Image-derived Phenotypes Research Articles

Exploring causal effects and potential mediating mechanisms of genetically linked environmental senses with intracerebral hemorrhage.

The occurrence mechanism of intracerebral hemorrhage remains unclear. Several recent studies have highlighted the close relationship between environmental senses and intracerebral hemorrhage, but the mechanisms of causal mediation are inconclusive. We aimed to investigate the causal relationships and potential mechanisms between environmental senses and intracerebral hemorrhage. Multiple Mendelian randomization methods were used to identify a causal relationship between environmental senses and intracerebral hemorrhage. Gut microbiota and brain imaging phenotypes were used to find possible mediators. Enrichment and molecular interaction analyses were used to identify potential mediators and molecular targets. No causal relationship between temperature and visual perception with intracerebral hemorrhage was found, whereas long-term noise was identified as a risk factor for intracerebral hemorrhage (OR 2.95, 95% CI: 1.25 to 6.93, PIVW = 0.01). The gut microbiota belonging to the class Negativicutes and the order Selenomonadales and the brain image-derived phenotypes ICA100 node 54, edge 803, edge 1149, and edge 1323 played mediating roles. "Regulation of signaling and function in synaptic organization" is the primary biological pathway of noise-induced intracerebral hemorrhage, and ARHGAP22 may be the critical gene. This study emphasized the importance of environmental noise in the prevention, disease management, and underlying biological mechanisms of intracerebral hemorrhage.

Multi-Omics Integration Analysis Pinpoint Proteins Influencing Brain Structure and Function: Toward Drug Targets and Neuroimaging Biomarkers for Neuropsychiatric Disorders.

Integrating protein quantitative trait loci (pQTL) data and summary statistics from genome-wide association studies (GWAS) of brain image-derived phenotypes (IDPs) can benefit in identifying IDP-related proteins. Here, we developed a systematic omics-integration analytic framework by sequentially using proteome-wide association study (PWAS), Mendelian randomization (MR), and colocalization (COLOC) analyses to identify the potentially causal brain and plasma proteins for IDPs, followed by pleiotropy analysis, mediation analysis, and drug exploration analysis to investigate potential mediation pathways of pleiotropic proteins to neuropsychiatric disorders (NDs) as well as candidate drug targets. A total of 201 plasma proteins and 398 brain proteins were significantly associated with IDPs from PWAS analysis. Subsequent MR and COLOC analyses further identified 313 potentially causal IDP-related proteins, which were significantly enriched in neural-related phenotypes, among which 91 were further identified as pleiotropic proteins associated with both IDPs and NDs, including EGFR, TMEM106B, GPT, and HLA-B. Drug prioritization analysis showed that 6.33% of unique pleiotropic proteins had drug targets or interactions with medications for NDs. Nine potential mediation pathways were identified to illustrate the mediating roles of the IDPs in the causal effect of the pleiotropic proteins on NDs, including the indirect effect of TMEM106B on Alzheimer's disease (AD) risk via radial diffusivity (RD) of the posterior limb of the internal capsule (PLIC), with the mediation proportion being 11.18%, and the indirect effect of EGFR on AD through RD of PLIC, RD of splenium of corpus callosum (SCC), and fractional anisotropy (FA) of SCC, with the mediation proportion being 18.99%, 22.79%, and 19.91%, respectively. These findings provide novel insights into pathogenesis, drug targets, and neuroimaging biomarkers of NDs.

Causal relationships involving brain imaging-derived phenotypes based on UKB imaging cohort: a review of Mendelian randomization studies.

The UK Biobank (UKB) has the largest adult brain imaging dataset, which encompasses over 40,000 participants. A significant number of Mendelian randomization (MR) studies based on UKB neuroimaging data have been published to validate potential causal relationships identified in observational studies. Relevant articles published before December 2023 were identified following the PRISMA protocol. Included studies (n = 34) revealed that there were causal relationships between various lifestyles, diseases, biomarkers, and brain image-derived phenotypes (BIDPs). In terms of lifestyle habits and environmental factors, there were causal relationships between alcohol consumption, tea intake, coffee consumption, smoking, educational attainment, and certain BIDPs. Additionally, some BIDPs could serve as mediators between leisure/physical inactivity and major depressive disorder. Regarding diseases, BIDPs have been found to have causal relationships not only with Alzheimer's disease, stroke, psychiatric disorders, and migraine, but also with cardiovascular diseases, diabetes, poor oral health, osteoporosis, and ankle sprain. In addition, there were causal relationships between certain biological markers and BIDPs, such as blood pressure, LDL-C, IL-6, telomere length, and more.

Structural correlations between brain magnetic resonance image-derived phenotypes and retinal neuroanatomy.

The eye is a well-established model of brain structure and function, yet region-specific structural correlations between the retina and the brain remain underexplored. Therefore, we aim to explore and describe the relationships between the retinal layer thicknesses and brain magnetic resonance image (MRI)-derived phenotypes in UK Biobank. Participants with both quality-controlled optical coherence tomography (OCT) and brain MRI were included in this study. Retinal sublayer thicknesses and total macular thickness were derived from OCT scans. Brain image-derived phenotypes (IDPs) of 153 cortical and subcortical regions were processed from MRI scans. We utilized multivariable linear regression models to examine the association between retinal thickness and brain regional volumes. All analyses were corrected for multiple testing and adjusted for confounders. Data from 6446 participants were included in this study. We identified significant associations between volumetric brain MRI measures of subregions in the occipital lobe (intracalcarine cortex), parietal lobe (postcentral gyrus), cerebellum (lobules VI, VIIb, VIIIa, VIIIb, and IX), and deep brain structures (thalamus, hippocampus, caudate, putamen, pallidum, and accumbens) and the thickness of the innermost retinal sublayers and total macular thickness (all p < 3.3 × 10-5). We did not observe statistically significant associations between brain IDPs and the thickness of the outer retinal sublayers. Thinner inner and total retinal thicknesses are associated with smaller volumes of specific brain regions. Notably, these relationships extend beyond anatomically established retina-brain connections.

Unsupervised deep representation learning enables phenotype discovery for genetic association studies of brain imaging

Understanding the genetic architecture of brain structure is challenging, partly due to difficulties in designing robust, non-biased descriptors of brain morphology. Until recently, brain measures for genome-wide association studies (GWAS) consisted of traditionally expert-defined or software-derived image-derived phenotypes (IDPs) that are often based on theoretical preconceptions or computed from limited amounts of data. Here, we present an approach to derive brain imaging phenotypes using unsupervised deep representation learning. We train a 3-D convolutional autoencoder model with reconstruction loss on 6130 UK Biobank (UKBB) participants’ T1 or T2-FLAIR (T2) brain MRIs to create a 128-dimensional representation known as Unsupervised Deep learning derived Imaging Phenotypes (UDIPs). GWAS of these UDIPs in held-out UKBB subjects (n = 22,880 discovery and n = 12,359/11,265 replication cohorts for T1/T2) identified 9457 significant SNPs organized into 97 independent genetic loci of which 60 loci were replicated. Twenty-six loci were not reported in earlier T1 and T2 IDP-based UK Biobank GWAS. We developed a perturbation-based decoder interpretation approach to show that these loci are associated with UDIPs mapped to multiple relevant brain regions. Our results established unsupervised deep learning can derive robust, unbiased, heritable, and interpretable brain imaging phenotypes.

A comprehensive analysis of APOE genotype effects on human brain structure in the UK Biobank

Alzheimer’s disease (AD) risk is increased in carriers of the apolipoprotein E (APOE) ε4 allele and decreased in ε2 allele carriers compared with the ε3ε3 genotype. The aim of this study was to determine whether: the APOE genotype affects brain grey (GM) or white matter (WM) structure; and if differences exist, the age when they become apparent and whether there are differential effects by sex. We used cross-sectional magnetic resonance imaging data from ~43,000 (28,494 after pre-processing) white British cognitively healthy participants (7,446 APOE ε4 carriers) aged 45–80 years from the UK Biobank cohort and investigated image-derived phenotypes (IDPs). We observed no statistically significant effects of APOE genotype on GM structure volumes or median T2* in subcortical structures, a measure related to iron content. The volume of white matter hyperintensities differed significantly between APOE genotype groups with higher volumes in APOE ε4ε4 (effect size 0.14 standard deviations [SD]) and ε3ε4 carriers (effect size 0.04 SD) but no differences in ε2 carriers compared with ε3ε3 carriers. WM integrity measures in the dorsal (mean diffusivity [MD]) and ventral cingulum (MD and intracellular volume fraction), posterior thalamic radiation (MD and isotropic volume fraction) and sagittal stratum (MD) indicated lower integrity in APOE ε4ε4 carriers (effect sizes around 0.2–0.3 SD) and ε3ε4 (effect sizes around 0.05 SD) carriers but no differences in ε2 carriers compared with the APOE ε3ε3 genotype. Effects did not differ between men and women. APOE ε4 homozygotes had lower WM integrity specifically at older ages with a steeper decline of WM integrity from the age of 60 that corresponds to around 5 years greater “brain age”. APOE genotype affects various white matters measures, which might be indicative of preclinical AD processes. This hypothesis can be assessed in future when clinical outcomes become available.

Unsupervised ensemble-based phenotyping enhances discoverability of genes related to left-ventricular morphology

Recent genome-wide association studies have successfully identified associations between genetic variants and simple cardiac morphological parameters derived from cardiac magnetic resonance images. However, the emergence of large databases, including genetic data linked to cardiac magnetic resonance facilitates the investigation of more nuanced patterns of cardiac shape variability than those studied so far. Here we propose a framework for gene discovery coined unsupervised phenotype ensembles. The unsupervised phenotype ensemble builds a redundant yet highly expressive representation by pooling a set of phenotypes learnt in an unsupervised manner, using deep learning models trained with different hyperparameters. These phenotypes are then analysed via genome-wide association studies, retaining only highly confident and stable associations across the ensemble. We applied our approach to the UK Biobank database to extract geometric features of the left ventricle from image-derived three-dimensional meshes. We demonstrate that our approach greatly improves the discoverability of genes that influence left ventricle shape, identifying 49 loci with study-wide significance and 25 with suggestive significance. We argue that our approach would enable more extensive discovery of gene associations with image-derived phenotypes for other organs or image modalities.

Brain imaging derived phenotypes: a biomarker for the onset of inflammatory bowel disease and a potential mediator of mental complications.

Inflammatory bowel disease (IBD), mainly categorized into Crohn's disease (CD) and ulcerative colitis (UC), is a chronic relapsing gastrointestinal disorder that significantly impairs patients' quality of life. IBD patients often experience comorbidities such as anxiety and depression, and the underlying mechanisms and treatment strategies remain areas of investigation. We conducted a Mendelian randomization(MR) analysis utilizing brain image derived phenotypes (IDP) from the UK Biobank database to investigate the causal relationships between IBD and alterations in brain structural morphology and connectivity of neural tracts. This study aimed to identify biological evidence linking IBD to psychiatric disorders such as anxiety and depression. Specifically, the volume of grey matter in the Left Frontal Orbital Cortex exhibited a negative association with the onset of Crohn's disease (odds ratio (OR) [95% confidence interval (CI)]: 0.315[0.180~0.551], adjusted P=0.001), while the volume of the superior frontal cortex in the right hemisphere showed a positive correlation with the development of Ulcerative colitis (OR [95% CI]: 2.285[1.793~2.911], adjusted P<0.001), and the volume of lateral occipital cortex in the left hemisphere demonstrated a positive relationship with Crohn's disease onset (OR [95% CI]: 1.709[1.671~1.747], adjusted P<0.001). In the context of reverse causality, the onset of UC or CD has led to alterations in imaging derived phenotypes associated with five disorders (anxiety, depression, schizophrenia, bipolar disorder, pain) and three functions (memory, emotion, language). Our study has demonstrated a causal relationship between IBD and IDPs. IDPs may serve as potential biomarkers for the progression of IBD and as predictive intermediaries for the development of neurological diseases in IBD patients.

Precision MRI phenotyping of muscle volume and quality at a population scale.

Introduction: Magnetic resonance imaging (MRI) enables direct measurements of muscle volume and quality, allowing for an in-depth understanding of their associations with anthropometric traits, and health conditions. However, it is unclear which muscle volume measurements: total muscle volume, regional measurements, measurements of muscle quality: intermuscular adipose tissue (IMAT) or proton density fat fraction (PDFF), are most informative and associate with relevant health conditions such as dynapenia and frailty. Methods: We have measured image-derived phenotypes (IDPs) including total and regional muscle volumes and measures of muscle quality, derived from the neck-to-knee Dixon images in 44,520 UK Biobank participants. We further segmented paraspinal muscle from 2D quantitative MRI to quantify muscle PDFF and iron concentration. We defined dynapenia based on grip strength below sex-specific cut-off points and frailty based on five criteria (weight loss, exhaustion, grip strength, low physical activity and slow walking pace). We used logistic regression to investigate the association between muscle volume and quality measurements and dynapenia and frailty. Results: Muscle volumes were significantly higher in male compared with female participants, even after correcting for height while, IMAT (corrected for muscle volume) and paraspinal muscle PDFF were significantly higher in female compared with male participants. From the overall cohort, 7.6% (N = 3,261) were identified with dynapenia, and 1.1% (N = 455) with frailty. Dynapenia and frailty were positively associated with age and negatively associated with physical activity levels. Additionally, reduced muscle volume and quality measurements were associated with both dynapenia and frailty. In dynapenia, muscle volume IDPs were most informative, particularly total muscle exhibiting odds ratios (OR) of 0.392, while for frailty, muscle quality was found to be most informative, in particular thigh IMAT volume indexed to height squared (OR = 1.396), both with p-values below the Bonferroni-corrected threshold (). Conclusion: Our fully automated method enables the quantification of muscle volumes and quality suitable for large population-based studies. For dynapenia, muscle volumes particularly those including greater body coverage such as total muscle are the most informative, whilst, for frailty, markers of muscle quality were the most informative IDPs. These results suggest that different measurements may have varying diagnostic values for different health conditions.

Leukocyte Telomere Length and Cardiac Structure and Function: A Mendelian Randomization Study.

Existing research demonstrates the association of shorter leukocyte telomere length with increased risk of age-related health outcomes including cardiovascular diseases. However, the direct causality of these relationships has not been definitively established. Cardiovascular aging at an organ level may be captured using image-derived phenotypes of cardiac anatomy and function. In the current study, we use 2-sample Mendelian randomization to assess the causal link between leukocyte telomere length and 54 cardiac magnetic resonance imaging measures representing structure and function across the 4 cardiac chambers. Genetically predicted shorter leukocyte telomere length was causally linked to smaller ventricular cavity sizes including left ventricular end-systolic volume, left ventricular end-diastolic volume, lower left ventricular mass, and pulmonary artery. The association with left ventricular mass (β =0.217, Pfalse discovery rate=0.016) remained significant after multiple testing adjustment, whereas other associations were attenuated. Our findings support a causal role for shorter leukocyte telomere length and faster cardiac aging, with the most prominent relationship with left ventricular mass.

A statistical method for image-mediated association studies discovers genes and pathways associated with four brain disorders

Brain imaging and genomics are critical tools enabling characterization of the genetic basis of brain disorders. However, imaging large cohorts is expensive and may be unavailable for legacy datasets used for genome-wide association studies (GWASs). Using an integrated feature selection/aggregation model, we developed an image-mediated association study (IMAS), which utilizes borrowed imaging/genomics data to conduct association mapping in legacy GWAS cohorts. By leveraging the UK Biobank image-derived phenotypes (IDPs), the IMAS discovered genetic bases underlying four neuropsychiatric disorders and verified them by analyzing annotations, pathways, and expression quantitative trait loci (eQTLs). A cerebellar-mediated mechanism was identified to be common to the four disorders. Simulations show that, if the goal is identifying genetic risk, our IMAS is more powerful than a hypothetical protocol in which the imaging results were available in the GWAS dataset. This implies the feasibility of reanalyzing legacy GWAS datasets without conducting additional imaging, yielding cost savings for integrated analysis of genetics and imaging.

Identifying the joint signature of brain atrophy and gene variant scores in Alzheimer’s Disease

The joint modeling of genetic data and brain imaging information allows for determining the pathophysiological pathways of neurodegenerative diseases such as Alzheimer’s disease (AD). This task has typically been approached using mass-univariate methods that rely on a complete set of Single Nucleotide Polymorphisms (SNPs) to assess their association with selected image-derived phenotypes (IDPs). However, such methods are prone to multiple comparisons bias and, most importantly, fail to account for potential cross-feature interactions, resulting in insufficient detection of significant associations. Ways to overcome these limitations while reducing the number of traits aim at conveying genetic information at the gene level and capturing the integrated genetic effects of a set of genetic variants, rather than looking at each SNP individually. Their associations with brain IDPs are still largely unexplored in the current literature, though they can uncover new potential genetic determinants for brain modulations in the AD continuum. In this work, we explored an explainable multivariate model to analyze the genetic basis of the grey matter modulations, relying on the AD Neuroimaging Initiative (ADNI) phase 3 dataset. Cortical thicknesses and subcortical volumes derived from T1-weighted Magnetic Resonance were considered to describe the imaging phenotypes. At the same time the genetic counterpart was represented by gene variant scores extracted by the Sequence Kernel Association Test (SKAT) filtering model. Moreover, transcriptomic analysis was carried on to assess the expression of the resulting genes in the main brain structures as a form of validation. Results highlighted meaningful genotype–phenotype interactionsas defined by three latent components showing a significant difference in the projection scores between patients and controls. Among the significant associations, the model highlighted EPHX1 and BCAS1 gene variant scores involved in neurodegenerative and myelination processes, hence relevant for AD. In particular, the first was associated with decreased subcortical volumes and the second with decreasedtemporal lobe thickness. Noteworthy, BCAS1 is particularly expressed in the dentate gyrus. Overall, the proposed approach allowed capturing genotype–phenotype interactions in a restricted study cohort that was confirmed by transcriptomic analysis, offering insights into the underlying mechanisms of neurodegeneration in AD in line with previous findings and suggesting new potential disease biomarkers.

Brain imaging endophenotypes by unsupervised deep learning

AbstractBackgroundUnderstanding the genetic architecture of brain structure and Alzheimer’s disease is challenging, partly due to difficulties in designing robust, non‐biased descriptors of the brain.MethodWe present approaches to derive robust brain imaging phenotypes using unsupervised deep representation learning. Training a 3‐D convolutional autoencoder model with reconstruction loss, we derived a vector representation (termed endophenotype) that captures rich morphological information of the brain. Further, we developed a perturbation‐based decoder interpretation approach that can highlight brain regions that are most relevant to individual endophenotypes.ResultUsing UK Biobank data, we trained the model using over 6,000 UK Biobank (UKBB) participants’ T1 or T2‐FLAIR (T2) brain MRIs. The model is used to derive 128 endophenotypes. The endophenotypes have a mean heritability of 0.3 and the GWAS of which have identified 43 independent loci in the held‐out UKBiobank dataset (discovery n = 22,962/replication n = 12,848), among which 13 loci have not been previously reported by the UK Biobank Big40 study.ConclusionUsing UK Biobank data, we show that, compared to traditional brain image‐derived phenotypes (IDPs), our endophenotypes are more heritable and have higher power for genetic discovery.

Exploring Successful Cognitive Aging: Insights Regarding Brain Structure, Function, and Demographics.

In the realm of cognitive science, the phenomenon of "successful cognitive aging" stands as a hallmark of individuals who exhibit cognitive abilities surpassing those of their age-matched counterparts. However, it is paramount to underscore a significant gap in the current research, which is marked by a paucity of comprehensive inquiries that deploy substantial sample sizes to methodically investigate the cerebral biomarkers and contributory elements underpinning this cognitive success. It is within this context that our present study emerges, harnessing data derived from the UK Biobank. In this study, a highly selective cohort of 1060 individuals aged 65 and above was meticulously curated from a larger pool of 17,072 subjects. The selection process was guided by their striking cognitive resilience, ascertained via rigorous evaluation encompassing both generic and specific cognitive assessments, compared to their peers within the same age stratum. Notably, the cognitive abilities of the chosen participants closely aligned with the cognitive acumen commonly observed in middle-aged individuals. Our study leveraged a comprehensive array of neuroimaging-derived metrics, obtained from three Tesla MRI scans (T1-weighted images, dMRI, and resting-state fMRI). The metrics included image-derived phenotypes (IDPs) that addressed grey matter morphology, the strength of brain network connectivity, and the microstructural attributes of white matter. Statistical analyses were performed employing ANOVA, Mann-Whitney U tests, and chi-square tests to evaluate the distinctive aspects of IDPs pertinent to the domain of successful cognitive aging. Furthermore, these analyses aimed to elucidate lifestyle practices that potentially underpin the maintenance of cognitive acumen throughout the aging process. Our findings unveiled a robust and compelling association between heightened cognitive aptitude and the integrity of white matter structures within the brain. Furthermore, individuals who exhibited successful cognitive aging demonstrated markedly enhanced activity in the cerebral regions responsible for auditory perception, voluntary motor control, memory retention, and emotional regulation. These advantageous cognitive attributes were mirrored in the health-related lifestyle choices of the surveyed cohort, characterized by elevated educational attainment, a lower incidence of smoking, and a penchant for moderate alcohol consumption. Moreover, they displayed superior grip strength and enhanced walking speeds. Collectively, these findings furnish valuable insights into the multifaceted determinants of successful cognitive aging, encompassing both neurobiological constituents and lifestyle practices. Such comprehensive comprehension significantly contributes to the broader discourse on aging, thereby establishing a solid foundation for the formulation of targeted interventions aimed at fostering cognitive well-being among aging populations.

Identifying radiomics signatures in body composition imaging for the prediction of outcome following pancreatic cancer resection.

Computerized radiological image analysis (radiomics) enables the investigation of image-derived phenotypes by extracting large numbers of quantitative features. We hypothesized that radiomics features may contain prognostic information that enhances conventional body composition analysis. We aimed to investigate whether body composition-associated radiomics features hold additional value over conventional body composition analysis and clinical patient characteristics used to predict survival of pancreatic ductal adenocarcinoma (PDAC) patients. Computed tomography images of 304 patients undergoing elective pancreatic cancer resection were analysed. 2D radiomics features were extracted from skeletal muscle and subcutaneous and visceral adipose tissue (SAT and VAT) compartments from a single slice at the third lumbar vertebra. The study population was randomly split (80:20) into training and holdout subsets. Feature ranking with Least Absolute Shrinkage Selection Operator (LASSO) followed by multivariable stepwise Cox regression in 1000 bootstrapped re-samples of the training data was performed and tested on the holdout data. The fitted regression predictors were used as "scores" for a clinical (C-Score), body composition (B-Score), and radiomics (R-Score) model. To stratify patients into the highest 25% and lowest 25% risk of mortality compared to the middle 50%, the Harrell Concordance Index was used. Based on LASSO and stepwise cox regression for overall survival, ASA ≥3 and age were the most important clinical variables and constituted the C-score, and VAT-index (VATI) was the most important body composition variable and constituted the B-score. Three radiomics features (SATI_original_shape2D_Perimeter, VATI_original_glszm_SmallAreaEmphasis, and VATI_original_firstorder_Maximum) emerged as the most frequent set of features and yielded an R-Score. Of the mean concordance indices of C-, B-, and R-scores, R-score performed best (0.61, 95% CI 0.56-0.65, p<0.001), followed by the C-score (0.59, 95% CI 0.55-0.63, p<0.001) and B-score (0.55, 95% CI 0.50-0.60, p=0.03). Kaplan-Meier projection revealed that C-, B, and R-scores showed a clear split in the survival curves in the training set, although none remained significant in the holdout set. It is feasible to implement a data-driven radiomics approach to body composition imaging. Radiomics features provided improved predictive performance compared to conventional body composition variables for the prediction of overall survival of PDAC patients undergoing primary resection.

Abdominal imaging associates body composition with COVID-19 severity.

The main drivers of COVID-19 disease severity and the impact of COVID-19 on long-term health after recovery are yet to be fully understood. Medical imaging studies investigating COVID-19 to date have mostly been limited to small datasets and post-hoc analyses of severe cases. The UK Biobank recruited recovered SARS-CoV-2 positive individuals (n = 967) and matched controls (n = 913) who were extensively imaged prior to the pandemic and underwent follow-up scanning. In this study, we investigated longitudinal changes in body composition, as well as the associations of pre-pandemic image-derived phenotypes with COVID-19 severity. Our longitudinal analysis, in a population of mostly mild cases, associated a decrease in lung volume with SARS-CoV-2 positivity. We also observed that increased visceral adipose tissue and liver fat, and reduced muscle volume, prior to COVID-19, were associated with COVID-19 disease severity. Finally, we trained a machine classifier with demographic, anthropometric and imaging traits, and showed that visceral fat, liver fat and muscle volume have prognostic value for COVID-19 disease severity beyond the standard demographic and anthropometric measurements. This combination of image-derived phenotypes from abdominal MRI scans and ensemble learning to predict risk may have future clinical utility in identifying populations at-risk for a severe COVID-19 outcome.

Supervised Phenotype Discovery from Multimodal Brain Imaging.

Data-driven discovery of image-derived phenotypes (IDPs) from large-scale multimodal brain imaging data has enormous potential for neuroscientific and clinical research by linking IDPs to subjects' demographic, behavioural, clinical and cognitive measures (i.e., nonimaging derived phenotypes or nIDPs). However, current approaches are primarily based on unsupervised approaches, without the use of information in nIDPs. In this paper, we proposed a semi-supervised, multimodal, and multi-task fusion approach, termed SuperBigFLICA, for IDP discovery, which simultaneously integrates information from multiple imaging modalities as well as multiple nIDPs. SuperBigFLICA is computationally efficient and largely avoids the need for parameter tuning. Using the UK Biobank brain imaging dataset with around 40,000 subjects and 47 modalities, along with more than 17,000 nIDPs, we showed that SuperBigFLICA enhances the prediction power of nIDPs, benchmarked against IDPs derived by conventional expert-knowledge and unsupervised-learning approaches (with average nIDP prediction accuracy improvements of up to 46%). It also enables the learning of generic imaging features that can predict new nIDPs. Further empirical analysis of the SuperBigFLICA algorithm demonstrates its robustness in different prediction tasks and the ability to derive biologically meaningful IDPs in predicting health outcomes and cognitive nIDPs, such as fluid intelligence and hypertension.

Relationships of Residential Distance to Major Traffic Roads with Dementia Incidence and Brain Structure Measures: Mediation Role of Air Pollution.

Background: Uncertainty exists regarding the operating pathways between near-roadway exposure and dementia incidence. We intend to examine relationships between proximity to major roadways with dementia incidence and brain MRI structure measures, and potential mediation roles of air and noise pollution. Methods: The cohort study was based on the UK Biobank. Baseline survey was conducted from 2006 to 2010, with linkage to electronic health records conducted for follow-up. Residential distance to major roadways was ascertained residential address postcode. A land use regression model was applied for estimating traffic-related air pollution at residence. Dementia incidence was ascertained using national administrative databases. Brain MRI measures were derived as image-derived phenotypes, including total brain, white matter, gray matter, and peripheral cortical gray matter. Results: We included 460,901 participants [mean (SD) age: 57.1 (8.1) years; men: 45.7%]. Compared with individuals living >1,000 m from major traffic roads, living ≤1,000 m was associated with a 13% to 14% higher dementia risk, accounting for 10% of dementia cases. Observed association between residential distance and dementia was substantially mediated by traffic-related air pollution, mainly nitrogen dioxide (proportion mediated: 63.6%; 95% CI, 27.0 to 89.2%) and PM2.5 (60.9%, 26.8 to 87.0%). The shorter residential distance was associated with smaller volumes of brain structures, which was also mediated by traffic-related air pollutants. No significant mediation role was observed of noise pollution. Conclusions: The shorter residential distance to major roads was associated with elevated dementia incidence and smaller brain structure volumes, which was mainly mediated by traffic-related air pollution.

SynthA1c: Towards Clinically Interpretable Patient Representations for Diabetes Risk Stratification.

Early diagnosis of Type 2 Diabetes Mellitus (T2DM) is crucial to enable timely therapeutic interventions and lifestyle modifications. As the time available for clinical office visits shortens and medical imaging data become more widely available, patient image data could be used to opportunistically identify patients for additional T2DM diagnostic workup by physicians. We investigated whether image-derived phenotypic data could be leveraged in tabular learning classifier models to predict T2DM risk in an automated fashion to flag high-risk patients without the need for additional blood laboratory measurements. In contrast to traditional binary classifiers, we leverage neural networks and decision tree models to represent patient data as 'SynthA1c' latent variables, which mimic blood hemoglobin A1c empirical lab measurements, that achieve sensitivities as high as 87.6%. To evaluate how SynthA1c models may generalize to other patient populations, we introduce a novel generalizable metric that uses vanilla data augmentation techniques to predict model performance on input out-of-domain covariates. We show that image-derived phenotypes and physical examination data together can accurately predict diabetes risk as a means of opportunistic risk stratification enabled by artificial intelligence and medical imaging. Our code is available at https://github.com/allisonjchae/DMT2RiskAssessment.

Telomere length is causally connected to brain MRI image derived phenotypes: A mendelian randomization study.

Recent evidence suggests that shorter telomere length (TL) is associated with neuro degenerative diseases and aging related outcomes. The causal association between TL and brain characteristics represented by image derived phenotypes (IDPs) from different magnetic resonance imaging (MRI) modalities remains unclear. Here, we use two-sample Mendelian randomization (MR) to systematically assess the causal relationships between TL and 3,935 brain IDPs. Overall, the MR results suggested that TL was causally associated with 193 IDPs with majority representing diffusion metrics in white matter tracts. 68 IDPs were negatively associated with TL indicating that longer TL causes decreasing in these IDPs, while the other 125 were associated positively (longer TL leads to increased IDPs measures). Among them, ten IDPs have been previously reported as informative biomarkers to estimate brain age. However, the effect direction between TL and IDPs did not reflect the observed direction between aging and IDPs: longer TL was associated with decreases in fractional anisotropy and increases in axial, radial and mean diffusivity. For instance, TL was positively associated with radial diffusivity in the left perihippocampal cingulum tract and with mean diffusivity in right perihippocampal cingulum tract. Our results revealed a causal role of TL on white matter integrity which makes it a valuable factor to be considered when brain age is estimated and investigated.