Crowdsourcing with the drift diffusion model of decision making.

Crowdsourcing involves the use of annotated labels with unknown reliability to estimate ground truth labels in datasets. A common task in crowdsourcing involves estimating reliabilities of annotators (such as through the sensitivities and specificities of annotators in the binary label setting). In the literature, beta or dirichlet distributions are typically imposed as priors on annotator reliability. In this study, we investigated the use of a neuroscientifically validated model of decision making, known as the drift-diffusion model, as a prior on the annotator labeling process. Two experiments were conducted on synthetically generated data with non-linear (sinusoidal) decision boundaries. Variational inference was used to predict ground truth labels and annotator related parameters. Our method performed similarly to a state-of-the-art technique (SVGPCR) in prediction of crowdsourced data labels and prediction through a crowdsourced-generated Gaussian process classifier. By relying on a neuroscientifically validated model of decision making to model annotator behavior, our technique opens the avenue of predicting neuroscientific biomarkers of annotators, expanding the scope of what may be learnt about annotators in crowdsourcing tasks.

Recent advancements and applications of deep learning in heart failure: Α systematic review.

BACKGROUND: Heart failure (HF), a global health challenge, requires innovative diagnostic and management approaches. The rapid evolution of deep learning (DL) in healthcare necessitates a comprehensive review to evaluate these developments and their potential to enhance HF evaluation, aligning clinical practices with technological advancements. OBJECTIVE: This review aims to systematically explore the contributions of DL technologies in the assessment of HF, focusing on their potential to improve diagnostic accuracy, personalize treatment strategies, and address the impact of comorbidities. METHODS: A thorough literature search was conducted across four major electronic databases: PubMed, Scopus, Web of Science and IEEE Xplore, yielding 137 articles that were subsequently categorized into five primary application areas: cardiovascular disease (CVD) classification, HF detection, image analysis, risk assessment, and other clinical analyses. The selection criteria focused on studies utilizing DL algorithms for HF assessment, not limited to HF detection but extending to any attempt in analyzing and interpreting HF-related data. RESULTS: The analysis revealed a notable emphasis on CVD classification and HF detection, with DL algorithms showing significant promise in distinguishing between affected individuals and healthy subjects. Furthermore, the review highlights DL's capacity to identify underlying cardiomyopathies and other comorbidities, underscoring its utility in refining diagnostic processes and tailoring treatment plans to individual patient needs. CONCLUSIONS: This review establishes DL as a key innovation in HF management, highlighting its role in advancing diagnostic accuracy and personalized care. The insights provided advocate for the integration of DL in clinical settings and suggest directions for future research to enhance patient outcomes in HF care.

Usformer: A small network for left atrium segmentation of 3D LGE MRI.

Left atrial (LA) fibrosis plays a vital role as a mediator in the progression of atrial fibrillation. 3D late gadolinium-enhancement (LGE) MRI has been proven effective in identifying LA fibrosis. Image analysis of 3D LA LGE involves manual segmentation of the LA wall, which is both lengthy and challenging. Automated segmentation poses challenges owing to the diverse intensities in data from various vendors, the limited contrast between LA and surrounding tissues, and the intricate anatomical structures of the LA. Current approaches relying on 3D networks are computationally intensive since 3D LGE MRIs and the networks are large. Regarding this issue, most researchers came up with two-stage methods: initially identifying the LA center using a scaled-down version of the MRIs and subsequently cropping the full-resolution MRIs around the LA center for final segmentation. We propose a lightweight transformer-based 3D architecture, Usformer, designed to precisely segment LA volume in a single stage, eliminating error propagation associated with suboptimal two-stage training. The transposed attention facilitates capturing the global context in large 3D volumes without significant computation requirements. Usformer outperforms the state-of-the-art supervised learning methods in terms of accuracy and speed. First, with the smallest Hausdorff Distance (HD) and Average Symmetric Surface Distance (ASSD), it achieved a dice score of 93.1% and 92.0% in the 2018 Atrial Segmentation Challenge and our local institutional dataset, respectively. Second, the number of parameters and computation complexity are largely reduced by 2.8x and 3.8x, respectively. Moreover, Usformer does not require a large dataset. When only 16 labeled MRI scans are used for training, Usformer achieves a 92.1% dice score in the challenge dataset. The proposed Usformer delineates the boundaries of the LA wall relatively accurately, which may assist in the clinical translation of LA LGE for planning catheter ablation of atrial fibrillation.

Focused active learning for histopathological image classification.

Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with artifacts, ambiguities, and class imbalances, as commonly seen in the medical field. The lack of precise uncertainty estimations leads to the acquisition of images with a low informative value. To address these challenges, we propose Focused Active Learning (FocAL), which combines a Bayesian Neural Network with Out-of-Distribution detection to estimate different uncertainties for the acquisition function. Specifically, the weighted epistemic uncertainty accounts for the class imbalance, aleatoric uncertainty for ambiguous images, and an OoD score for artifacts. We perform extensive experiments to validate our method on MNIST and the real-world Panda dataset for the classification of prostate cancer. The results confirm that other AL methods are 'distracted' by ambiguities and artifacts which harm the performance. FocAL effectively focuses on the most informative images, avoiding ambiguities and artifacts during acquisition. For both experiments, FocAL outperforms existing AL approaches, reaching a Cohen's kappa of 0.764 with only 0.69% of the labeled Panda data.

A physics based machine learning model to characterize room temperature semiconductor detectors in 3D.

Room temperature semiconductor radiation detectors (RTSD) for X-ray and γ -ray detection are vital tools for medical imaging, astrophysics and other applications. CdZnTe (CZT) has been the main RTSD for more than three decades with desired detection properties. In a typical pixelated configuration, CZT have electrodes on opposite ends. For advanced event reconstruction algorithms at sub-pixel level, detailed characterization of the RTSD is required in three dimensional (3D) space. However, 3D characterization of the material defects and charge transport properties in the sub-pixel regime is a labor intensive process with skilled manpower and novel experimental setups. Presently, state-of-art characterization is done over the bulk of the RTSD considering homogenous properties. In this paper, we propose a novel physics based machine learning (PBML) model to characterize the RTSD over a discretized sub-pixelated 3D volume which is assumed. Our novel approach is the first to characterize a full 3D charge transport model of the RTSD. In this work, we first discretize the RTSD between a pixelated electrodes spatially into 3 dimensions-x, y, and z. The resulting discretizations are termed as voxels in 3D space. In each voxel, the different physics based charge transport properties such as drift, trapping, detrapping and recombination of charges are modeled as trainable model weights. The drift of the charges considers second order non-linear motion which is observed in practice with the RTSDs. Based on the electron-hole pair injections as input to the PBML model, and signals at the electrodes, free and trapped charges (electrons and holes) as outputs of the model, the PBML model determines the trainable weights by backpropagating the loss function. The trained weights of the model represents one-to-one relation to that of the actual physical charge transport properties in a voxelized detector.

Characterizing major depressive disorder and substance use disorder using heatmaps and variable interactions: The utility of operant behavior and brain structure relationships.

BACKGROUND: Rates of depression and addiction have risen drastically over the past decade, but the lack of integrative techniques remains a barrier to accurate diagnoses of these mental illnesses. Changes in reward/aversion behavior and corresponding brain structures have been identified in those with major depressive disorder (MDD) and cocaine-dependence polysubstance abuse disorder (CD). Assessment of statistical interactions between computational behavior and brain structure may quantitatively segregate MDD and CD. METHODS: Here, 111 participants [40 controls (CTRL), 25 MDD, 46 CD] underwent structural brain MRI and completed an operant keypress task to produce computational judgment metrics. Three analyses were performed: (1) linear regression to evaluate groupwise (CTRL v. MDD v. CD) differences in structure-behavior associations, (2) qualitative and quantitative heatmap assessment of structure-behavior association patterns, and (3) the k-nearest neighbor machine learning approach using brain structure and keypress variable inputs to discriminate groups. RESULTS: This study yielded three primary findings. First, CTRL, MDD, and CD participants had distinct structure-behavior linear relationships, with only 7.8% of associations overlapping between any two groups. Second, the three groups had statistically distinct slopes and qualitatively distinct association patterns. Third, a machine learning approach could discriminate between CTRL and CD, but not MDD participants. CONCLUSIONS: These findings demonstrate that variable interactions between computational behavior and brain structure, and the patterns of these interactions, segregate MDD and CD. This work raises the hypothesis that analysis of interactions between operant tasks and structural neuroimaging might aide in the objective classification of MDD, CD and other mental health conditions.

Predicting COVID-19 Vaccination Uptake Using a Small and Interpretable Set of Judgment and Demographic Variables: Cross-Sectional Cognitive Science Study.

BACKGROUND: Despite COVID-19 vaccine mandates, many chose to forgo vaccination, raising questions about the psychology underlying how judgment affects these choices. Research shows that reward and aversion judgments are important for vaccination choice; however, no studies have integrated such cognitive science with machine learning to predict COVID-19 vaccine uptake. OBJECTIVE: This study aims to determine the predictive power of a small but interpretable set of judgment variables using 3 machine learning algorithms to predict COVID-19 vaccine uptake and interpret what profile of judgment variables was important for prediction. METHODS: We surveyed 3476 adults across the United States in December 2021. Participants answered demographic, COVID-19 vaccine uptake (ie, whether participants were fully vaccinated), and COVID-19 precaution questions. Participants also completed a picture-rating task using images from the International Affective Picture System. Images were rated on a Likert-type scale to calibrate the degree of liking and disliking. Ratings were computationally modeled using relative preference theory to produce a set of graphs for each participant (minimum R2>0.8). In total, 15 judgment features were extracted from these graphs, 2 being analogous to risk and loss aversion from behavioral economics. These judgment variables, along with demographics, were compared between those who were fully vaccinated and those who were not. In total, 3 machine learning approaches (random forest, balanced random forest [BRF], and logistic regression) were used to test how well judgment, demographic, and COVID-19 precaution variables predicted vaccine uptake. Mediation and moderation were implemented to assess statistical mechanisms underlying successful prediction. RESULTS: Age, income, marital status, employment status, ethnicity, educational level, and sex differed by vaccine uptake (Wilcoxon rank sum and chi-square P<.001). Most judgment variables also differed by vaccine uptake (Wilcoxon rank sum P<.05). A similar area under the receiver operating characteristic curve (AUROC) was achieved by the 3 machine learning frameworks, although random forest and logistic regression produced specificities between 30% and 38% (vs 74.2% for BRF), indicating a lower performance in predicting unvaccinated participants. BRF achieved high precision (87.8%) and AUROC (79%) with moderate to high accuracy (70.8%) and balanced recall (69.6%) and specificity (74.2%). It should be noted that, for BRF, the negative predictive value was <50% despite good specificity. For BRF and random forest, 63% to 75% of the feature importance came from the 15 judgment variables. Furthermore, age, income, and educational level mediated relationships between judgment variables and vaccine uptake. CONCLUSIONS: The findings demonstrate the underlying importance of judgment variables for vaccine choice and uptake, suggesting that vaccine education and messaging might target varying judgment profiles to improve uptake. These methods could also be used to aid vaccine rollouts and health care preparedness by providing location-specific details (eg, identifying areas that may experience low vaccination and high hospitalization).

Learning from crowds for automated histopathological image segmentation.

Automated semantic segmentation of histopathological images is an essential task in Computational Pathology (CPATH). The main limitation of Deep Learning (DL) to address this task is the scarcity of expert annotations. Crowdsourcing (CR) has emerged as a promising solution to reduce the individual (expert) annotation cost by distributing the labeling effort among a group of (non-expert) annotators. Extracting knowledge in this scenario is challenging, as it involves noisy annotations. Jointly learning the underlying (expert) segmentation and the annotators' expertise is currently a commonly used approach. Unfortunately, this approach is frequently carried out by learning a different neural network for each annotator, which scales poorly when the number of annotators grows. For this reason, this strategy cannot be easily applied to real-world CPATH segmentation. This paper proposes a new family of methods for CR segmentation of histopathological images. Our approach consists of two coupled networks: a segmentation network (for learning the expert segmentation) and an annotator network (for learning the annotators' expertise). We propose to estimate the annotators' behavior with only one network that receives the annotator ID as input, achieving scalability on the number of annotators. Our family is composed of three different models for the annotator network. Within this family, we propose a novel modeling of the annotator network in the CR segmentation literature, which considers the global features of the image. We validate our methods on a real-world dataset of Triple Negative Breast Cancer images labeled by several medical students. Our new CR modeling achieves a Dice coefficient of 0.7827, outperforming the well-known STAPLE (0.7039) and being competitive with the supervised method with expert labels (0.7723). The code is available at https://github.com/wizmik12/CRowd_Seg.

Deep Learning for Cardiovascular Imaging: A Review.

Importance: Artificial intelligence (AI), driven by advances in deep learning (DL), has the potential to reshape the field of cardiovascular imaging (CVI). While DL for CVI is still in its infancy, research is accelerating to aid in the acquisition, processing, and/or interpretation of CVI across various modalities, with several commercial products already in clinical use. It is imperative that cardiovascular imagers are familiar with DL systems, including a basic understanding of how they work, their relative strengths compared with other automated systems, and possible pitfalls in their implementation. The goal of this article is to review the methodology and application of DL to CVI in a simple, digestible fashion toward demystifying this emerging technology. Observations: At its core, DL is simply the application of a series of tunable mathematical operations that translate input data into a desired output. Based on artificial neural networks that are inspired by the human nervous system, there are several types of DL architectures suited to different tasks; convolutional neural networks are particularly adept at extracting valuable information from CVI data. We survey some of the notable applications of DL to tasks across the spectrum of CVI modalities. We also discuss challenges in the development and implementation of DL systems, including avoiding overfitting, preventing systematic bias, improving explainability, and fostering a human-machine partnership. Finally, we conclude with a vision of the future of DL for CVI. Conclusions and Relevance: Deep learning has the potential to meaningfully affect the field of CVI. Rather than a threat, DL could be seen as a partner to cardiovascular imagers in reducing technical burden and improving efficiency and quality of care. High-quality prospective evidence is still needed to demonstrate how the benefits of DL CVI systems may outweigh the risks.

Boost event-driven tactile learning with location spiking neurons.

Tactile sensing is essential for a variety of daily tasks. Inspired by the event-driven nature and sparse spiking communication of the biological systems, recent advances in event-driven tactile sensors and Spiking Neural Networks (SNNs) spur the research in related fields. However, SNN-enabled event-driven tactile learning is still in its infancy due to the limited representation abilities of existing spiking neurons and high spatio-temporal complexity in the event-driven tactile data. In this paper, to improve the representation capability of existing spiking neurons, we propose a novel neuron model called "location spiking neuron," which enables us to extract features of event-based data in a novel way. Specifically, based on the classical Time Spike Response Model (TSRM), we develop the Location Spike Response Model (LSRM). In addition, based on the most commonly-used Time Leaky Integrate-and-Fire (TLIF) model, we develop the Location Leaky Integrate-and-Fire (LLIF) model. Moreover, to demonstrate the representation effectiveness of our proposed neurons and capture the complex spatio-temporal dependencies in the event-driven tactile data, we exploit the location spiking neurons to propose two hybrid models for event-driven tactile learning. Specifically, the first hybrid model combines a fully-connected SNN with TSRM neurons and a fully-connected SNN with LSRM neurons. And the second hybrid model fuses the spatial spiking graph neural network with TLIF neurons and the temporal spiking graph neural network with LLIF neurons. Extensive experiments demonstrate the significant improvements of our models over the state-of-the-art methods on event-driven tactile learning, including event-driven tactile object recognition and event-driven slip detection. Moreover, compared to the counterpart artificial neural networks (ANNs), our SNN models are 10× to 100× energy-efficient, which shows the superior energy efficiency of our models and may bring new opportunities to the spike-based learning community and neuromorphic engineering. Finally, we thoroughly examine the advantages and limitations of various spiking neurons and discuss the broad applicability and potential impact of this work on other spike-based learning applications.

DeepCOVID-Fuse: A Multi-Modality Deep Learning Model Fusing Chest X-rays and Clinical Variables to Predict COVID-19 Risk Levels.

The COVID-19 pandemic has posed unprecedented challenges to global healthcare systems, highlighting the need for accurate and timely risk prediction models that can prioritize patient care and allocate resources effectively. This study presents DeepCOVID-Fuse, a deep learning fusion model that predicts risk levels in patients with confirmed COVID-19 by combining chest radiographs (CXRs) and clinical variables. The study collected initial CXRs, clinical variables, and outcomes (i.e., mortality, intubation, hospital length of stay, Intensive care units (ICU) admission) from February to April 2020, with risk levels determined by the outcomes. The fusion model was trained on 1657 patients (Age: 58.30 ± 17.74; Female: 807) and validated on 428 patients (56.41 ± 17.03; 190) from the local healthcare system and tested on 439 patients (56.51 ± 17.78; 205) from a different holdout hospital. The performance of well-trained fusion models on full or partial modalities was compared using DeLong and McNemar tests. Results show that DeepCOVID-Fuse significantly (p < 0.05) outperformed models trained only on CXRs or clinical variables, with an accuracy of 0.658 and an area under the receiver operating characteristic curve (AUC) of 0.842. The fusion model achieves good outcome predictions even when only one of the modalities is used in testing, demonstrating its ability to learn better feature representations across different modalities during training.

The Relationship Between a History of High-risk and Destructive Behaviors and COVID-19 Infection: Preliminary Study.

BACKGROUND: The COVID-19 pandemic has heightened mental health concerns, but the temporal relationship between mental health conditions and SARS-CoV-2 infection has not yet been investigated. Specifically, psychological issues, violent behaviors, and substance use were reported more during the COVID-19 pandemic than before the pandemic. However, it is unknown whether a prepandemic history of these conditions increases an individual's susceptibility to SARS-CoV-2. OBJECTIVE: This study aimed to better understand the psychological risks underlying COVID-19, as it is important to investigate how destructive and risky behaviors may increase a person's susceptibility to COVID-19. METHODS: In this study, we analyzed data from a survey of 366 adults across the United States (aged 18 to 70 years); this survey was administered between February and March of 2021. The participants were asked to complete the Global Appraisal of Individual Needs-Short Screener (GAIN-SS) questionnaire, which indicates an individual's history of high-risk and destructive behaviors and likelihood of meeting diagnostic criteria. The GAIN-SS includes 7 questions related to externalizing behaviors, 8 related to substance use, and 5 related to crime and violence; responses were given on a temporal scale. The participants were also asked whether they ever tested positive for COVID-19 and whether they ever received a clinical diagnosis of COVID-19. GAIN-SS responses were compared between those who reported and those who did not report COVID-19 to determine if those who reported COVID-19 also reported GAIN-SS behaviors (Wilcoxon rank sum test, α=.05). In total, 3 hypotheses surrounding the temporal relationships between the recency of GAIN-SS behaviors and COVID-19 infection were tested using proportion tests (α=.05). GAIN-SS behaviors that significantly differed (proportion tests, α=.05) between COVID-19 responses were included as independent variables in multivariable logistic regression models with iterative downsampling. This was performed to assess how well a history of GAIN-SS behaviors statistically discriminated between those who reported and those who did not report COVID-19. RESULTS: Those who reported COVID-19 more frequently indicated past GAIN-SS behaviors (Q<0.05). Furthermore, the proportion of those who reported COVID-19 was higher (Q<0.05) among those who reported a history of GAIN-SS behaviors; specifically, gambling and selling drugs were common across the 3 proportion tests. Multivariable logistic regression revealed that GAIN-SS behaviors, particularly gambling, selling drugs, and attention problems, accurately modeled self-reported COVID-19, with model accuracies ranging from 77.42% to 99.55%. That is, those who exhibited destructive and high-risk behaviors before and during the pandemic could be discriminated from those who did not exhibit these behaviors when modeling self-reported COVID-19. CONCLUSIONS: This preliminary study provides insights into how a history of destructive and risky behaviors influences infection susceptibility, offering possible explanations for why some persons may be more susceptible to COVID-19, potentially in relation to reduced adherence to prevention guidelines or not seeking vaccination.

Learning-based physical models of room-temperature semiconductor detectors with reduced data.

Room-temperature semiconductor radiation detectors (RTSD) have broad applications in medical imaging, homeland security, astrophysics and others. RTSDs such as CdZnTe, CdTe are often pixelated, and characterization of these detectors at micron level can benefit 3-D event reconstruction at sub-pixel level. Material defects alongwith electron and hole charge transport properties need to be characterized which requires several experimental setups and is labor intensive. The current state-of-art approaches characterize each detector pixel, considering the detector in bulk. In this article, we propose a new microscopic learning-based physical models of RTSD based on limited data compared to what is dictated by the physical equations. Our learning models uses a physical charge transport considering trapping centers. Our models learn these material properties in an indirect manner from the measurable signals at the electrodes and/or free and/or trapped charges distributed in the RTSD for electron-hole charge pair injections in the material. Based on the amount of data used during training our physical model, our algorithm characterizes the detector for charge drifts, trapping, detrapping and recombination coefficients considering multiple trapping centers or as a single equivalent trapping center. The RTSD is segmented into voxels spatially, and in each voxel, the material properties are modeled as learnable parameters. Depending on the amount of data, our models can characterize the RTSD either completely or in an equivalent manner.

Identifying Defects without a priori Knowledge in a Room-Temperature Semiconductor Detector Using Physics Inspired Machine Learning Model.

Room-temperature semiconductor radiation detectors (RTSD) such as CdZnTe are popular in Computed Tomography (CT) imaging and other applications. Transport properties and material defects with respect to electron and hole transport often need to be characterized, which is a labor intensive process. However, these defects often vary from one RTSD to another and are not known a priori during characterization of the material. In recent years, physics-inspired machine learning (PI-ML) models have been developed for the RTSDs which have the ability to characterize the defects in a RTSD by discretizing it volumetrically. These learning models capture the heterogeneity of the defects in the RTSD-which arises due to the fabrication process and the energy bands of elements in the RTSD. In those models, the different defects of RTSD-trapping, detrapping and recombination for electrons and holes-are present. However, these defects are often unknown. In this work, we show the capabilities of a PI-ML model which has been developed considering all the material defects to identify certain defects which are present (or absent). Additionally, these models can identify the defects over the volume of the RTSD in a discretized manner.

Towards Building a Distributed Virtual Flow Meter via Compressed Continual Learning.

A robust-accurate estimation of fluid flow is the main building block of a distributed virtual flow meter. Unfortunately, a big leap in algorithm development would be required for this objective to come to fruition, mainly due to the inability of current machine learning algorithms to make predictions outside the training data distribution. To improve predictions outside the training distribution, we explore the continual learning (CL) paradigm for accurately estimating the characteristics of fluid flow in pipelines. A significant challenge facing CL is the concept of catastrophic forgetting. In this paper, we provide a novel approach for how to address the forgetting problem via compressing the distributed sensor data to increase the capacity of the CL memory bank using a compressive learning algorithm. Through extensive experiments, we show that our approach provides around 8% accuracy improvement compared to other CL algorithms when applied to a real-world distributed sensor dataset collected from an oilfield. Noticeable accuracy improvement is also achieved when using our proposed approach with the CL benchmark datasets, achieving state-of-the-art accuracies for the CIFAR-10 dataset on blurry10 and blurry30 settings of 80.83% and 88.91%, respectively.

Impacts of Image Obfuscation on Fine-grained Activity Recognition in Egocentric Video.

Automated detection and validation of fine-grained human activities from egocentric vision has gained increased attention in recent years due to the rich information afforded by RGB images. However, it is not easy to discern how much rich information is necessary to detect the activity of interest reliably. Localization of hands and objects in the image has proven helpful to distinguishing between hand-related fine-grained activities. This paper describes the design of a hand-object-based mask obfuscation method (HOBM) and assesses its effect on automated recognition of fine-grained human activities. HOBM masks all pixels other than the hand and object in-hand, improving the protection of personal user information (PUI). We test a deep learning model trained with and without obfuscation using a public egocentric activity dataset with 86 class labels and achieve almost similar classification accuracies (2% decrease with obfuscation). Our findings show that it is possible to protect PUI at smaller image utility costs (loss of accuracy).

Detecting Screen Presence with Activity-Oriented RGB Camera in Egocentric Videos.

Screen time is associated with several health risk behaviors including mindless eating, sedentary behavior, and decreased academic performance. Screen time behavior is traditionally assessed with self-report measures, which are known to be burdensome, inaccurate, and imprecise. Recent methods to automatically detect screen time are geared more towards detecting television screens from wearable cameras that record high-resolution video. Activity-oriented wearable cameras (i.e., cameras oriented towards the wearer with a fisheye lens) have recently been designed and shown to reduce privacy concerns, yet pose a greater challenge in capturing screens due to their orientation and fewer pixels on target. Methods that detect screens from low-power, low-resolution wearable camera video are needed given the increased adoption of such devices in longitudinal studies. We propose a method that leverages deep learning algorithms and lower-resolution images from an activity-oriented camera to detect screen presence from multiple types of screens with high variability of pixel on target (e.g., near and far TV, smartphones, laptops, and tablets). We test our system in a real-world study comprising 10 individuals, 80 hours of data, and 1.2 million low-resolution RGB frames. Our results outperform existing state-of-the-art video screen detection methods yielding an F1-score of 81%. This paper demonstrates the potential for detecting screen-watching behavior in longitudinal studies using activity-oriented cameras, paving the way for a nuanced understanding of screen time's relationship with health risk behaviors.

A multicohort geometric deep learning study of age dependent cortical and subcortical morphologic interactions for fluid intelligence prediction.

The relationship of human brain structure to cognitive function is complex, and how this relationship differs between childhood and adulthood is poorly understood. One strong hypothesis suggests the cognitive function of Fluid Intelligence (Gf) is dependent on prefrontal cortex and parietal cortex. In this work, we developed a novel graph convolutional neural networks (gCNNs) for the analysis of localized anatomic shape and prediction of Gf. Morphologic information of the cortical ribbons and subcortical structures was extracted from T1-weighted MRIs within two independent cohorts, the Adolescent Brain Cognitive Development Study (ABCD; age: 9.93 ± 0.62 years) of children and the Human Connectome Project (HCP; age: 28.81 ± 3.70 years). Prediction combining cortical and subcortical surfaces together yielded the highest accuracy of Gf for both ABCD (R = 0.314) and HCP datasets (R = 0.454), outperforming the state-of-the-art prediction of Gf from any other brain measures in the literature. Across both datasets, the morphology of the amygdala, hippocampus, and nucleus accumbens, along with temporal, parietal and cingulate cortex consistently drove the prediction of Gf, suggesting a significant reframing of the relationship between brain morphology and Gf to include systems involved with reward/aversion processing, judgment and decision-making, motivation, and emotion.

A Joint Intensity-Neuromorphic Event Imaging System With Bandwidth-Limited Communication Channel.

We present a novel adaptive multimodal intensity-event algorithm to optimize an overall objective of object tracking under bit rate constraints for a host-chip architecture. The chip is a computationally resource-constrained device acquiring high-resolution intensity frames and events, while the host is capable of performing computationally expensive tasks. We develop a joint intensity-neuromorphic event rate-distortion compression framework with a quadtree (QT)-based compression of intensity and events scheme. The goal of this compression framework is to optimally allocate bits to the intensity frames and neuromorphic events based on the minimum distortion at a given communication channel capacity. The data acquisition on the chip is driven by the presence of objects of interest in the scene as detected by an object detector. The most informative intensity and event data are communicated to the host under rate constraints so that the best possible tracking performance is obtained. The detection and tracking of objects in the scene are done on the distorted data at the host. Intensity and events are jointly used in a fusion framework to enhance the quality of the distorted images, in order to improve the object detection and tracking performance. The performance assessment of the overall system is done in terms of the multiple object tracking accuracy (MOTA) score. Compared with using intensity modality only, there is an improvement in MOTA using both these modalities in different scenarios.

State-of-the-Art Deep Learning Methods on Electrocardiogram Data: Systematic Review.

BACKGROUND: Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient's health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals. OBJECTIVE: This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications. METHODS: The PubMed search engine was systematically searched by combining "deep learning" and keywords such as "ecg," "ekg," "electrocardiogram," "electrocardiography," and "electrocardiology." Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches. RESULTS: We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models. CONCLUSIONS: We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.