The University of Florida (UF) proposes to develop a nation-wide digital course to upskill biomedical researchers’ expertise in artificial intelligence (AI). The AI Passport for Biomedical Research (AIPassportBMR) overall objectives are to provide diverse biomedical researchers the opportunity to augment their skills in a concise and comprehensive course based on innovative learning techniques and will be the first scalable, self-correcting AI training program that is dynamic enough to withstand constant evolution of AI technologies. AIPassportBMR will focus on technical skills while providing mentorship on how to expand biomedical research into the AI field with highly collaborative sessions that include national leaders in medical AI. Moreover, due to the disparity in the current AI workforce, participants will be selected to increase diversity and inclusive excellence. Biomedical research and AI each align with institutional priorities, possess robust resources, and represent highly collaborative and successful scientific communities at UF. Designed as a digital experiential learning community, this program will enable predoctoral trainees and early-stage investigators in biomedical, behavioral, and clinical sciences to acquire the multidisciplinary skills necessary to integrate AI into their research while creating a nationwide community of likeminded mentors and peers. Our approach aligns with the objectives outlined in the IPERT initiate to provide skills development and mentoring to an inclusive audience through the following three overarching aims: Aim 1. AIPassportBMR Program: Develop the educational and technological infrastructure for community-driven experiential biomedical AI training using a See-Practice-Share-Reflect learning approach, Aim 2. Real-World Evaluation: Implement, evaluate, and fine-tune AIPassportBMR using an implementation mapping framework and Cognitive Theory of Culture to align instructional design with learners’ subcultural and educational needs, Aim 3. AI Digital Community of Practice: Build a support mosaic network of peers, mentors and coaches and the capacity for sustainable nationwide dissemination of the AI research training program. To further expand AIPassportBMR, the digital community learning platform program will be disseminated nationwide to build capacity for biomedical AI workforce development and support replication for all biomedical researchers. This program is committed to promoting diversity and inclusive excellence for its participants.

Human emotions are dynamic, multidimensional responses to challenges and opportunities that emerge from network interactions in the brain. Disruptions of these dynamics underlie emotional dysregulation in many mental disorders including anxiety and depression. To empirically study the neural basis of human emotion inference, experimenters often have observers view natural images varying in affective content, while at the same time recording their brain activity using electroencephalogram (EEG) and/or Functional magnetic resonance imaging (fMRI). Despite extensive research over the last few decades, much remains to be learned about the computational principles subserving the recognition of emotions in natural scenes. A major roadblock faced by empirical neuroscientists is the inability to carry out precisely manipulate human neural systems and test the consequences in imaging data. Deep Neural Networks (DNN), owing to their high relevance to human neural systems and extraordinary prediction capability, have become a promising tool for testing these sorts of hypotheses in swift and nearly costless computer simulations. The overarching goal of this project is to develop a neuroscience-inspired, DNN-based deep learning framework for emotion inference in real-world scenarios by synergistically integrating neuron-, circuit-, and system-level mechanisms. Recognizing that the state-of-the-art DNNs are centered on bottom-up and feedforward-only processing, which disagrees with the strong goal-oriented top-down modulation recurrence observed in the physiology, this project aims to enrich DNNs and enable closer AI-neuroscience interaction by incorporating goal-oriented top-down modulation and reciprocal interactions DNNs and test the model assumptions and predictions on neuroimaging data. To meet these goals, the project aims to develop a brain-inspired goal-oriented and bidirectional deep learning model for emotion inference. Despite the great promise shown by today?s deep learning as a framework for modeling biological vision, their architecture is limited to emulating the visual cortex for face/object/scene recognition and rarely goes beyond the inferotemporal cortex (IT), which is necessary for modeling high-level cognitive processes. In this project, we propose to build a biologically plausible deep learning architecture by integrating an in-silico amygdala module into the visual cortex architecture in DNN (the VCA model). The researchers hope to build neuron-, circuit-, and system-level modulation via goal-oriented attention priming, and multi-pathway predictive coding to 1) elucidate the mechanism of selectivity underlying preference and response to naturalistic emotions by artificial neurons; 2) differentiate fine-grained emotional responses via multi-path predictive coding, and 3) refine the neuroscientific understanding of human neuro-behavioral data by comparing attention priming and temporal generalization observed in simultaneous fMRI-EEG data to the computational observations using our brain-inspired VCA model. This project introduces two key innovations, both patterned after how brain operates, into DNN architecture and demonstrate their superior performance when applied to complex real-world tasks. Successful execution of the project can lead to the development of a new generation of AI-models that are inspired by neuroscience and that may in turn power neuroscience research.

There is a pressing need for effective interventions to remediate age-related cognitive decline and alter the trajectory toward Alzheimer’s disease. The NIA Alzheimer’s Disease Initiative funded Phase III Augmenting Cognitive Training in Older Adults (ACT) trial aimed to demonstrate that transcranial direct current stimulation (tDCS) paired with cognitive training could achieve this goal. The present study proposes a state of the art secondary data analysis of ACT trial data that will further this aim by 1) elucidate mechanism of action underlying response to tDCS treatment with CT, 2) address heterogeneity of response in tDCS augmented CT by determining how individual variation in the dose of electrical current delivered to the brain interacts with individual brain anatomical characteristics; and 3) refine the intervention strategy of tDCS paired with CT by evaluating methods for precision delivery targeted dosing characteristics to facilitate tDCS augmented outcomes. tDCS intervention to date, including ACT, apply a fixed dosing approach whereby a single stimulation intensity (e.g., 2mA) and set of electrode positions on the scalp (e.g., F3/F4) is applied to all participants/patients. However, our recent work has demonstrated that age-related changes in neuroanatomy as well as individual variability in head/brain structures (e.g., skull thickness) significantly impacts the distribution and intensity of electrical current induced in the brain from tDCS. This project will use person-specific MRI-derived finite element computational models of electric current characteristics (current intensity and direction of current flow) and new methods for enhancing the precision and accuracy of derived models to precisely quantify the heterogeneity of current delivery in older adults. We will leverage these individualized precision models with state-of-the-art support vector machine learning methods to determine the relationship between current characteristics and treatment response to tDCS and CT. We will leverage the inherent heterogeneity of neuroanatomy and fixed current delivery to provide insight in the not only which dosing parameters were associated with treatment response, but also brain region specific information to facilitate targeted delivery of stimulation in future trials. Further still, the current study will also pioneer new methods for calculation of precision dosing parameters for tDCS delivery to potentially optimize treatment response, as well as identify clinical and demographic characteristics that are associated with response to tDCS and CT in older adults. Leveraging a robust and comprehensive behavioral and multimodal neuroimaging data set for ACT with advanced computational methods, the proposed study will provide critical information for mechanism, heterogeneity of treatment response and a pathway to refined precision dosing approaches for remediating age- related cognitive decline and altering the trajectory of older adults toward Alzheimer’s disease.

There is a pressing need for effective interventions to remediate age-related cognitive decline and alter the trajectory toward Alzheimer’s disease. The NIA Alzheimer’s Disease Initiative funded Phase III Augmenting Cognitive Training in Older Adults (ACT) trial aimed to demonstrate that transcranial direct current stimulation (tDCS) paired with cognitive training could achieve this goal. The present study proposes a state of the art secondary data analysis of ACT trial data that will further this aim by 1) elucidate mechanism of action underlying response to tDCS treatment with CT, 2) address heterogeneity of response in tDCS augmented CT by determining how individual variation in the dose of electrical current delivered to the brain interacts with individual brain anatomical characteristics; and 3) refine the intervention strategy of tDCS paired with CT by evaluating methods for precision delivery targeted dosing characteristics to facilitate tDCS augmented outcomes. tDCS intervention to date, including ACT, apply a fixed dosing approach whereby a single stimulation intensity (e.g., 2mA) and set of electrode positions on the scalp (e.g., F3/F4) is applied to all participants/patients. However, our recent work has demonstrated that age-related changes in neuroanatomy as well as individual variability in head/brain structures (e.g., skull thickness) significantly impacts the distribution and intensity of electrical current induced in the brain from tDCS. This project will use person-specific MRI-derived finite element computational models of electric current characteristics (current intensity and direction of current flow) and new methods for enhancing the precision and accuracy of derived models to precisely quantify the heterogeneity of current delivery in older adults. We will leverage these individualized precision models with state-of-the-art support vector machine learning methods to determine the relationship between current characteristics and treatment response to tDCS and CT. We will leverage the inherent heterogeneity of neuroanatomy and fixed current delivery to provide insight in the not only which dosing parameters were associated with treatment response, but also brain region specific information to facilitate targeted delivery of stimulation in future trials. Further still, the current study will also pioneer new methods for calculation of precision dosing parameters for tDCS delivery to potentially optimize treatment response, as well as identify clinical and demographic characteristics that are associated with response to tDCS and CT in older adults. Leveraging a robust and comprehensive behavioral and multimodal neuroimaging data set for ACT with advanced computational methods, the proposed study will provide critical information for mechanism, heterogeneity of treatment response and a pathway to refined precision dosing approaches for remediating age- related cognitive decline and altering the trajectory of older adults toward Alzheimer’s disease.

Driven by its performance accuracy, machine learning (ML) has been used extensively for various applications in the healthcare domain. Despite its promising performance, researchers and the public have grown alarmed by two unsettling deficiencies of these otherwise useful and powerful models. First, there is a lack of trustworthiness - ML models are prone to interference or deception and exhibit erratic behaviors when in action dealing with unseen data, despite good practice during the training phase. Second, there is a lack of interpretability - ML models have been described as 'black-boxes' because there is little explanation for why the models make the predictions they do. This has called into question the applicability of ML to decision-making in critical scenarios such as image-based disease diagnostics or medical treatment recommendation. The ultimate goal of this project is to develop computational foundation for trustworthy and explainable Artificial Intelligence (AI), and offer a low-cost and non-invasive ML-based approach to early diagnosis of neurodegenerative diseases. In particular, the project aims to develop computational theories, ML algorithms, and prototype systems. The project includes developing principled solutions to trustworthy ML and making the ML prediction process transparent to end-users. The later will focus on explaining how and why an ML model makes such a prediction, while dissecting its underlying structure for deeper understanding. The proposed models are further extended to a multi-modal and spatial-temporal framework, an important aspect of applying ML models to healthcare. A verification framework with end-users is defined, which will further enhance the trustworthiness of the prototype systems. This project will benefit a variety of high-impact AI-based applications in terms of their explainability, trustworthy, and verifiability. It not only advances the research fronts of deep learning and AI, but also supports transformations in diagnosing neurodegenerative diseases.

This project will develop the computational foundation for trustworthy and explainable AI with several innovations. First, the project will systematically study the trustworthiness of ML systems. This will be measured by novel metrics such as, adversarial robustness and semantic saliency, and will be carried out to establish the theoretical basis and practical limits of trustworthiness of ML algorithms. Second, the project provides a paradigm shift for explainable AI, explaining how and why a ML model makes its prediction, moving away from ad-hoc explanations (i.e. what features are important to the prediction). A proof-based approach, which probes all the hidden layers of a given model to identify critical layers and neurons involved in a prediction from a local point of view, will be devised. Third, a verification framework, where users can verify the model's performance and explanations with proofs, will be designed to further enhance the trustworthiness of the system. Finally, the project also advances the frontier of neurodegenerative diseases early diagnosis from multimodal imaging and longitudinal data by: (i) identifying retinal vasculature biomarkers using proof-based probing in biomarker graph networks; (ii) connecting biomarkers of the retina and the brain vasculature via cross- modality explainable AI model; and, (iii) recognizing the longitudinal trajectory of vasculature biomarkers via a spatio-temporal recurrent explainable model. This synergistic effort between computer science and medicine will enable a wide range of applications to trustworthy and explainable AI for healthcare. The results of this project will be assimilated into the courses and summer programs that the research team have developed with specially designed projects to train students with trustworthy and explainable AI.

History has taught us that exposures to radionuclides can happen any day almost anywhere in the US and elsewhere and we have done little to prepare ourselves. Our ability to perform dosimetry modeling for such scenarios and efforts into biomarker and mitigation discovery are archaic and our tendency to rely on external beam radiation to model these is utterly misplaced. We should and we can do much better. This program centers on the hypothesis that radiation from internal emitters is very unevenly distributed within a body, amongst organs, and even within organs, tissues and cells. The half-life and decay schema of the radionuclide, its activity and concentration, particle size and morphology, and its chemical form and solubility are all critical, as are the route of uptake, tissue structure, genetic makeup, physiology, danger signaling and the crosstalk with the immune system. Conceptually this suggests that the analysis of radionuclide distribution requires measurements at the MESO, MICRO and NANO level for accurate dosimetry modeling and biokinetics analyses, that will much better align with biological endpoints, and therefore with meaningful countermeasure development. In many ways our program integrates the three main pillars of radiation science, namely radiation physics, radiation chemistry and radiation biology, taking into account pharmacokinetics and pharmacodynamics aspects of particle distribution at subcellular, cellular, and tissue levels. In other words, to understand the biological effects of internal emitters and find the best possible mitigation strategies a systematic study is called for, one that includes but is not limited to: a) radionuclide physical and chemical form and intravital migration, b) protracted exposure times, c) radiation quality parameters, d) novel virtual phantom modeling beyond few MACRO reference models ; e) novel biokinetics with sex- and age- specificity; f) MESO, MICRO and NANO scale histology and immunohistochemistry with integrated radionuclide distribution information; g) exploration of molecular biomarkers of radionuclide intake and contamination and h) countermeasures that modulate radionuclide distribution and possibly also improve DNA, cell and tissue repair. We have assembled a team with diverse scientific expertise that can tackle these challenges within an integrated program. There is an incredibly impressive technological toolbox at our disposal and our goal is to generate a meaningful blueprint for understanding and predicting biological consequences of exposure to radionuclides. The possible benefits of this program to the radiation research community and the general population are immense.

The purpose of the SHARE P01 research program project is to address HIV and alcohol use around three themes; 1) Emerging adulthood (ages 18 -29); 2) Self-management of HIV and alcohol; and 3) Translational behavioral science. Emerging adulthood is a developmental stage marked by significant change in social roles, expectations as a new adult, and increased responsibilities. It is also marked by poor HIV self- management and increased alcohol use. Emerging adults with HIV (hereafter called young people living with HIV; YPLWH) may face even more challenges given intersectional stigma. This age group continues to have very high rates of new HIV infections. Interventions designed specifically for the unique developmental challenges of emerging adults are needed, yet emerging adults are often included with older adults in intervention programs. The concept of self-management emerged concurrently within both the substance abuse and chronic illness literatures, and fits well with the developmental challenges of emerging adulthood. Self-management, a framework we have utilized in our work with YPLWH, refers to the ability to manage symptoms, treatments, lifestyle changes, and consequences of health conditions. Current research now identifies individual-level self-management skills such as self-control, decision-making, self-reinforcement, and problem solving as that protect against substance use and improve other health outcomes and can be embedded in the Information-Motivation-Behavioral Skills model. Although we have conducted multiple studies with YPLWH, only one intervention to date (Healthy Choices conducted by our team) improved both alcohol use and viral suppression in YPLWH in large trials. The goal of the SHARE P01 is to utilize advances in translational behavioral science to optimize behavioral interventions and define new developmentally- and culturally-appropriate intervention targets to improve self-management of alcohol and HIV in YPLWH. We will focus our efforts in Florida, a state hardest hit by the HIV epidemic but with a particularly strong academic- community partnership to support translation. We have assembled research teams to conduct self- management studies across the translational spectrum to address self-management and improve alcohol use and viral suppression (and thereby reduce transmission) in diverse YPLWH in Florida. The P01 will consist of three research projects (DEFINE, ENGAGE, and SUSTAIN), representing different stages on the translational spectrum and targeting different core competencies, supported by two cores (Community Engagement Core and Data Science Core). If successful, the SHARE P01 has the potential to greatly advance programs promoting self-management of HIV and alcohol use among a particularly vulnerable, but under-researched group, emerging adults living with HIV. SHARE also has a high potential for scale-up and implementation beyond Florida and across the United States.

As persons living with HIV (PLWH) live longer, approximately 50% will experience HIV-related cognitive dysfunction, which may affect daily activities, contribute to morbidity and mortality, and increase the likelihood of HIV transmission. Alcohol consumption among PLWH may further exacerbate long-term cognitive dysfunction, with the presumed mechanism involving the gut microbiome, microbial translocation, systemic inflammation, and ultimately neuroinflammation. However, there are many gaps in our understanding regarding the specific pathophysiological mechanisms, and a need to offer interventions that are effective and acceptable in helping PLWH to reduce drinking or to protect them against alcohol-related harm. The overarching goal of this P01 is to identify and ultimately implement new/improved, targeted interventions that will improve outcomes related to cognitive and brain dysfunction in persons with HIV who drink alcohol. The proposed P01 activity will extend our current line of research that forms the core of the Southern HIV & Alcohol Research Consortium (SHARC). The specific aims of this P01 are to: 1) improve our understanding of the specific mechanisms that connect the gut microbiome to cognitive and brain health outcomes in persons with HIV; 2) evaluate interventions that are intended to reduce the impact of alcohol on brain and cognitive health in persons with HIV; and 3) connect and extend the research activity from this P01 with the training programs and community engagement activity in the SHARC. Our P01 will utilize two cores that provide infrastructure to two Research Components (RC1, RC2). The two RC will together enroll 200 PLWH with at-risk drinking into clinical trials that share common timepoints and outcome assessments. RC1 will compare two strategies to extend contingency management to 60 days, using breathalyzers and wrist-worn biosensors to monitor drinking. RC2 uses a hybrid trial design to evaluate two biomedical interventions targeting the gut-brain axis. One intervention is a wearable, transcutaneous vagus nerve stimulator that is hypothesized to stimulate the autonomic nervous system, resulting in decreased inflammation and improved cognition. The other intervention is a probiotic supplement intended to improve the gut microbiome in persons with HIV and alcohol consumption. All participants in RC2, and a subset of those in RC1 will have neuroimaging at two timepoints. The Data Science Core will provide data management and analytical support, and will analyze existing data and the data collected from this P01 using a machine learning and AI approach to identify factors associated with intervention success or failure. The Administrative Core will provide scientific leadership, clinical research and recruitment infrastructure, and connection to the outstanding training programs, development opportunities, and community engagement provided by the SHARC. Our community engagement with diverse populations, and collection of acceptability data from clinical trial participants, will facilitate our readiness to scale up the most promising interventions and move towards implementation in the next phase of our research.

The number of persons living with HIV (PLWH) continues to increase in the United States. Alcohol consumption is a significant barrier to both achieving the goal of ending the HIV epidemic and preventing comorbidities among PLWH, as it contributes to both HIV transmission and HIV-related complications. Recent advances in data capture systems such as mHealth devices, medical imaging, and high-throughput biotechnologies make large/complex research and clinical datasets available, including survey data, multi-omics data, electronic medical records, and/or other sources of reliable information related to engagement in care. This offers tremendous potential of applying “big” data to extract knowledge and insights regarding fundamental physiology, understand the mechanisms by which the pathogenic effects of biotic and abiotic factors are realized, and identify potential intervention targets. We propose to integrate the disparate data sources maintained by our partners and then utilize the big data to address research questions in treating HIV and alcohol-related morbidity and mortality. Specifically, we will pursue the following three aims: 1) Integrate the disparate data sources through standardization, harmonization, and merging; 2) Develop a web-based data sharing platform including virtual data sharing communities, data privacy protection, streamlined data approval and access, and tracking of ongoing research activities; 3) Provide statistical support to junior investigators to use the data repository for exploratory data analysis and proposal development. The proposed study will tap into disparate data sources, unleash the potential of data and information, accelerate knowledge discovery, advance data-powered health, and transform discovery to improve health outcomes for PLWH.

Classical aversive conditioning is a well-established laboratory model for studying acquisition and extinction of defensive responses. In experimental animals, as well as in humans, research to date has been mainly focused on the role of limbic structures (e.g., the amygdala) in these responses. Recent evidence has begun to stress the important contribution by the brain’s sensory and attention control systems in maintaining the neural representations of conditioned responses and in facilitating their extinction. The proposed research breaks new ground by combining novel neuroimaging techniques with advanced computational methods to examine the brain’s visual and attention processes underlying fear acquisition and extinction in humans. Major advances will be made along three specific aims. In Aim 1, we characterize the brain network dynamics of visuocortical threat bias formation, extinction, and recall in a two-day learning paradigm. In Aim 2, we establish and test a computational model of threat bias generalization. In Aim 3, we examine the relation between individual differences in generalization and recall of conditioned visuocortical threat biases and individual differences in heightened autonomic reactivity to conditioned threat, a potential biomarker for assessing the predisposition to developing the disorders of fear and anxiety. It is expected that accomplishing these research aims will address two NIMH strategic priorities: defining the circuitry and brain networks underlying complex behaviors (Objective 1) and identifying and validating new targets for treatment that are derived from the understanding of disease mechanisms (Objective 3). It is further expected that this project will enable a paradigm shift in research on dysfunctional attention to threat from one that focuses primarily on limbic-prefrontal circuits to one that emphasizes the interactions among sensory, attention, executive control and limbic systems.

Across the globe, there has been a considerable growth in the number of people diagnosed with Parkinsonism. Estimates indicate that from 1990 to 2015 the number of Parkinsonism diagnoses doubled, with more than 6 million people currently carrying the diagnosis, and by year 2040, 12 and 14.2 million people will be diagnosed with Parkinsonism. Parkinson’s disease (PD), multiple system atrophy Parkinsonian variant (MSAp), and progressive supranuclear palsy (PSP) are neurodegenerative forms of Parkinsonism, which can be difficult to diagnose as they share similar motor and non-motor features, and they each have an increased chance of developing dementia. In the first five years of a PD diagnosis, about 58% of PD are misdiagnosed, and of these misdiagnoses about half have either MSA or PSP. Since PD, MSAp, and PSP require unique treatment plans and different medications, and clinical trials testing new medications require the correct diagnosis, there is an urgent need for both clinic ready and clinical-trial ready markers for differential diagnosis of PD, MSAp, and PSP. Over the past decade, we have developed diffusion imaging as an innovative biomarker for differentiating PD, MSAp, and PSP. In this proposal, we will leverage our extensive experience to create a web-based software tool that can process diffusion imaging data from anywhere in the world. We will disseminate and test the tool in the largest prospective cohort of participants with Parkinsonism (PD, MSAp, PSP), working closely with the Parkinson Study Group. The reason to test this in the Parkinson Study Group network, is because they are the community that evaluates Phase II and Phase III clinical trials in Parkinsonism. This web-based software tool will be capable of reading raw diffusion imaging data, performing quality assurance procedures, analyzing the data using a validated pipeline, and providing imaging metrics and diagnostic probability. We will test the performance of the wAID-P by enrolling 315 total subjects (105 PD, 105 MSAp, 105 PSP) across 21 sites in the Parkinson Study Group. Each site will perform imaging, clinical scales, diagnosis, and will upload the data to the web-based software tool. The clinical diagnosis will be blinded to the diagnostic algorithm and the imaging diagnosis will be compared to the movement disorders trained neurologist diagnosis. We will also enroll a portion of the cohort into a brain bank to ascertain pathological confirmation and to test the algorithm against cases with post-mortem diagnoses. The final outcome will be to disseminate a validated diagnostic algorithm to the Parkinson neurological and radiological community and to make it available to all on a website.

The temporal dynamics of blood flows through the network of cerebral arteries and veins provides a window into the health of the human brain. Since the brain is vulnerable to disrupted blood supply, brain dynamics serves as a crucial indicator for many kinds of neurological diseases such as stroke, brain cancer, and Alzheimer's disease. Existing efforts at characterizing brain dynamics have predominantly centered on 'isolated' models in which data from single-voxel, single-modality, and single-subject are characterized. However, the brain is a vast network, naturally connected on structural and functional levels, and multimodal imaging provides complementary information on this natural connectivity. Thus, the current isolated models are deemed not capable of offering the platform necessary to enable many of the potential advancements in understanding, diagnosing, and treating neurological and cognitive diseases, leaving a critical gap between the current computational modeling capabilities and the needs in brain dynamics analysis. This project aims to bridge this gap by exploiting multi-scale structural (voxel, vasculature, tissue) connectivity and multi-modal (anatomical, angiography, perfusion) connectivity to develop an integrated connective computational paradigm for characterizing and understanding brain dynamics.

The temporal dynamics of blood flows through the network of cerebral arteries and veins provides a window into the health of the human brain. Since the brain is vulnerable to disrupted blood supply, brain dynamics serves as a crucial indicator for many kinds of neurological diseases such as stroke, brain cancer, and Alzheimer's disease. Existing efforts at characterizing brain dynamics have predominantly centered on 'isolated' models in which data from single-voxel, single-modality, and single-subject are characterized. However, the brain is a vast network, naturally connected on structural and functional levels, and multimodal imaging provides complementary information on this natural connectivity. Thus, the current isolated models are deemed not capable of offering the platform necessary to enable many of the potential advancements in understanding, diagnosing, and treating neurological and cognitive diseases, leaving a critical gap between the current computational modeling capabilities and the needs in brain dynamics analysis. This project aims to bridge this gap by exploiting multi-scale structural (voxel, vasculature, tissue) connectivity and multi-modal (anatomical, angiography, perfusion) connectivity to develop an integrated connective computational paradigm for characterizing and understanding brain dynamics.

This project establishes the NSF Industry/University Collaborative Research Center for Big Learning (CBL). The vision is to create intelligence towards intelligence-driven society. Through catalyzing the fusion of diverse expertise from the consortium of faculty members, students, industry partners, and federal agencies, CBL seeks to create state-of-the-art deep learning methodologies and technologies and enable intelligent applications, transforming broad domains, such as business, healthcare, Internet-of-Things, and cybersecurity. This timely initiative creates a unique platform for empowering our next-generation talents with cutting-edge technologies of societal relevance and significance. This project establishes the NSF Industry/University Collaborative Research Center for Big Learning (CBL) at University of Florida (UF). With substantial breakthroughs in multiple modalities of challenges, such as computer vision, speech recognitions, and natural language understanding, the renaissance of machine intelligence is dawning. The CBL vision is to create intelligence towards intelligence-driven society. The mission is to pioneer novel deep learning algorithms, systems, and applications through unified and coordinated efforts in the CBL consortium. The UF Site will focus on intelligent platforms and applications and closely collaborate with other sites on deep learning algorithms, systems, and applications. The CBL will have broad transformative impacts in technologies, education, and society. CBL aims to create pioneering research and applications to address a broad spectrum of real-world challenges, making significant contributions and impacts to the deep learning community. The discoveries from CBL will make significant contributions to promote products and services of industry in general and CBL industry partners in particular. As the magnet of deep learning research and applications, CBL offers an ideal platform to nurture next-generation talents through world-class mentors from both academia and industry, disseminates the cutting-edge technologies, and facilitates industry/university collaboration and technology transfer. The center repository will be hosted at http://nsfcbl.org. The data, code, documents will be well organized and maintained on the CBL servers for the duration of the center for more than five years and beyond. The internal code repository will be managed by GitLab. After the software packages are well documented and tested, they will be released and managed by popular public code hosting services, such as GitHub and Bitbucket.

Human emotions are dynamic, multidimensional responses to challenges and opportunities, which emerge from network interactions in the brain. Disruptions of these network interactions underlie emotional dysregulation in many mental disorders, including anxiety and depression. Creating an AI-based model system that is informed and validated by known biological findings and can be used to carry out causal manipulations and test the consequences against human imaging data will thus be a highly significant development in the short term. The long-term goal is to understand how the human brain processes emotional information and how the process breaks down in mental disorders. NIH currently funds the team to record and analyze fMRI data from humans viewing natural images of varying emotional content. In the process of their research, they recognize that empirical studies such as theirs have significant limitations. Chief among them is the lack of ability to manipulate the system to establish the causal basis for the observed relationship between brain and behavior. The advent of AI, especially deep neural networks (DNNs), opens a new avenue to address this problem. Creating an AI-based model system that is informed and validated by known biological findings and that can be used to carry out causal manipulations and allow the testing of the consequences against human imaging data will thus be a significant step toward achieving our long-term goal.

Human emotions are dynamic, multidimensional responses to challenges and opportunities, which emerge from network interactions in the brain. Disruptions of these network interactions underlie emotional dysregulation in many mental disorders, including anxiety and depression. Creating an AI-based model system that is informed and validated by known biological findings and can be used to carry out causal manipulations and test the consequences against human imaging data will thus be a highly significant development in the short term. The long-term goal is to understand how the human brain processes emotional information and how the process breaks down in mental disorders. NIH currently funds the team to record and analyze fMRI data from humans viewing natural images of varying emotional content. In the process of their research, they recognize that empirical studies such as theirs have significant limitations. Chief among them is the lack of ability to manipulate the system to establish the causal basis for the observed relationship between brain and behavior. The advent of AI, especially deep neural networks (DNNs), opens a new avenue to address this problem. Creating an AI-based model system that is informed and validated by known biological findings and that can be used to carry out causal manipulations and allow the testing of the consequences against human imaging data will thus be a significant step toward achieving our long-term goal.

Vision-threatening diseases are one of the leading causes of blindness. DR, a common complication of diabetes, is the leading cause of blindness in American adults and the fastest growing disease threatening nearly 415 million diabetic patients worldwide. With professional eye imaging devices such as fundus cameras or Optical Coherence Tomography (OCT) scanners, most of the vision-threatening diseases can be curable if detected early. However, these diseases are still damaging people’s vision and leading to irreversible blindness, especially in rural areas and low-income communities where professional imaging devices and medical specialists are not available or not even affordable. There is an urgent need for early detection of vision-threatening diseases before vision loss in these areas. The current practice of DR screening relies on human experts to manually examine and diagnose DR in stereoscopic color fundus photographs at hospitals using professional fundus camera, which is time-consuming and infeasible for large-scale screening. It also puts an enormous burden on ophthalmologists and increases waiting lists and may undermine the standards of health care. Therein, automatic DR diagnosis systems with ophthalmologist-level performance are a critical and unmet need for DR screening. Electronic Health Records (EHR) have been increasingly implemented in US hospitals. Vast amounts of longitudinal patient data have been accumulated and are available electronically in structured tables, narrative text, and images. There is an increasing need for multimodal synergistic learning methods to link different data sources for clinical and translational studies. Recent emerging of AI technologies, especially deep learning (DL) algorithms, have greatly improved the performance of automated vision-disease diagnosis systems based on EHR data. However, the current systems are unable to detect early stage of vision-diseases. On the other hand, the clinical text provides detailed diagnosis, symptoms, and other critical observations documented by physicians, which could be a valuable resource to help lesion detection from medical images. Multimodal synergistic learning is the key to linking clinical text to medical images for lesion detection. This study proposes to leverage the narrative clinical text to improve lesion level detection from medical images via clinical Natural Language Processing (NLP). The team hypothesizes that early stage vision-threatening diseases can be detected using smartphone-based fundus camera via multimodal learning integrating clinical text and images with limited lesion-level labels via clinical NLP. The ultimate goal is to improve the early detection and prevention of vision-threatening diseases among rural and low-income areas by developing a low-cost, highly efficient system that can leverage both clinical narratives and images.

In the current era of invigorating brain research, there is emerging attention in leveraging machine learning in understanding the brain, particularly exploring the brain dynamics. With the ever-increasing amount of neuroscience data, new challenges and opportunities arise for brain dynamics analysis, such as data-driven reconstruction and computer-aided diagnosis. However, there are few attempts to bridge the semantic gaps between the raw brain imaging data and the diagnosis. We will develop robust and data-driven techniques for the purpose of modeling, estimating functional parameters from the limited data brain images, and making decision support practical based on efficient direct estimation of the brain dynamics. This is an interdisciplinary research combining medical image analysis, machine learning, neuroscience, and the domain expertise.