Efficient Federated Learning for distributed NeuroImaging Data.

Recent advancements in neuroimaging have led to greater data sharing among the scientific community. However, institutions frequently maintain control over their data, citing concerns related to research culture, privacy, and accountability. This creates a demand for innovative tools capable of analyzing amalgamated datasets without the need to transfer actual data between entities. To address this challenge, we propose a decentralized sparse federated learning (FL) strategy. This approach emphasizes local training of sparse models to facilitate efficient communication within such frameworks. By capitalizing on model sparsity and selectively sharing parameters between client sites during the training phase, our method significantly lowers communication overheads. This advantage becomes increasingly pronounced when dealing with larger models and accommodating the diverse resource capabilities of various sites. We demonstrate the effectiveness of our approach through the application to the Adolescent Brain Cognitive Development (ABCD) dataset.

A deep learning approach for mental health quality prediction using functional network connectivity and assessment data.

While one can characterize mental health using questionnaires, such tools do not provide direct insight into the underlying biology. By linking approaches that visualize brain activity to questionnaires in the context of individualized prediction, we can gain new insights into the biology and behavioral aspects of brain health. Resting-state fMRI (rs-fMRI) can be used to identify biomarkers of these conditions and study patterns of abnormal connectivity. In this work, we estimate mental health quality for individual participants using static functional network connectivity (sFNC) data from rs-fMRI. The deep learning model uses the sFNC data as input to predict four categories of mental health quality and visualize the neural patterns indicative of each group. We used guided gradient class activation maps (guided Grad-CAM) to identify the most discriminative sFNC patterns. The effectiveness of this model was validated using the UK Biobank dataset, in which we showed that our approach outperformed four alternative models by 4-18% accuracy. The proposed model's performance evaluation yielded a classification accuracy of 76%, 78%, 88%, and 98% for the excellent, good, fair, and poor mental health categories, with poor mental health accuracy being the highest. The findings show distinct sFNC patterns across each group. The patterns associated with excellent mental health consist of the cerebellar-subcortical regions, whereas the most prominent areas in the poor mental health category are in the sensorimotor and visual domains. Thus the combination of rs-fMRI and deep learning opens a promising path for developing a comprehensive framework to evaluate and measure mental health. Moreover, this approach had the potential to guide the development of personalized interventions and enable the monitoring of treatment response. Overall this highlights the crucial role of advanced imaging modalities and deep learning algorithms in advancing our understanding and management of mental health.

Self-supervised multimodal learning for group inferences from MRI data: Discovering disorder-relevant brain regions and multimodal links.

In recent years, deep learning approaches have gained significant attention in predicting brain disorders using neuroimaging data. However, conventional methods often rely on single-modality data and supervised models, which provide only a limited perspective of the intricacies of the highly complex brain. Moreover, the scarcity of accurate diagnostic labels in clinical settings hinders the applicability of the supervised models. To address these limitations, we propose a novel self-supervised framework for extracting multiple representations from multimodal neuroimaging data to enhance group inferences and enable analysis without resorting to labeled data during pre-training. Our approach leverages Deep InfoMax (DIM), a self-supervised methodology renowned for its efficacy in learning representations by estimating mutual information without the need for explicit labels. While DIM has shown promise in predicting brain disorders from single-modality MRI data, its potential for multimodal data remains untapped. This work extends DIM to multimodal neuroimaging data, allowing us to identify disorder-relevant brain regions and explore multimodal links. We present compelling evidence of the efficacy of our multimodal DIM analysis in uncovering disorder-relevant brain regions, including the hippocampus, caudate, insula, - and multimodal links with the thalamus, precuneus, and subthalamus hypothalamus. Our self-supervised representations demonstrate promising capabilities in predicting the presence of brain disorders across a spectrum of Alzheimer's phenotypes. Comparative evaluations against state-of-the-art unsupervised methods based on autoencoders, canonical correlation analysis, and supervised models highlight the superiority of our proposed method in achieving improved classification performance, capturing joint information, and interpretability capabilities. The computational efficiency of the decoder-free strategy enhances its practical utility, as it saves compute resources without compromising performance. This work offers a significant step forward in addressing the challenge of understanding multimodal links in complex brain disorders, with potential applications in neuroimaging research and clinical diagnosis.

Revisiting Functional Dysconnectivity: a Review of Three Model Frameworks in Schizophrenia.

PURPOSE OF REVIEW: Over the last decade, evidence suggests that a combination of behavioral and neuroimaging findings can help illuminate changes in functional dysconnectivity in schizophrenia. We review the recent connectivity literature considering several vital models, considering connectivity findings, and relationships with clinical symptoms. We reviewed resting state fMRI studies from 2017 to 2023. We summarized the role of two sets of brain networks (cerebello-thalamo-cortical (CTCC) and the triple network set) across three hypothesized models of schizophrenia etiology (neurodevelopmental, vulnerability-stress, and neurotransmitter hypotheses). RECENT FINDINGS: The neurotransmitter and neurodevelopmental models best explained CTCC-subcortical dysfunction, which was consistently connected to symptom severity and motor symptoms. Triple network dysconnectivity was linked to deficits in executive functioning, and the salience network (SN)-default mode network dysconnectivity was tied to disordered thought and attentional deficits. This paper links behavioral symptoms of schizophrenia (symptom severity, motor, executive functioning, and attentional deficits) to various hypothesized mechanisms.

Chromatic fusion: Generative multimodal neuroimaging data fusion provides multi-informed insights into schizophrenia.

This work proposes a novel generative multimodal approach to jointly analyze multimodal data while linking the multimodal information to colors. We apply our proposed framework, which disentangles multimodal data into private and shared sets of features from pairs of structural (sMRI), functional (sFNC and ICA), and diffusion MRI data (FA maps). With our approach, we find that heterogeneity in schizophrenia is potentially a function of modality pairs. Results show (1) schizophrenia is highly multimodal and includes changes in specific networks, (2) non-linear relationships with schizophrenia are observed when interpolating among shared latent dimensions, and (3) we observe a decrease in the modularity of functional connectivity and decreased visual-sensorimotor connectivity for schizophrenia patients for the FA-sFNC and sMRI-sFNC modality pairs, respectively. Additionally, our results generally indicate decreased fractional corpus callosum anisotropy, and decreased spatial ICA map and voxel-based morphometry strength in the superior frontal lobe as found in the FA-sFNC, sMRI-FA, and sMRI-ICA modality pair clusters. In sum, we introduce a powerful new multimodal neuroimaging framework designed to provide a rich and intuitive understanding of the data which we hope challenges the reader to think differently about how modalities interact.

A deep learning approach to estimating initial conditions of Brain Network Models in reference to measured fMRI data.

Introduction: Brain Network Models (BNMs) are mathematical models that simulate the activity of the entire brain. These models use neural mass models to represent local activity in different brain regions that interact with each other via a global structural network. Researchers have been interested in using these models to explain measured brain activity, particularly resting state functional magnetic resonance imaging (rs-fMRI). BNMs have shown to produce similar properties as measured data computed over longer periods of time such as average functional connectivity (FC), but it is unclear how well simulated trajectories compare to empirical trajectories on a timepoint-by-timepoint basis. During task fMRI, the relevant processes pertaining to task occur over the time frame of the hemodynamic response function, and thus it is important to understand how BNMs capture these dynamics over these short periods. Methods: To test the nature of BNMs' short-term trajectories, we used a deep learning technique called Neural ODE to simulate short trajectories from estimated initial conditions based on observed fMRI measurements. To compare to previous methods, we solved for the parameterization of a specific BNM, the Firing Rate Model, using these short-term trajectories as a metric. Results: Our results show an agreement between parameterization of using previous long-term metrics with the novel short term metrics exists if also considering other factors such as the sensitivity in accuracy with relative to changes in structural connectivity, and the presence of noise. Discussion: Therefore, we conclude that there is evidence that by using Neural ODE, BNMs can be simulated in a meaningful way when comparing against measured data trajectories, although future studies are necessary to establish how BNM activity relate to behavioral variables or to faster neural processes during this time period.

Enhancing collaborative neuroimaging research: introducing COINSTAC Vaults for federated analysis and reproducibility.

Collaborative neuroimaging research is often hindered by technological, policy, administrative, and methodological barriers, despite the abundance of available data. COINSTAC (The Collaborative Informatics and Neuroimaging Suite Toolkit for Anonymous Computation) is a platform that successfully tackles these challenges through federated analysis, allowing researchers to analyze datasets without publicly sharing their data. This paper presents a significant enhancement to the COINSTAC platform: COINSTAC Vaults (CVs). CVs are designed to further reduce barriers by hosting standardized, persistent, and highly-available datasets, while seamlessly integrating with COINSTAC's federated analysis capabilities. CVs offer a user-friendly interface for self-service analysis, streamlining collaboration, and eliminating the need for manual coordination with data owners. Importantly, CVs can also be used in conjunction with open data as well, by simply creating a CV hosting the open data one would like to include in the analysis, thus filling an important gap in the data sharing ecosystem. We demonstrate the impact of CVs through several functional and structural neuroimaging studies utilizing federated analysis showcasing their potential to improve the reproducibility of research and increase sample sizes in neuroimaging studies.

Chromatic fusion: generative multimodal neuroimaging data fusion provides multi-informed insights into schizophrenia.

This work proposes a novel generative multimodal approach to jointly analyze multimodal data while linking the multimodal information to colors. By linking colors to private and shared information from modalities, we introduce chromatic fusion, a framework that allows for intuitively interpreting multimodal data. We test our framework on structural, functional, and diffusion modality pairs. In this framework, we use a multimodal variational autoencoder to learn separate latent subspaces; a private space for each modality, and a shared space between both modalities. These subspaces are then used to cluster subjects, and colored based on their distance from the variational prior, to obtain meta-chromatic patterns (MCPs). Each subspace corresponds to a different color, red is the private space of the first modality, green is the shared space, and blue is the private space of the second modality. We further analyze the most schizophrenia-enriched MCPs for each modality pair and find that distinct schizophrenia subgroups are captured by schizophrenia-enriched MCPs for different modality pairs, emphasizing schizophrenia's heterogeneity. For the FA-sFNC, sMRI-ICA, and sMRI-ICA MCPs, we generally find decreased fractional corpus callosum anisotropy and decreased spatial ICA map and voxel-based morphometry strength in the superior frontal lobe for schizophrenia patients. To additionally highlight the importance of the shared space between modalities, we perform a robustness analysis of the latent dimensions in the shared space across folds. These robust latent dimensions are subsequently correlated with schizophrenia to reveal that for each modality pair, multiple shared latent dimensions strongly correlate with schizophrenia. In particular, for FA-sFNC and sMRI-sFNC shared latent dimensions, we respectively observe a reduction in the modularity of the functional connectivity and a decrease in visual-sensorimotor connectivity for schizophrenia patients. The reduction in modularity couples with increased fractional anisotropy in the left part of the cerebellum dorsally. The reduction in the visual-sensorimotor connectivity couples with a reduction in the voxel-based morphometry generally but increased dorsal cerebellum voxel-based morphometry. Since the modalities are trained jointly, we can also use the shared space to try and reconstruct one modality from the other. We show that cross-reconstruction is possible with our network and is generally much better than depending on the variational prior. In sum, we introduce a powerful new multimodal neuroimaging framework designed to provide a rich and intuitive understanding of the data that we hope challenges the reader to think differently about how modalities interact.

GLACIER: GLASS-BOX TRANSFORMER FOR INTERPRETABLE DYNAMIC NEUROIMAGING.

Deep learning models can perform as well or better than humans in many tasks, especially vision related. Almost exclusively, these models are used to perform classification or prediction. However, deep learning models are usually of black-box nature, and it is often difficult to interpret the model or the features. The lack of interpretability causes a restrain from applying deep learning to fields such as neuroimaging, where the results must be transparent, and interpretable. Therefore, we present a 'glass-box' deep learning model and apply it to the field of neuroimaging. Our model mixes spatial and temporal dimensions in succession to estimate dynamic connectivity between the brain's intrinsic networks. The interpretable connectivity matrices produced by our model result in beating state-of-the-art models on many tasks using multiple functional MRI datasets. More importantly, our model estimates task-based flexible connectivity matrices, unlike static methods such as Pearson's correlation coefficients.

Automated Interpretation of Clinical Electroencephalograms Using Artificial Intelligence.

Importance: Electroencephalograms (EEGs) are a fundamental evaluation in neurology but require special expertise unavailable in many regions of the world. Artificial intelligence (AI) has a potential for addressing these unmet needs. Previous AI models address only limited aspects of EEG interpretation such as distinguishing abnormal from normal or identifying epileptiform activity. A comprehensive, fully automated interpretation of routine EEG based on AI suitable for clinical practice is needed. Objective: To develop and validate an AI model (Standardized Computer-based Organized Reporting of EEG-Artificial Intelligence [SCORE-AI]) with the ability to distinguish abnormal from normal EEG recordings and to classify abnormal EEG recordings into categories relevant for clinical decision-making: epileptiform-focal, epileptiform-generalized, nonepileptiform-focal, and nonepileptiform-diffuse. Design, Setting, and Participants: In this multicenter diagnostic accuracy study, a convolutional neural network model, SCORE-AI, was developed and validated using EEGs recorded between 2014 and 2020. Data were analyzed from January 17, 2022, until November 14, 2022. A total of 30 493 recordings of patients referred for EEG were included into the development data set annotated by 17 experts. Patients aged more than 3 months and not critically ill were eligible. The SCORE-AI was validated using 3 independent test data sets: a multicenter data set of 100 representative EEGs evaluated by 11 experts, a single-center data set of 9785 EEGs evaluated by 14 experts, and for benchmarking with previously published AI models, a data set of 60 EEGs with external reference standard. No patients who met eligibility criteria were excluded. Main Outcomes and Measures: Diagnostic accuracy, sensitivity, and specificity compared with the experts and the external reference standard of patients' habitual clinical episodes obtained during video-EEG recording. Results: The characteristics of the EEG data sets include development data set (N = 30 493; 14 980 men; median age, 25.3 years [95% CI, 1.3-76.2 years]), multicenter test data set (N = 100; 61 men, median age, 25.8 years [95% CI, 4.1-85.5 years]), single-center test data set (N = 9785; 5168 men; median age, 35.4 years [95% CI, 0.6-87.4 years]), and test data set with external reference standard (N = 60; 27 men; median age, 36 years [95% CI, 3-75 years]). The SCORE-AI achieved high accuracy, with an area under the receiver operating characteristic curve between 0.89 and 0.96 for the different categories of EEG abnormalities, and performance similar to human experts. Benchmarking against 3 previously published AI models was limited to comparing detection of epileptiform abnormalities. The accuracy of SCORE-AI (88.3%; 95% CI, 79.2%-94.9%) was significantly higher than the 3 previously published models (P < .001) and similar to human experts. Conclusions and Relevance: In this study, SCORE-AI achieved human expert level performance in fully automated interpretation of routine EEGs. Application of SCORE-AI may improve diagnosis and patient care in underserved areas and improve efficiency and consistency in specialized epilepsy centers.

Enhancing Collaborative Neuroimaging Research: Introducing COINSTAC Vaults for Federated Analysis and Reproducibility.

Collaborative neuroimaging research is often hindered by technological, policy, administrative, and methodological barriers, despite the abundance of available data. COINSTAC is a platform that successfully tackles these challenges through federated analysis, allowing researchers to analyze datasets without publicly sharing their data. This paper presents a significant enhancement to the COINSTAC platform: COINSTAC Vaults (CVs). CVs are designed to further reduce barriers by hosting standardized, persistent, and highly-available datasets, while seamlessly integrating with COINSTAC's federated analysis capabilities. CVs offer a user-friendly interface for self-service analysis, streamlining collaboration and eliminating the need for manual coordination with data owners. Importantly, CVs can also be used in conjunction with open data as well, by simply creating a CV hosting the open data one would like to include in the analysis, thus filling an important gap in the data sharing ecosystem. We demonstrate the impact of CVs through several functional and structural neuroimaging studies utilizing federated analysis showcasing their potential to improve the reproducibility of research and increase sample sizes in neuroimaging studies.

Causal Learning through Deliberate Undersampling.

Domain scientists interested in causal mechanisms are usually limited by the frequency at which they can collect the measurements of social, physical, or biological systems. A common and plausible assumption is that higher measurement frequencies are the only way to gain more informative data about the underlying dynamical causal structure. This assumption is a strong driver for designing new, faster instruments, but such instruments might not be feasible or even possible. In this paper, we show that this assumption is incorrect: there are situations in which we can gain additional information about the causal structure by measuring more slowly than our current instruments. We present an algorithm that uses graphs at multiple measurement timescales to infer underlying causal structure, and show that inclusion of structures at slower timescales can nonetheless reduce the size of the equivalence class of possible causal structures. We provide simulation data about the probability of cases in which deliberate undersampling yields a gain, as well as the size of this gain.

Through the looking glass: Deep interpretable dynamic directed connectivity in resting fMRI.

Brain network interactions are commonly assessed via functional (network) connectivity, captured as an undirected matrix of Pearson correlation coefficients. Functional connectivity can represent static and dynamic relations, but often these are modeled using a fixed choice for the data window Alternatively, deep learning models may flexibly learn various representations from the same data based on the model architecture and the training task. However, the representations produced by deep learning models are often difficult to interpret and require additional posthoc methods, e.g., saliency maps. In this work, we integrate the strengths of deep learning and functional connectivity methods while also mitigating their weaknesses. With interpretability in mind, we present a deep learning architecture that exposes a directed graph layer that represents what the model has learned about relevant brain connectivity. A surprising benefit of this architectural interpretability is significantly improved accuracy in discriminating controls and patients with schizophrenia, autism, and dementia, as well as age and gender prediction from functional MRI data. We also resolve the window size selection problem for dynamic directed connectivity estimation as we estimate windowing functions from the data, capturing what is needed to estimate the graph at each time-point. We demonstrate efficacy of our method in comparison with multiple existing models that focus on classification accuracy, unlike our interpretability-focused architecture. Using the same data but training different models on their own discriminative tasks we are able to estimate task-specific directed connectivity matrices for each subject. Results show that the proposed approach is also more robust to confounding factors compared to standard dynamic functional connectivity models. The dynamic patterns captured by our model are naturally interpretable since they highlight the intervals in the signal that are most important for the prediction. The proposed approach reveals that differences in connectivity among sensorimotor networks relative to default-mode networks are an important indicator of dementia and gender. Dysconnectivity between networks, specially sensorimotor and visual, is linked with schizophrenic patients, however schizophrenic patients show increased intra-network default-mode connectivity compared to healthy controls. Sensorimotor connectivity was important for both dementia and schizophrenia prediction, but schizophrenia is more related to dysconnectivity between networks whereas, dementia bio-markers were mostly intra-network connectivity.

Path analysis: A method to estimate altered pathways in time-varying graphs of neuroimaging data.

Graph-theoretical methods have been widely used to study human brain networks in psychiatric disorders. However, the focus has primarily been on global graphic metrics with little attention to the information contained in paths connecting brain regions. Details of disruption of these paths may be highly informative for understanding disease mechanisms. To detect the absence or addition of multistep paths in the patient group, we provide an algorithm estimating edges that contribute to these paths with reference to the control group. We next examine where pairs of nodes were connected through paths in both groups by using a covariance decomposition method. We apply our method to study resting-state fMRI data in schizophrenia versus controls. Results show several disconnectors in schizophrenia within and between functional domains, particularly within the default mode and cognitive control networks. Additionally, we identify new edges generating additional paths. Moreover, although paths exist in both groups, these paths take unique trajectories and have a significant contribution to the decomposition. The proposed path analysis provides a way to characterize individuals by evaluating changes in paths, rather than just focusing on the pairwise relationships. Our results show promise for identifying path-based metrics in neuroimaging data.

Mind the gap: functional network connectivity interpolation between schizophrenia patients and controls using a variational autoencoder.

Mental disorders such as schizophrenia have been challenging to characterize due in part to their heterogeneous presentation in individuals. Most studies have focused on identifying groups differences and have typically ignored the heterogeneous patterns within groups. Here we propose a novel approach based on a variational autoencoder (VAE) to interpolate static functional network connectivity (sFNC) across individuals, with group-specific patterns between schizophrenia patients and controls captured simultaneously. We then visualize the original sFNC in a 2D grid according to the samples in the VAE latent space. We observe a high correspondence between the generated and the original sFNC. The proposed framework facilitates data visualization and can potentially be applied to predict the stage that a subject falls within a disorder continuum as well as characterize individual heterogeneity within and between groups.

Interpreting models interpreting brain dynamics.

Brain 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. Yet, the difficulty of reliable training on high-dimensional low sample size datasets and the unclear relevance of the resulting predictive markers prevent the widespread use of deep learning in functional neuroimaging. In this work, we introduce a deep learning framework to learn from high-dimensional dynamical data while maintaining stable, ecologically valid interpretations. Results successfully demonstrate that the proposed framework enables learning the dynamics of resting-state fMRI directly from small data and capturing compact, stable interpretations of features predictive of function and dysfunction.

Decentralized Brain Age Estimation Using MRI Data.

Recent studies have demonstrated that neuroimaging data can be used to estimate biological brain age, as it captures information about the neuroanatomical and functional changes the brain undergoes during development and the aging process. However, researchers often have limited access to neuroimaging data because of its challenging and expensive acquisition process, thereby limiting the effectiveness of the predictive model. Decentralized models provide a way to build more accurate and generalizable prediction models, bypassing the traditional data-sharing methodology. In this work, we propose a decentralized method for biological brain age estimation using support vector regression models and evaluate it on three different feature sets, including both volumetric and voxelwise structural MRI data as well as resting functional MRI data. The results demonstrate that our decentralized brain age regression models can achieve similar performance compared to the models trained with all the data in one location.

Statelets: Capturing recurrent transient variations in dynamic functional network connectivity.

Dynamic functional network connectivity (dFNC) analysis is a widely used approach for capturing brain activation patterns, connectivity states, and network organization. However, a typical sliding window plus clustering (SWC) approach for analyzing dFNC models the system through a fixed sequence of connectivity states. SWC assumes connectivity patterns span throughout the brain, but they are relatively spatially constrained and temporally short-lived in practice. Thus, SWC is neither designed to capture transient dynamic changes nor heterogeneity across subjects/time. We propose a state-space time series summarization framework called "statelets" to address these shortcomings. It models functional connectivity dynamics at fine-grained timescales, adapting time series motifs to changes in connectivity strength, and constructs a concise yet informative representation of the original data that conveys easily comprehensible information about the phenotypes. We leverage the earth mover distance in a nonstandard way to handle scale differences and utilize kernel density estimation to build a probability density profile for local motifs. We apply the framework to study dFNC of patients with schizophrenia (SZ) and healthy control (HC). Results demonstrate SZ subjects exhibit reduced modularity in their brain network organization relative to HC. Statelets in the HC group show an increased recurrence across the dFNC time-course compared to the SZ. Analyzing the consistency of the connections across time reveals significant differences within visual, sensorimotor, and default mode regions where HC subjects show higher consistency than SZ. The introduced approach also enables handling dynamic information in cross-modal and multimodal applications to study healthy and disordered brains.

Privacy-preserving quality control of neuroimaging datasets in federated environments.

Privacy concerns for rare disease data, institutional or IRB policies, access to local computational or storage resources or download capabilities are among the reasons that may preclude analyses that pool data to a single site. A growing number of multisite projects and consortia were formed to function in the federated environment to conduct productive research under constraints of this kind. In this scenario, a quality control tool that visualizes decentralized data in its entirety via global aggregation of local computations is especially important, as it would allow the screening of samples that cannot be jointly evaluated otherwise. To solve this issue, we present two algorithms: decentralized data stochastic neighbor embedding, dSNE, and its differentially private counterpart, DP-dSNE. We leverage publicly available datasets to simultaneously map data samples located at different sites according to their similarities. Even though the data never leaves the individual sites, dSNE does not provide any formal privacy guarantees. To overcome that, we rely on differential privacy: a formal mathematical guarantee that protects individuals from being identified as contributors to a dataset. We implement DP-dSNE with AdaCliP, a method recently proposed to add less noise to the gradients per iteration. We introduce metrics for measuring the embedding quality and validate our algorithms on these metrics against their centralized counterpart on two toy datasets. Our validation on six multisite neuroimaging datasets shows promising results for the quality control tasks of visualization and outlier detection, highlighting the potential of our private, decentralized visualization approach.

NeuroCrypt: Machine Learning Over Encrypted Distributed Neuroimaging Data.

The field of neuroimaging can greatly benefit from building machine learning models to detect and predict diseases, and discover novel biomarkers, but much of the data collected at various organizations and research centers is unable to be shared due to privacy or regulatory concerns (especially for clinical data or rare disorders). In addition, aggregating data across multiple large studies results in a huge amount of duplicated technical debt and the resources required can be challenging or impossible for an individual site to build. Training on the data distributed across organizations can result in models that generalize much better than models trained on data from any of organizations alone. While there are approaches for decentralized sharing, these often do not provide the highest possible guarantees of sample privacy that only cryptography can provide. In addition, such approaches are often focused on probabilistic solutions. In this paper, we propose an approach that leverages the potential of datasets spread among a number of data collecting organizations by performing joint analyses in a secure and deterministic manner when only encrypted data is shared and manipulated. The approach is based on secure multiparty computation which refers to cryptographic protocols that enable distributed computation of a function over distributed inputs without revealing additional information about the inputs. It enables multiple organizations to train machine learning models on their joint data and apply the trained models to encrypted data without revealing their sensitive data to the other parties. In our proposed approach, organizations (or sites) securely collaborate to build a machine learning model as it would have been trained on the aggregated data of all the organizations combined. Importantly, the approach does not require a trusted party (i.e. aggregator), each contributing site plays an equal role in the process, and no site can learn individual data of any other site. We demonstrate effectiveness of the proposed approach, in a range of empirical evaluations using different machine learning algorithms including logistic regression and convolutional neural network models on human structural and functional magnetic resonance imaging datasets.