Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging.
Ontology highlight
ABSTRACT:
SUBMITTER: Saboo KV
PROVIDER: S-EPMC9045384 | biostudies-literature | 2022 May
REPOSITORIES: biostudies-literature
Publications
Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging.
Saboo Krishnakant V KV Hu Chang C Varatharajah Yogatheesan Y Przybelski Scott A SA Reid Robert I RI Schwarz Christopher G CG Graff-Radford Jonathan J Knopman David S DS Machulda Mary M MM Mielke Michelle M MM Petersen Ronald C RC Arnold Paul M PM Worrell Gregory A GA Jones David T DT Jack Clifford R CR Iyer Ravishankar K RK Vemuri Prashanthi P
NeuroImage 20220220
Specific brain structures (gray matter regions and white matter tracts) play a dominant role in determining cognitive decline and explain the heterogeneity in cognitive aging. Identification of these structures is crucial for screening of older adults at risk of cognitive decline. Using deep learning models augmented with a model-interpretation technique on data from 1432 Mayo Clinic Study of Aging participants, we identified a subset of brain structures that were most predictive of individualiz ...[more]
Similar Datasets
Project description:Deep neural networks (DNNs) models have the potential to provide new insights in the study of cognitive processes, such as human decision making, due to their high capacity and data-driven design. While these models may be able to go beyond theory-driven models in predicting human behaviour, their opaque nature limits their ability to explain how an operation is carried out, undermining their usefulness as a scientific tool. Here we suggest the use of a DNN model as an exploratory tool to identify predictable and consistent human behaviour, and using explicit, theory-driven models, to characterise the high-capacity model. To demonstrate our approach, we trained an exploratory DNN model to predict human decisions in a four-armed bandit task. We found that this model was more accurate than two explicit models, a reward-oriented model geared towards choosing the most rewarding option, and a reward-oblivious model that was trained to predict human decisions without information about rewards. Using experimental simulations, we were able to characterise the exploratory model using the explicit models. We found that the exploratory model converged with the reward-oriented model's predictions when one option was clearly better than the others, but that it predicted pattern-based explorations akin to the reward-oblivious model's predictions. These results suggest that predictable decision patterns that are not solely reward-oriented may contribute to human decisions. Importantly, we demonstrate how theory-driven cognitive models can be used to characterise the operation of DNNs, making DNNs a useful explanatory tool in scientific investigation.
| S-EPMC8933393 | biostudies-literature
Project description:Cognitive decline in Parkinson's disease (PD) varies widely. While models to predict cognitive progression exist, comparing traditional probabilistic models to deep learning methods remains understudied. This study compares sequential modeling techniques to identify cognitive progression in individuals with and without PD. Using data from the Parkinson's Progression Marker Initiative, shallow Markov, deep recurrent (long short-term memory [LSTM]), and nonrecurrent (temporal fusion transformer [TFT]) models were compared to predict cognitive status over time. Cognitive status was categorized into normal cognition (NC), mild cognitive impairment (MCI), and dementia. Predictions were made annually for up to 3 years using clinical data, including demographics, cognitive assessments, PD severity, and medical history. Each approach was evaluated using inverse probability weighted (IPW-) F1 scores. An ensemble method combined outputs from the Markov, LSTM, and TFT models. The dataset included 917 individuals (53% PD; 30% at risk for PD; 17% Healthy Controls). The TFT model outperformed others across all annual periods (IPW-F1 = 0.468) compared to the Markov (IPW-F1 = 0.349) and LSTM (IPW-F1 = 0.414) models, with improved performance using an ensemble approach (IPW-F1 = 0.502). For MCI and dementia predictions, which were rarer occurrences compared to NC status (ratios: 50:8:1), the TFT model consistently outperformed competing models, achieving IPW-F1 scores of 0.496 and 0.533 for MCI and dementia, respectively. In conclusion, sequential deep learning models like TFT, which mitigate long-term memory loss and can interpret complex, high-dimensional data, perform best overall in predicting clinically important cognitive transitions. These methods should be further explored for predicting degenerative conditions.
| S-EPMC11544638 | biostudies-literature
Project description:Cellular phenotypic heterogeneity is an important hallmark of many biological processes and understanding its origins remains a substantial challenge. This heterogeneity often reflects variations in the chromatin structure, influenced by factors such as viral infections and cancer, which dramatically reshape the cellular landscape. To address the challenge of identifying distinct cell states, we developed artificial intelligence of the nucleus (AINU), a deep learning method that can identify specific nuclear signatures at the nanoscale resolution. AINU can distinguish different cell states based on the spatial arrangement of core histone H3, RNA polymerase II or DNA from super-resolution microscopy images. With only a small number of images as the training data, AINU correctly identifies human somatic cells, human-induced pluripotent stem cells, very early stage infected cells transduced with DNA herpes simplex virus type 1 and even cancer cells after appropriate retraining. Finally, using AI interpretability methods, we find that the RNA polymerase II localizations in the nucleoli aid in distinguishing human-induced pluripotent stem cells from their somatic cells. Overall, AINU coupled with super-resolution microscopy of nuclear structures provides a robust tool for the precise detection of cellular heterogeneity, with considerable potential for advancing diagnostics and therapies in regenerative medicine, virology and cancer biology.
| S-EPMC11415298 | biostudies-literature
Project description:IntroductionThe utility of retinal photography-derived aging biomarkers for predicting cognitive decline remains under-explored.MethodsA memory-clinic cohort in Singapore was followed-up for 5 years. RetiPhenoAge, a retinal aging biomarker, was derived from retinal photographs using deep-learning. Using competing risk analysis, we determined the associations of RetiPhenoAge with cognitive decline and dementia, with the UK Biobank utilized as the replication cohort. The associations of RetiPhenoAge with MRI markers(cerebral small vessel disease [CSVD] and neurodegeneration) and its underlying plasma proteomic profile were evaluated.ResultsOf 510 memory-clinic subjects(N = 155 cognitive decline), RetiPhenoAge associated with incident cognitive decline (subdistribution hazard ratio [SHR] 1.34, 95% confidence interval [CI] 1.10-1.64, p = 0.004), and incident dementia (SHR 1.43, 95% CI 1.02-2.01, p = 0.036). In the UK Biobank (N = 33 495), RetiPhenoAge similarly predicted incident dementia (SHR 1.25, 95% CI 1.09-1.41, p = 0.008). RetiPhenoAge significantly associated with CSVD, brain atrophy, and plasma proteomic signatures related to aging.DiscussionRetiPhenoAge may provide a non-invasive prognostic screening tool for cognitive decline and dementia.HighlightsRetiPhenoAge, a retinal aging marker, was studied in an Asian memory clinic cohort. Older RetiPhenoAge predicted future cognitive decline and incident dementia. It also linked to neuropathological markers, and plasma proteomic profiles of aging. UK Biobank replication found that RetiPhenoAge predicted 12-year incident dementia. Future studies should validate RetiPhenoAge as a prognostic biomarker for dementia.
| S-EPMC11881618 | biostudies-literature
Project description:Background and objectivesDeep learning utilizing convolutional neural networks (CNNs) applied to hematoxylin & eosin (H&E)-stained slides numerically encodes histomorphological tumor features. Tumor heterogeneity is an emerging biomarker in colon cancer that is, captured by these features, whereas microsatellite instability (MSI) is an established biomarker traditionally assessed by immunohistochemistry or polymerase chain reaction.MethodsH&E-stained slides from The Cancer Genome Atlas (TCGA) colon cohort are passed through the CNN. Resulting imaging features are used to cluster morphologically similar slide regions. Tile-level pairwise similarities are calculated and used to generate a tumor heterogeneity score (THS). Patient-level THS is then correlated with TCGA-reported biomarkers, including MSI-status.ResultsH&E-stained images from 313 patients generated 534 771 tiles. Deep learning automatically identified and annotated cells by type and clustered morphologically similar slide regions. MSI-high tumors demonstrated significantly higher THS than MSS/MSI-low (p < 0.001). THS was higher in MLH1-silent versus non-silent tumors (p < 0.001). The sequencing derived MSIsensor score also correlated with THS (r = 0.51, p < 0.0001).ConclusionsDeep learning provides spatially resolved visualization of imaging-derived biomarkers and automated quantification of tumor heterogeneity. Our novel THS correlates with MSI-status, indicating that with expanded training sets, translational tools could be developed that predict MSI-status using H&E-stained images alone.
| S-EPMC11446314 | biostudies-literature
Project description:PurposeTo study the individual course of retinal changes caused by healthy aging using deep learning.DesignRetrospective analysis of a large data set of retinal OCT images.ParticipantsA total of 85 709 adults between the age of 40 and 75 years of whom OCT images were acquired in the scope of the UK Biobank population study.MethodsWe created a counterfactual generative adversarial network (GAN), a type of neural network that learns from cross-sectional, retrospective data. It then synthesizes high-resolution counterfactual OCT images and longitudinal time series. These counterfactuals allow visualization and analysis of hypothetical scenarios in which certain characteristics of the imaged subject, such as age or sex, are altered, whereas other attributes, crucially the subject's identity and image acquisition settings, remain fixed.Main outcome measuresUsing our counterfactual GAN, we investigated subject-specific changes in the retinal layer structure as a function of age and sex. In particular, we measured changes in the retinal nerve fiber layer (RNFL), combined ganglion cell layer plus inner plexiform layer (GCIPL), inner nuclear layer to the inner boundary of the retinal pigment epithelium (INL-RPE), and retinal pigment epithelium (RPE).ResultsOur counterfactual GAN is able to smoothly visualize the individual course of retinal aging. Across all counterfactual images, the RNFL, GCIPL, INL-RPE, and RPE changed by -0.1 μm ± 0.1 μm, -0.5 μm ± 0.2 μm, -0.2 μm ± 0.1 μm, and 0.1 μm ± 0.1 μm, respectively, per decade of age. These results agree well with previous studies based on the same cohort from the UK Biobank population study. Beyond population-wide average measures, our counterfactual GAN allows us to explore whether the retinal layers of a given eye will increase in thickness, decrease in thickness, or stagnate as a subject ages.ConclusionThis study demonstrates how counterfactual GANs can aid research into retinal aging by generating high-resolution, high-fidelity OCT images, and longitudinal time series. Ultimately, we envision that they will enable clinical experts to derive and explore hypotheses for potential imaging biomarkers for healthy and pathologic aging that can be refined and tested in prospective clinical trials.Financial disclosuresProprietary or commercial disclosure may be found after the references.
| S-EPMC10127123 | biostudies-literature
Project description:BackgroundUS-based studies have reported that older blacks perform worse than older whites on cognitive tests and have higher risk of Alzheimer disease dementia (AD). It is unclear whether these findings reflect differences in cognitive decline.MethodsThe Chicago Health and Aging Project followed individuals, 65+ years old (64% black, 36% white), for up to 18 years. Participants underwent triennial cognitive assessments; stratified randomized samples underwent assessments for AD. We compared black and white participants' cognitive performance, cognitive decline rate (N = 7,735), and AD incidence (N = 2,144), adjusting for age and sex.ResultsBlack participants performed worse than white participants on the cognitive tests; 441 participants developed AD. Black participants' incident AD risk was twice that of whites (RR = 1.9; 95% CI, 1.4, 2.7), with 58 excess cases/1,000 occurring among blacks (95% CI, 28, 88). Among noncarriers of APOE ε4, blacks had 2.3 times the AD risk (95% CI, 1.5, 3.6), but among carriers, race was not associated with risk (RR = 1.1; 95% CI, 0.6, 2.0; Pinteraction = 0.05). However, cognitive decline was not faster among blacks: the black-white difference in 5-year change in global cognitive score was 0.007 standard unit (95% CI, -0.034, 0.047). Years of education accounted for a sizable portion of racial disparities in cognitive level and AD risk, in analyses using a counterfactual approach.ConclusionsThe higher risk of AD among blacks may stem from lower level of cognitive test performance persisting throughout the observation period rather than faster rate of late-life cognitive decline. Disparities in educational attainment may contribute to these performance disparities. See video abstract at, http://links.lww.com/EDE/B299.
| S-EPMC5718953 | biostudies-literature
Project description:The unexpected high species richness of deep-sea sediments gives rise to the questions, which processes produce and maintain diversity in the deep sea, and at what spatial scales do these processes operate? The idea of a small-scale habitat structure at the deep-sea floor provides the background for this study. At small scales biogenic structures create a heterogeneous environment that influences the structure of the surrounding communities and the dynamics of the meiobenthic populations. As an example for biogenic structures, small deep-sea sponges (Tentorium semisuberites Schmidt 1870) and their sedimentary environment were investigated for small-scale distribution patterns of benthic deep-sea nematodes. Sampling was carried out with the remotely operated vehicle Victor 6000 at the Arctic deep-sea observatory HAUSGARTEN. In order to investigate nematode community patterns sediment cores around three small sponges and corresponding control cores were analysed. A total of approx. 5800 nematodes were identified. The comparison of the nematode communities from sponge and control samples indicated an influence of the biogenic structure "sponge" on diversity patterns and habitat heterogeneity. The increased number of nematode species and functional groups found in the sediments around the sponges suggest that on a small scale the sponge acts as a gradient and creates a more divers habitat structure. The nematode community from the sponge sediments shows a greater taxonomic variance and species richness together with lower relative abundances of the species compared to those from control sediments. Obviously, the more homogeneous habitat conditions of the control sediments offer less micro-habitats than the sediments around the sponges. This seems to reduce the number of functional groups and species coexisting in the control sediments.
| S-EPMC3247241 | biostudies-literature
Project description:Computational methods that automatically extract knowledge from data are critical for enabling data-driven materials science. A reliable identification of lattice symmetry is a crucial first step for materials characterization and analytics. Current methods require a user-specified threshold, and are unable to detect average symmetries for defective structures. Here, we propose a machine learning-based approach to automatically classify structures by crystal symmetry. First, we represent crystals by calculating a diffraction image, then construct a deep learning neural network model for classification. Our approach is able to correctly classify a dataset comprising more than 100,000 simulated crystal structures, including heavily defective ones. The internal operations of the neural network are unraveled through attentive response maps, demonstrating that it uses the same landmarks a materials scientist would use, although never explicitly instructed to do so. Our study paves the way for crystal structure recognition of-possibly noisy and incomplete-three-dimensional structural data in big-data materials science.
| S-EPMC6050314 | biostudies-literature
Project description:Metallo-β-Lactamases (MBLs) protect bacteria from almost all β-lactam antibiotics. Verona integron-encoded MBL (VIM) enzymes are among the most clinically important MBLs, with VIM-1 increasing in carbapenem-resistant Enterobacteriaceae (Escherichia coli, Klebsiella pneumoniae) that are among the hardest bacterial pathogens to treat. VIM enzymes display sequence variation at residues (224 and 228) that in related MBLs are conserved and participate in substrate binding. How they accommodate this variability, while retaining catalytic efficiency against a broad substrate range, has remained unclear. Here, we present crystal structures of VIM-1 and its complexes with a substrate-mimicking thioenolate inhibitor, ML302F, that restores meropenem activity against a range of VIM-1 producing clinical strains, and the hydrolysed product of the carbapenem meropenem. Comparison of these two structures identifies a water-mediated hydrogen bond, between the carboxylate group of substrate/inhibitor and the backbone carbonyl of the active site zinc ligand Cys221, that is common to both complexes. Structural comparisons show that the responsible Cys221-bound water is observed in all known VIM structures, participates in carboxylate binding with other inhibitor classes, and thus effectively replicates the role of the conserved Lys224 in analogous complexes with other MBLs. These results provide a mechanism for substrate binding that permits the variation at positions 224 and 228 that is a hallmark of VIM MBLs. ENZYMES: EC 3.5.2.6 DATABASES: Co-ordinates and structure factors for protein structures described in this manuscript have been deposited in the Protein Data Bank (www.rcsb.org/pdb) with accession codes 5N5G (VIM-1), 5N5H (VIM-1:ML302F complex) and 5N5I (VIM-1-hydrolysed meropenem complex).
| S-EPMC6326847 | biostudies-literature