atrophy. Results WMH volume was larger in Aβpos‐AD compared to Aβneg‐controls in all regions, with the greatest changes in the splenium of the corpus callosum (S‐CC). In Aβpos‐AD patients, larger total and regional WMH volume, especially in the S‐CC, was strongly associated with decreased cognition. Discussion WMH specifically contribute to lower cognition in AD, independently from amyloid deposition and atrophy. This study emphasizes the clinical relevance of WMH in AD, especially posterior WMH, and most notably S‐CC WMH.

show abstract

White Matter Hyperintensities in Alzheimer’s Disease: A Lesion Probability Mapping Study

Cited by 33 publications

References 34 publications

Interpretable Brain Disease Classification and Relevance-Guided Deep Learning

Interpretable Brain Disease Classification and Relevance-Guided Deep Learning

White Matter Hyperintensities Quantification in Healthy Adults: A Systematic Review and Meta‐Analysis

White matter hyperintensity topography in Alzheimer's disease and links to cognition

Contact Info

Product

Resources

About