Dataset Information

Deep learning reveals 3D atherosclerotic plaque distribution and composition.

ABSTRACT: Complications of atherosclerosis are the leading cause of morbidity and mortality worldwide. Various genetically modified mouse models are used to investigate disease trajectory with classical histology, currently the preferred methodology to elucidate plaque composition. Here, we show the strength of light-sheet fluorescence microscopy combined with deep learning image analysis for characterising and quantifying plaque burden and composition in whole aorta specimens. 3D imaging is a non-destructive method that requires minimal ex vivo handling and can be up-scaled to large sample sizes. Combined with deep learning, atherosclerotic plaque in mice can be identified without any ex vivo staining due to the autofluorescent nature of the tissue. The aorta and its branches can subsequently be segmented to determine how anatomical position affects plaque composition and progression. Here, we find the highest plaque accumulation in the aortic arch and brachiocephalic artery. Simultaneously, aortas can be stained for markers of interest (for example the pan immune cell marker CD45) and quantified. In ApoE-/- mice we observe that levels of CD45 reach a plateau after which increases in plaque volume no longer correlate to immune cell infiltration. All underlying code is made publicly available to ease adaption of the method.

SUBMITTER: Jurtz VI

PROVIDER: S-EPMC7726562 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning reveals 3D atherosclerotic plaque distribution and composition.

Jurtz Vanessa Isabell VI Skovbjerg Grethe G Salinas Casper Gravesen CG Roostalu Urmas U Pedersen Louise L Hecksher-Sørensen Jacob J Rolin Bidda B Nyberg Michael M van de Bunt Martijn M Ingvorsen Camilla C

Scientific reports 20201209 1

Complications of atherosclerosis are the leading cause of morbidity and mortality worldwide. Various genetically modified mouse models are used to investigate disease trajectory with classical histology, currently the preferred methodology to elucidate plaque composition. Here, we show the strength of light-sheet fluorescence microscopy combined with deep learning image analysis for characterising and quantifying plaque burden and composition in whole aorta specimens. 3D imaging is a non-destruc ...[more]

PMID: 33299076

Similar Datasets

Project description:ImportanceThe density of atherosclerotic plaque forms the basis for categorizing calcified and noncalcified morphology of plaques.ObjectiveTo assess whether alterations in plaque across a range of density measurements provide a more detailed understanding of atherosclerotic disease progression.Design, setting, and participantsThis cohort study enrolled 857 patients who underwent serial coronary computed tomography angiography 2 or more years apart and had quantitative measurements of coronary plaques throughout the entire coronary artery tree. The study was conducted from 2013 to 2016 at 13 sites in 7 countries.Main outcomes and measuresThe main outcome was progression of plaque composition of individual coronary plaques. Six plaque composition types were defined on a voxel-level basis according to the plaque attenuation (expressed in Hounsfield units [HU]): low attenuation (-30 to 75 HU), fibro-fatty (76-130 HU), fibrous (131-350 HU), low-density calcium (351-700 HU), high-density calcium (701-1000 HU), and 1K (>1000 HU). The progression rates of these 6 compositional plaque types were evaluated according to the interaction between statin use and baseline plaque volume, adjusted for risk factors and time interval between scans. Plaque progression was also examined based on baseline calcium density. Analysis was performed among lesions matched at baseline and follow-up. Data analyses were conducted from August 2019 through March 2020.ResultsIn total, 2458 coronary lesions in 857 patients (mean [SD] age, 62.1 [8.7] years; 540 [63.0%] men; 548 [63.9%] received statin therapy) were included. Untreated coronary lesions increased in volume over time for all 6 compositional types. Statin therapy was associated with volume decreases in low-attenuation plaque (β, -0.02; 95% CI, -0.03 to -0.01; P = .001) and fibro-fatty plaque (β, -0.03; 95% CI, -0.04 to -0.02; P < .001) and greater progression of high-density calcium plaque (β, 0.02; 95% CI, 0.01-0.03; P < .001) and 1K plaque (β, 0.02; 95% CI, 0.01-0.03; P < .001). When analyses were restricted to lesions without low-attenuation plaque or fibro-fatty plaque at baseline, statin therapy was not associated with a change in overall calcified plaque volume (β, -0.03; 95% CI, -0.08 to 0.02; P = .24) but was associated with a transformation toward more dense calcium. Interaction analysis between baseline plaque volume and calcium density showed that more dense coronary calcium was associated with less plaque progression.Conclusions and relevanceThe results suggest an association of statin use with greater rates of transformation of coronary atherosclerosis toward high-density calcium. A pattern of slower overall plaque progression was observed with increasing density. All findings support the concept of reduced atherosclerotic risk with increased densification of calcium.

Project description:Total and regional body composition are strongly correlated with metabolic syndrome and have been estimated non-invasively from 3D optical scans using linear parameterizations of body shape and linear regression models. Prior works produced accurate and precise predictions on many, but not all, body composition targets relative to the reference dual X-Ray absorptiometry (DXA) measurement. Here, we report the effects of replacing linear models with nonlinear parameterization and regression models on the precision and accuracy of body composition estimation in a novel application of deep 3D convolutional graph networks to human body composition modeling. We assembled an ensemble dataset of 4286 topologically standardized 3D optical scans from four different human body shape databases, DFAUST, CAESAR, Shape Up! Adults, and Shape Up! Kids and trained a parameterized shape model using a graph convolutional 3D autoencoder (3DAE) in lieu of linear PCA. We trained a nonlinear Gaussian process regression (GPR) on the 3DAE parameter space to predict body composition via correlations to paired DXA reference measurements from the Shape Up! scan subset. We tested our model on a set of 424 randomly withheld test meshes and compared the effects of nonlinear computation against prior linear models. Nonlinear GPR produced up to 20% reduction in prediction error and up to 30% increase in precision over linear regression for both sexes in 10 tested body composition variables. Deep shape features produced 6-8% reduction in prediction error over linear PCA features for males only and a 4-14% reduction in precision error for both sexes. Our best performing nonlinear model predicting body composition from deep features outperformed prior work using linear methods on all tested body composition prediction metrics in both precision and accuracy. All coefficients of determination (R2) for all predicted variables were above 0.86. We show that GPR is a more precise and accurate method for modeling body composition mappings from body shape features than linear regression. Deep 3D features learned by a graph convolutional autoencoder only improved male body composition accuracy but improved precision in both sexes. Our work achieved lower estimation RMSEs than all previous work on 10 metrics of body composition.

Dataset Information

Deep learning reveals 3D atherosclerotic plaque distribution and composition.

Publications

Deep learning reveals 3D atherosclerotic plaque distribution and composition.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets