Sequence Labeling Research Articles

Multi-granularity sequence generation for hierarchical image classification

Hierarchical multi-granularity image classification is a challenging task that aims to tag each given image with multiple granularity labels simultaneously. Existing methods tend to overlook that different image regions contribute differently to label prediction at different granularities, and also insufficiently consider relationships between the hierarchical multi-granularity labels. We introduce a sequence-to-sequence mechanism to overcome these two problems and propose a multi-granularity sequence generation (MGSG) approach for the hierarchical multi-granularity image classification task. Specifically, we introduce a transformer architecture to encode the image into visual representation sequences. Next, we traverse the taxonomic tree and organize the multi-granularity labels into sequences, and vectorize them and add positional information. The proposed multi-granularity sequence generation method builds a decoder that takes visual representation sequences and semantic label embedding as inputs, and outputs the predicted multi-granularity label sequence. The decoder models dependencies and correlations between multi-granularity labels through a masked multi-head self-attention mechanism, and relates visual information to the semantic label information through a cross-modality attention mechanism. In this way, the proposed method preserves the relationships between labels at different granularity levels and takes into account the influence of different image regions on labels with different granularities. Evaluations on six public benchmarks qualitatively and quantitatively demonstrate the advantages of the proposed method. Our project is available at https://github.com/liuxindazz/mgsg.

To click or not to click for short pulse-labeling of the bacterial cell wall.

A method of choice to study the spatio-temporal dynamics of bacterial cell growth and division is to analyze the localization of cell wall synthesis regions by fluorescence microscopy. For this, nascent cell wall biopolymers need to be labeled with fluorescent reporters, like fluorescent d-alanines (FDAs) that can be incorporated into the peptidoglycan. To achieve high spatial and temporal resolution, dense, high-intensity fluorescence labeling must be obtained in the shortest possible time. However, modifications carried by d-Ala can hinder their uptake by the enzymes that incorporate them into the peptidoglycan, such as the d,d-transpeptidases. Conversely, these modifications can impede the elimination of the incorporated d-Ala derivatives by d,d-carboxypeptidases, making the labeling more persistent. In this context, we synthesized clickable d-Alas and tested their incorporation into the peptidoglycan using different labeling approaches, prior or after their conjugation to clickable fluorescent dyes through SPAAC reaction. Our data allow ranking of the d-Ala derivatives in terms of their ease of incorporation and resistance to trimming during one-step, "one-pot" two-step or sequential two-step labeling strategies. We further show that a hybrid "one-step" approach, in which a FDA is used in combination with clickable choline and fluorescent dye, enables two-color co-labeling of peptidoglycan and teichoic acids. Finally, we identify a strategy compatible with the cell fixation required for super-resolution microscopy, by combining one-step labeling with FDA and sequential two-step labeling with clickable choline and fluorescent dye, allowing to obtain two-color high-resolution images of peptidoglycan and teichoic acid synthesis regions.

N4-Allylcytidine: a new nucleoside analogue for RNA labelling and chemical sequencing.

RNA labelling has become indispensable in studying RNA biology. Nucleoside analogues with a chemical sequencing power represent desirable RNA labelling molecules because precise labelling information at base resolution can be obtained. Here, we report a new nucleoside analogue, N4-allylcytidine (a4C), which is able to tag RNA through both in vitro and in vivo pathways and further specifically reacts with iodine to form 3, N4-cyclized cytidine (cyc-C) in a catalyst-free, fast and complete manner. Full spectroscopic characterization concluded that cyc-C consisted of paired diastereoisomers with opposite chiral carbon centers in the fused 3, N4-five-membered ring. During RNA reverse transcription into complementary DNA, cyc-C induces base misincorporation due to the disruption of canonical hydrogen bonding by the cyclized structure and thus can be accurately identified by sequencing at single base resolution. With the chemical sequencing rationale of a4C, successful applications have been performed including pinpointing N4-methylcytidine methyltransferases' substrate modification sites, metabolically labelling mammalian cellular RNAs, and mapping active cellular RNA polymerase locations with the chromatin run-on RNA sequencing technique. Collectively, our work demonstrates that a4C is a promising molecule for RNA labelling and chemical sequencing and expands the toolkit for studying sophisticated RNA biology.

The application effect of the Rasch measurement model combined with the CRF model: An analysis based on English discourse.

To analyze English discourse more accurately and provide more detailed feedback information, this study applies Rasch measurement and Conditional Random Field (CRF) models to English discourse analysis. The Rasch measurement model is widely used to evaluate and quantify the potential traits of individuals, and it has remarkable advantages in measurement and evaluation. By combining the CRF model, the Rasch model is employed to model the structural and semantic information in the discourse and use this model to carry out sequence labeling, to enhance the ability to capture the internal relations of the discourse. Finally, this study conducts comparative experiments on integrating the Rasch measurement and CRF models, comparing the outcomes against traditional scoring methods and the standalone CRF model. The research findings indicate that: (1) The discourse component syntactic analysis model on the Penn Treebank (PTB) database obtained Unlabeled Attachment Score (UAS) values of 94.07, 95.76, 95.67, and 95.43, and Labeled Attachment Score (LAS) values of 92.47, 92.33, 92.49, and 92.46 for the LOC, CRF, CRF2O, and MFVI models, respectively. After adding the Rasch measurement model, the UAS values of the four models on the PTB database are 96.85, 96.77, 96.92, and 96.78 for the LOC, CRF, CRF2O, and MFVI models, respectively, with LAS values of 95.33, 95.34, 95.39, and 95.32, all showing significant improvement. (2) By combining contextual information with CRF models, students can better understand their discourse expression, capture the connections between English discourse sentences, and analyze English discourse more comprehensively. This study provides new ideas and methods for researchers in English language education and linguistics.

Sequence Labeling as Non-Autoregressive Dual-Query Set Generation

Sequence Labeling as Non-Autoregressive Dual-Query Set Generation

Sparsely-Supervised Object Tracking.

Recent years have witnessed the incredible performance boost of data-driven deep visual object trackers. Despite the success, these trackers require millions of sequential manual labels on videos for supervised training, implying the heavy burden of human annotating. This raises a crucial question: how to train a powerful tracker from abundant videos using limited manual annotations? In this paper, we challenge the conventional belief that frame-by-frame labeling is indispensable, and show that providing a small number of annotated bounding boxes in each video is sufficient for training a strong tracker. To facilitate that, we design a novel SParsely-supervised Object Tracking (SPOT) framework. It regards the sparsely annotated boxes as anchors and progressively explores in the temporal span to discover unlabeled target snapshots. Under the teacher-student paradigm, SPOT leverages the unique transitive consistency inherent in the tracking task as supervision, extracting knowledge from both anchor snapshots and unlabeled target snapshots. We also utilize several effective training strategies, i.e., IoU filtering, asymmetric augmentation, and temporal calibration to further improve the training robustness of SPOT. The experimental results demonstrate that, given less than 5 labels for each video, trackers trained via SPOT perform on par with their fully-supervised counterparts. Moreover, our SPOT exhibits two desirable properties: 1) SPOT enables us to fully exploit large-scale video datasets by efficiently allocating sparse labels to more videos even under a limited labeling budget; 2) when equipped with a target discovery module, SPOT can even learn from purely unlabeled videos for performance gain. We hope this work could inspire the community to rethink the current annotation principles and make a step towards practical label-efficient deep tracking.

Tertiary amide bond formation by an engineered asparaginyl ligase.

Transpeptidases are powerful tools for site-specific protein modification, enabling the production of tailored biologics to investigate protein function and aiding the development of next-generation therapeutics and diagnostics. Although protein labelling at the N- or C-terminus is readily accomplished using a range of established transpeptidases, these reactions are generally limited to forming products that are linked by a standard (secondary) amide bond. Here we show that, unlike other widely used transpeptidases, an engineered asparaginyl ligase is able to efficiently synthesise tertiary amide bonds by accepting diverse secondary amine nucleophiles. These reactions proceed efficiently under mild conditions (near-neutral pH) and allow the optimal recognition elements for asparaginyl ligases (P1 Asn and P2'' Leu) to be preserved. Certain products, particularly proline-containing products, were found to be protected from recognition by the enzyme, allowing for straightforward sequential labelling of proteins. Additionally, incorporation of 4-azidoproline enables one-pot dual labelling directly at the ligation junction. These capabilities further expand the chemical diversity of asparaginyl ligase-catalysed reactions and provide an alternative approach for straightforward, successive modification of protein substrates.

Decomposed Meta-Learning for Few-Shot Sequence Labeling

Decomposed Meta-Learning for Few-Shot Sequence Labeling

Context-Aware Attentive Multilevel Feature Fusion for Named Entity Recognition.

In the era of information explosion, named entity recognition (NER) has attracted widespread attention in the field of natural language processing, as it is fundamental to information extraction. Recently, methods of NER based on representation learning, e.g., character embedding and word embedding, have demonstrated promising recognition results. However, existing models only consider partial features derived from words or characters while failing to integrate semantic and syntactic information, e.g., capitalization, inter-word relations, keywords, and lexical phrases, from multilevel perspectives. Intuitively, multilevel features can be helpful when recognizing named entities from complex sentences. In this study, we propose a novel attentive multilevel feature fusion (AMFF) model for NER, which captures the multilevel features in the current context from various perspectives. It consists of four components to, respectively, capture the local character-level (CL), global character-level (CG), local word-level (WL), and global word-level (WG) features in the current context. In addition, we further define document-level features crafted from other sentences to enhance the representation learning of the current context. To this end, we introduce a novel context-aware attentive multilevel feature fusion (CAMFF) model based on AMFF, to fully leverage document-level features from all the previous inputs. The obtained multilevel features are then fused and fed into a bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) network for the final sequence labeling. Extensive experiments on four benchmark datasets demonstrate that our proposed AMFF and CAMFF models outperform a set of state-of-the-art baseline methods and the features learned from multiple levels are complementary.

Validating the reconstruction of DNA silver nanoclusters induced by different DNA sequence via HPLC and exploring the optical properties of reconstructed DNA silver nanoclusters

We investigated the influence of redundant DNA templates on the optical properties of DNA-stabilized silver nanoclusters (DNA AgNCs).

OVAR-BPnet: A General Pulse Wave Deep Learning Approach for Cuffless Blood Pressure Measurement.

Pulse wave analysis, a non-invasive and cuff-less approach, holds promise for blood pressure (BP) measurement in precision medicine. In recent years, pulse wave learning for BP estimation has undergone extensive scrutiny. However, prevailing methods still encounter challenges in grasping comprehensive features from pulse waves and generalizing these insights for precise BP estimation. In this study, we propose a general pulse wave deep learning (PWDL) approach for BP estimation, introduc-ing the OVAR-BPnet model to powerfully capture intricate pulse wave features and showcasing its effectiveness on multiple types of pulse waves. The approach involves constructing population pulse waves and employing a model comprising an omni-scale convolution subnet, a Vision Transformer subnet, and a multilayer perceptron subnet. This design enables the learning of both single-period and multi-period waveform features from multiple subjects. Additionally, the approach employs a data augmentation strategy to enhance the morphological features of pulse waves and devise a label sequence regularization strategy to strengthen the intrinsic relationship of the subnets' output. Notably, this is the first study to validate the performance of the deep learning approach of BP estimation on three types of pulse waves: photoplethysmography, forehead imaging photoplethysmography, and radial artery pulse pressure waveform. Experiments show that the OVAR-BPnet model has achieved advanced levels in both evaluation indicators and international evaluation criteria, demonstrating its excellent competitiveness and generalizability. The PWDL approach has the potential for widespread application in convenient and continuous BP monitoring systems.

Biomedical event extraction using pre-trained SciBERT

Abstract Biomedical event extraction is applied to biomedical texts to obtain a list of events within the biomedical domain. The best GENIA biomedical event extraction research uses sequence labeling techniques with a joint approach, softmax decoder for event trigger identification, and the BioBERT v1.1 encoder. However, this event extraction model has three drawbacks: tasks are carried out independently, it does not provide special handling of multi-label event trigger labels, and it uses an encoder with vocabulary from non-biomedical domains. We propose to use the pipeline approach to provide forward information sigmoid to address multi-label event trigger labels and alternative BERT encoders with vocabulary from the biomedical domain. The experiment showed that the performance of the biomedical event extraction model increased after changing the encoder, which had been built using a biomedical-specific domain vocabulary. Changing the encoder to SciBERT while still using the joint approach and softmax decoder increased the precision by 4.22 points (reaching 69.88) and resulted in an F1-score of 58.48.

Dependency-based BERT for Chinese Event Argument Extraction

Existing event extraction methods independently identify and classify each argument role separately, ignoring the interdependence between different parameter roles. Further, these methods rely on simple vectors to represent word embeddings. By embedding explicit syntactic constraints in the attention mechanism, we address these shortcomings by using dependency syntax to guide the text modeling. Specifically, we use dependency syntax to guide the BERT model for Chinese event argument role extraction, which mainly consists of three stages. First, the self-attention method guided by a dependency syntactic parsing tree is embedded in the Transformer computing framework of the BERT model. In addition to obtaining a deep two-way linguistic representation of a word according to its context information, this method also expresses the long-distance syntactic dependency relationships between words based on context information. Secondly, the designed conditional layer normalization method is applied to the event argument extraction model in order to integrate the semantic information of trigger words into the text, thereby improving the accuracy of the argument role extraction. Lastly, conditional random fields (CRFs) are used to determine the optimal sequence of labels at the sentence level based on the dependence relationships between adjacent labels. According to the experimental results, the constructed model outperforms several strong baselines in the Chinese event argument extraction task on the ACE2005 dataset and the iFLYTEKA.I.2020 dataset.

Seeing both sides: context-aware heterogeneous graph matching networks for extracting-related arguments

Our research focuses on extracting exchanged views from dialogical documents through argument pair extraction (APE). The objective of this process is to facilitate comprehension of complex argumentative discourse by finding the related arguments. The APE comprises two stages: argument mining and argument matching. Researchers typically employ sequence labeling models for mining arguments and text matching models to calculate the relationships between them, thereby generating argument pairs. However, these approaches fail to capture long-distance contextual information and struggle to fully comprehend the complex structure of arguments. In our work, we propose the context-aware heterogeneous graph matching (HGMN) model for the APE task. First, we design a graph schema specifically tailored to argumentative texts, along with a heterogeneous graph attention network that effectively captures context information and structural information of arguments. Moreover, the text matching between arguments is converted into a graph matching paradigm and a multi-granularity graph matching model is proposed to handle the intricate relationships between arguments at various levels of granularity. In this way, the semantics of argument are modeled structurally and thus capture the complicated correlations between arguments. Extensive experiments are conducted to evaluate the HGMN model, including comparisons with existing methods and the GPT series of large language models (LLM). The results demonstrate that HGMN outperforms the state-of-the-art method.

RESEARCH ON NAMED ENTITY RECOGNITION METHODS FOR URBAN UNDERGROUND SPACE DISASTERS BASED ON TEXT INFORMATION EXTRACTION

Abstract. Urban underground space is a complex spatial scenario that is highly susceptible to disasters. To achieve entity recognition in textual information related to urban underground space disasters, this study proposes the ALBERT-BiLSTM-CRF model. The urban underground space disaster text data is firstly encoded using the ALBERT model, which captures the deep semantic information of words in the context. The encoded data is then fed into a BiLSTM network to obtain hidden state vectors for each word, enhancing the feature representation of words. Finally, these vectors are input into a CRF layer to obtain the optimal label sequence and complete named entity recognition. The proposed model achieves an accuracy of 95.41%, a recall of 94.08%, and an F1 score of 94.74%. Comparative experiments with the BiLSTM-CRF, BERT-CRF, and BERT-BiLSTM-CRF models are conducted on the Boson dataset and our experimental dataset, demonstrating the superior performance of the ALBERT-BiLSTM-CRF model.

A General Model for Aggregating Annotations Across Simple, Complex, and Multi-Object Annotation Tasks

Human annotations are vital to supervised learning, yet annotators often disagree on the correct label, especially as annotation tasks increase in complexity. A common strategy to improve label quality is to ask multiple annotators to label the same item and then aggregate their labels. To date, many aggregation models have been proposed for simple categorical or numerical annotation tasks, but far less work has considered more complex annotation tasks, such as those involving open-ended, multivariate, or structured responses. Similarly, while a variety of bespoke models have been proposed for specific tasks, our work is the first we are aware of to introduce aggregation methods that generalize across many, diverse complex tasks, including sequence labeling, translation, syntactic parsing, ranking, bounding boxes, and keypoints. This generality is achieved by applying readily available task-specific distance functions, then devising a task-agnostic method to model these distances between labels, rather than the labels themselves. This article presents a unified treatment of our prior work on complex annotation modeling and extends that work with investigation of three new research questions. First, how do complex annotation task and dataset properties impact aggregation accuracy? Second, how should a task owner navigate the many modeling choices in order to maximize aggregation accuracy? Finally, what tests and diagnoses can verify that aggregation models are specified correctly for the given data? To understand how various factors impact accuracy and to inform model selection, we conduct large-scale simulation studies and broad experiments on real, complex datasets. Regarding testing, we introduce the concept of unit tests for aggregation models and present a suite of such tests to ensure that a given model is not mis-specified and exhibits expected behavior. Beyond investigating these research questions above, we discuss the foundational concept and nature of annotation complexity, present a new aggregation model as a conceptual bridge between traditional models and our own, and contribute a new general semisupervised learning method for complex label aggregation that outperforms prior work.

Parsing Clinical Trial Eligibility Criteria for Cohort Query by a Multi-Input Multi-Output Sequence Labeling Model.

To enable electronic screening of eligible patients for clinical trials, free-text clinical trial eligibility criteria should be translated to a computable format. Natural language processing (NLP) techniques have the potential to automate this process. In this study, we explored a supervised multi-input multi-output (MIMO) sequence labelling model to parse eligibility criteria into combinations of fact and condition tuples. Our experiments on a small manually annotated training dataset showed that that the performance of the MIMO framework with a BERT-based encoder using all the input sequences achieved an overall lenient-level AUROC of 0.61. Although the performance is suboptimal, representing eligibility criteria into logical and semantically clear tuples can potentially make subsequent translation of these tuples into database queries more reliable.

MRI‐Based Water Exchange Rate Across the Blood‐Brain‐Barrier is Associated with Diffusion MRI Free Water in Older Adults

AbstractBackgroundThe blood brain barrier (BBB) tightly regulates the clearance of waste from the central nervous system. Changes in BBB function may disrupt such clearance mechanisms, resulting in increased waste and unrestricted fluid, or free water (FW), which can be measured using diffusion‐weighted imaging. Here, we explored whether MRI‐based BBB water exchange rate (kw; measure of BBB function) is associated with FW within white matter tracts connecting the executive control network (ECN). We further explored whether FW within the ECN would likewise be associated with executive function performance.MethodFifty‐three older adults (ages 65‐85) without dementia were scanned using a 3‐Tesla MRI Siemens Magnetom Prisma with a 64‐channel head coil. A 3D gradient‐and‐spin‐echo diffusion‐prepared arterial spin labeling (DP‐ASL) sequence and a 126‐direction main diffusion MRI sequence using 4 b‐values (0, 500, 1000, and 2000 s/mm2) were acquired. Each participant’s mean kw values averaged over the entire brain were calculated from the DP‐ASL data. FW maps were calculated, registered to FMRIB space, and skeletonized using FSL’s tract‐based spatial statistics (TBSS). Skeletonized FW values were averaged across the white matter tracts connecting the ECN using a previously defined fMRI template. All participants completed the cognitive assessment from the Uniform Data Set Version 3 within one year of the scan date. Executive function was assessed for each participant based on a composite measure including digit span backwards and trails making part B test minus part A. A multivariate linear regression model first tested the association between whole brain kw values (predictor) and FW in the ECN as the dependent variable. A second multivariate linear regression model then tested the association between FW in the ECN (predictor) and EF performance as the dependent variable. Models controlled for age and sex.ResultsWhole brain kw values were negatively associated with FW in the ECN (r = ‐0.338, p = 0.031). FW in the ECN was negatively associated with EF performance (r = ‐0.318, p = 0.024).ConclusionOur results suggest that BBB dysfunction is associated with free water in large‐scale cognitive networks. Subsequent free water changes in these networks are linked with associated decreases in cognitive performance.

Cerebral Blood Flow and Arterial Transit Time Variations in Elders with Long COVID

AbstractBackgroundMany COVID‐19 patients experience persistant neurological symptoms that often extend beyond the period of acute infection, referred to as “Long COVID”, where most patients reported brain fog and cognitive dysfunction. While elderly individuals are more vulnerable to possible enduring cognitive impairments after acute COVID‐19 requiring hospitalization, there is increasing concern that older patients with Long COVID will be at high risk for developing Alzheimer’s disease (AD) and dementia. Although there is emerging recognition of Long COVID, its underlying neuropathology remains unknown. This study aimed to investigate neurovascular function using advanced MRI perfusion in elder patients with Long COVID.MethodWell‐matched elderly Long COVID patients (n = 14, mean age = 60.1±4.3 years, 12F, 2M) and control subjects (n = 25, mean age = 60.4±7.2 years, 19F, 6M) underwent neurocognitive testing as well as neuroimaging. Patients were seen 711.57 ± 165.02 days after the initial mild non‐hospitalized COVID‐19 infection. Clinical cognitive complaints of Long COVID patients included memory changes (n = 12, 85.7%), attention (n = 12, 85.7%), speech/writing (n = 9, 64.3%), and multitasking (n = 9, 64.3%). Brain perfusion was evaluated using an advanced 3D pseudo‐continuous arterial spin labeling (pCASL) sequence with Hadamard encoded multiple post‐labeling delays (PLDs), enabling estimation of Cerebral Blood Flow (CBF) and Arterial Transit Time (ATT) ATT and ATT corrected CBF.ResultConventional MRI scans (T1, T2, and FlAIR) appear normal in all subjects. Voxelwise comparisons between Long‐COVID and control subjects showed a significant global decrease in the ATT (p < 0.05, cluster corrected at a < 0.05), along default mode and other key networks, where there is a trend of decreased CBF (p<0.05, uncorrected) specifically in the frontal lobe in those with Long COVID.ConclusionThese preliminary results in an aging group indicate that neurocognitive effects of Long COVID could be attributed to neurovascular dysfunction, even in those cases with initial non‐hospitalized mild COVID‐19 of more than 500 days. The novel finding of diffusely decreased ATT could be something attributable to the unique neurovascular mechanism of Long COVID. Future longitudinal research following the progression of those elderly Long COVID patients with known abnormal neurovascular function to fully evaluate their risk for developing AD and dementia.

Cerebral Blood Flow and Arterial Transit Time Variations in Elders with Long COVID

AbstractBackgroundMany COVID‐19 patients experience persistant neurological symptoms that often extend beyond the period of acute infection, referred to as “Long COVID”, where most patients reported brain fog and cognitive dysfunction. While elderly individuals are more vulnerable to possible enduring cognitive impairments after acute COVID‐19 requiring hospitalization, there is increasing concern that older patients with Long COVID will be at high risk for developing Alzheimer’s disease (AD) and dementia. Although there is emerging recognition of Long COVID, its underlying neuropathology remains unknown. This study aimed to investigate neurovascular function using advanced MRI perfusion in elder patients with Long COVID.MethodWell‐matched elderly Long COVID patients (n = 14, mean age = 60.1±4.3 years, 12F, 2M) and control subjects (n = 25, mean age = 60.4±7.2 years, 19F, 6M) underwent neurocognitive testing as well as neuroimaging. Patients were seen 711.57 ± 165.02 days after the initial mild non‐hospitalized COVID‐19 infection. Clinical cognitive complaints of Long COVID patients included memory changes (n = 12, 85.7%), attention (n = 12, 85.7%), speech/writing (n = 9, 64.3%), and multitasking (n = 9, 64.3%). Brain perfusion was evaluated using an advanced 3D pseudo‐continuous arterial spin labeling (pCASL) sequence with Hadamard encoded multiple post‐labeling delays (PLDs), enabling estimation of Cerebral Blood Flow (CBF) and Arterial Transit Time (ATT) ATT and ATT corrected CBF.ResultConventional MRI scans (T1, T2, and FlAIR) appear normal in all subjects. Voxelwise comparisons between Long‐COVID and control subjects showed a significant global decrease in the ATT (p < 0.05, cluster corrected at α < 0.05), along default mode and other key networks, where there is a trend of decreased CBF (p<0.05, uncorrected) specifically in the frontal lobe in those with Long COVID.ConclusionThese preliminary results in an aging group indicate that neurocognitive effects of Long COVID could be attributed to neurovascular dysfunction, even in those cases with initial non‐hospitalized mild COVID‐19 of more than 500 days. The novel finding of diffusely decreased ATT could be something attributable to the unique neurovascular mechanism of Long COVID. Future longitudinal research following the progression of those elderly Long COVID patients with known abnormal neurovascular function to fully evaluate their risk for developing AD and dementia.