159 research outputs found
PLIS: A metabolomic response monitor to a lifestyle intervention study in older adults
No full textThe response to lifestyle intervention studies is often heterogeneous, especially in older adults. Subtle responses that may represent a health gain for individuals are not always detected by classical health variables, stressing the need for novel biomarkers that detect intermediate changes in metabolic, inflammatory, and immunity-related health. Here, our aim was to develop and validate a molecular multivariate biomarker maximally sensitive to the individual effect of a lifestyle intervention; the Personalized Lifestyle Intervention Status (PLIS). We used 1 H-NMR fasting blood metabolite measurements from before and after the 13-week combined physical and nutritional Growing Old TOgether (GOTO) lifestyle intervention study in combination with a fivefold cross-validation and a bootstrapping method to train a separate PLIS score for men and women. The PLIS scores consisted of 14 and four metabolites for females and males, respectively. Performance of the PLIS score in tracking health gain was illustrated by association of the sex-specific PLIS scores with several classical metabolic health markers, such as BMI, trunk fat%, fasting HDL cholesterol, and fasting insulin, the primary outcome of the GOTO study. We also showed that the baseline PLIS score indicated which participants respond positively to the intervention. Finally, we explored PLIS in an independent physical activity lifestyle intervention study, showing similar, albeit remarkably weaker, associations of PLIS with classical metabolic health markers. To conclude, we found that the sex-specific PLIS score was able to track the individual short-term metabolic health gain of the GOTO lifestyle intervention study. The methodology used to train the PLIS score potentially provides a useful instrument to track personal responses and predict the participant's health benefit in lifestyle interventions similar to the GOTO study.Pattern Recognition and Bioinformatic
The Marriage of Neurotechnologies and Artificial Intelligence: Ethical, regulatory, and technological aspects
No full textThe dual concepts of neurotechnology and artificial intelligence (AI) form an intriguing but also potentially explosive mixture because of its many ethical and legal implications. The advent of AI and the progress in neurotechnologies are reshaping the landscape not only in all scientific fields but also in everyday life both individually and collectively, ushering in a new era where the centrality, integrity and identity of humans is no longer a fact. Such tumultuous progress has implications at all levels, individual, societal, economical and political. Without the pretension of exploring the whole set of relevant aspects, we aim at providing a multi-disciplinary view on the main ethical, legal and societal issues stemming from neurotechnology and AI, by assessing them using keywords like trustworthiness, fairness, awareness, security, and privacy. In this paper, we propose an overview on the current scenario, taking a philosophical perspective in the light of ethics, and boiling it down to aspects closely related to the technological developments and the regulatory measures that are currently in-place and called for
DynaLay: An Introspective Approach to Dynamic Layer Selection for Deep Networks
No full textDeep learning models have become increasingly computationally intensive, requiring extensive computational resources and time for both training and inference. A significant contributing factor to this challenge is the uniform computational effort expended on each input example, regardless of its complexity. We introduce \textbf{DynaLay}, an alternative architecture that features a decision-making agent to adaptively select the most suitable layers for processing each input, thereby endowing the model with a remarkable level of introspection. DynaLay reevaluates more complex inputs during inference, adjusting the computational effort to optimize both performance and efficiency. The core of the system is a main model equipped with Fixed-Point Iterative (FPI) layers, capable of accurately approximating complex functions, paired with an agent that chooses these layers or a direct action based on the introspection of the models inner state. The model invests more time in processing harder examples, while minimal computation is required for easier ones. This introspective approach is a step toward developing deep learning models that ``think'' and ``ponder'', rather than ``ballistically'' produce answers. Our experiments demonstrate that DynaLay achieves accuracy comparable to conventional deep models while significantly reducing computational demands.Master of Science (MS)Computer Scienc
Time Permutation Approaches to Self-Supervised Dynamic Neuroimaging
No full textFunctional magnetic resonance imaging (fMRI) captures brain dynamics, offering crucial insights into brain function and disorders. However, its high-dimensional, complex, and noisy nature makes interpretation challenging. Ensuring model interpretability is essential, especially in high-stakes domains like medicine. Addressing this concern requires the development of specialized methods. Another significant challenge is data scarcity, as privacy laws often limit access to clinical data. In such cases, efficient pretraining techniques can be valuable, enabling models to work effectively with limited data while still producing reliable results.
To address the challenge of data scarcity, we propose a novel pretraining method called time reversal. Our approach leverages self-supervised learning to train a model on the temporal direction of ICA-preprocessed fMRI data. The pretrained model is then applied to downstream classification tasks for three disorders: schizophrenia, Alzheimer's disease, and autism. Through extensive experiments, we demonstrate that during pretraining, the model effectively learns temporal patterns from a separate dataset. This learned temporal information enhances performance in downstream tasks, as evidenced by improved AUC scores compared to models trained from scratch. Our findings highlight time reversal as a promising approach for capturing essential temporal features and transferring this knowledge to related tasks.
To enhance interpretability, we employ model introspection techniques to interpret the proposed pretraining method. We use one of the popular methods (Integrated Gradients) to generate saliency maps that offer post-hoc explanations for pretraining, while Earth Mover’s Distance (EMD) quantifies the temporal dynamics of salient features in the downstream schizophrenia classification task. The saliency maps reveal more concentrated and biologically meaningful salient features along the time axis, aligning with the episodic nature of schizophrenia. We show that, by linking model predictions to meaningful temporal patterns in brain activity, time reversal strengthens the connection between deep learning and clinical relevance.
Additionally, it is possible to enhance interpretability by making the intermediate representations of the input more transparent. In most deep learning frameworks, an encoder maps the input to a latent representation, which is then decoded and used for prediction. We develop methods to interpret the latent representations in our self-supervised pretraining task, which focuses on the order of time points. To achieve this, we pretrain a model using time reversal, extract its latent representations, and feed them into a probe (logistic regression) for further analysis. The fMRI data consists of 53 components, which are associated with seven functional brain networks: sensorimotor, visual, sub-cortical, cognitive control, default mode, cerebellar, and auditory. These networks represent connectivity patterns across different brain regions. We first establish a mapping between the fMRI components and the latent features, allowing us to analyze the learned representations in a biologically meaningful way. Using this mapping, we examine the coefficients of the logistic regression probe to determine the contribution of each brain region to schizophrenia classification. This approach provides deeper insights into how specific brain networks influence model predictions, bridging the gap between deep learning and neuroscience.Doctor of Philosophy (PhD)Computer Scienc
La Vie Dans Les Plis
No full textLa vie dans les plis was premiered at The Firehouse Space (Brooklyn, NY) on June 9, 2014, by violinist Karen Rostron and pianist Mirna Lekić. The piece\u27s title is a reference to an eponimous collection of texts by Belgian author Henri Michaux. There is no direct connection between Michaux\u27s text and the structure of the piece. This choice of title, in addition to its great poetic beauty, is meant as an acknowledgement of my indebtedness to Henri Michaux\u27s writings, and, more generally, to Surrealist - and Surrealist-influenced - poetry, for revealing to me the artistic value of a bold exploration of the self
Sharing privacy-sensitive access to neuroimaging and genetics data: a review and preliminary validation
No full textThe growth of data sharing initiatives for neuroimaging and genomics represents an exciting opportunity to confront the “small N” problem that plagues contemporary neuroimaging studies while further understanding the role genetic markers play in the function of the brain. When it is possible, open data sharing provides the most benefits. However, some data cannot be shared at all due to privacy concerns and/or risk of re-identification. Sharing other data sets is hampered by the proliferation of complex data use agreements (DUAs) which preclude truly automated data mining. These DUAs arise because of concerns about the privacy and confidentiality for subjects; though many do permit direct access to data, they often require a cumbersome approval process that can take months. An alternative approach is to only share data derivatives such as statistical summaries—the challenges here are to reformulate computational methods to quantify the privacy risks associated with sharing the results of those computations. For example, a derived map of gray matter is often as identifiable as a fingerprint. Thus alternative approaches to accessing data are needed. This paper reviews the relevant literature on differential privacy, a framework for measuring and tracking privacy loss in these settings, and demonstrates the feasibility of using this framework to calculate statistics on data distributed at many sites while still providing privacy.This document is protected by copyright and was first published by Frontiers. All rights reserved. It is reproduced with permission.Peer reviewe
Distributed System for MeshNet
No full textThis thesis explores the integration of Meshnet models with distributed learning techniques to enhance MRI brain scan analysis, with a focus on optimizing brain tissue segmentation while maintaining secure distributed systems. Through refining Meshnet's architecture and training strategies, the goal is to enhance accuracy in identifying brain segmentations. Distributed learning strategies, particularly centralized aggregation, are investigated to enable collaborative model training while ensuring data privacy. Additionally, Coinstac is integrated for secure gradient aggregation from diverse nodes, facilitating collaborative analysis without compromising confidentiality. Implementation of a serverless architecture using public clouds extends global accessibility while upholding robust security measures. The primary aim is to empower professionals with advanced tools for collaborative research.Master of Science (MS)Computer Scienc
Decentralized temporal independent component analysis: leveraging fMRI data in collaborative settings
No full textPeer reviewe
Deep Interpretability Methods for Neuroimaging
No full textBrain dynamics are highly complex and yet hold the key to understanding brain function and dysfunction. The dynamics captured by resting-state functional magnetic resonance imaging data are noisy, high-dimensional, and not readily interpretable. The typical approach of reducing this data to low-dimensional features and focusing on the most predictive features comes with strong assumptions and can miss essential aspects of the underlying dynamics. In contrast, introspection of discriminatively trained deep learning models may uncover disorder-relevant elements of the signal at the level of individual time points and spatial locations. Nevertheless, the difficulty of reliable training on high-dimensional but small-sample datasets and the unclear relevance of the resulting predictive markers prevent the widespread use of deep learning in functional neuroimaging. In this dissertation, we address these challenges by proposing a deep learning framework to learn from high-dimensional dynamical data while maintaining stable, ecologically valid interpretations. The developed model is pre-trainable and alleviates the need to collect an enormous amount of neuroimaging samples to achieve optimal training.
We also provide a quantitative validation module, Retain and Retrain (RAR), that can objectively verify the higher predictability of the dynamics learned by the model. Results successfully demonstrate that the proposed framework enables learning the fMRI dynamics directly from small data and capturing compact, stable interpretations of features predictive of function and dysfunction. We also comprehensively reviewed deep interpretability literature in the neuroimaging domain. Our analysis reveals the ongoing trend of interpretability practices in neuroimaging studies and identifies the gaps that should be addressed for effective human-machine collaboration in this domain.
This dissertation also proposed a post hoc interpretability method, Geometrically Guided Integrated Gradients (GGIG), that leverages geometric properties of the functional space as learned by a deep learning model. With extensive experiments and quantitative validation on MNIST and ImageNet datasets, we demonstrate that GGIG outperforms integrated gradients (IG), which is considered to be a popular interpretability method in the literature. As GGIG is able to identify the contours of the discriminative regions in the input space, GGIG may be useful in various medical imaging tasks where fine-grained localization as an explanation is beneficial.Doctor of Philosophy (PhD)Computer Scienc
- …
