Scaling Neuroscience Research Using Federated Learning

Stripelis, Dimitris; Ambite, José Luis; Lam, Pradeep; Thompson, Paul M.

doi:10.1109/isbi48211.2021.9433925

Cited by 21 publications

(25 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, most ENIGMA meta-analytic studies currently focus on univariate measures derived from brain MRI, diffusion tensor imaging (DTI), electroencephalogram (EEG), or other data modalities, and relatively few have studied multivariate imaging measures. Federated learning models, such as decentralized independent component analysis ( Baker et al, 2015 ), sparse regression ( Plis et al, 2016 ), and distributed deep learning ( Kaissis et al, 2021 ; Stripelis et al, 2021 ; Warnat-Herresthal et al, 2021 ), have made solid progress with leveraging multivariate image features for statistical inferences, allowing iterative computation on remote datasets. Some other recent studies focus on multivariate linear modeling ( Silva et al, 2020 ), federated gradient averaging ( Remedios et al, 2020 ), and unbalanced data for multi-site ( Yeganeh et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Federated Morphometry Feature Selection for Hippocampal Morphometry Associated Beta-Amyloid and Tau Pathology

Dong

Zhang

et al. 2021

Front. Neurosci.

View full text Add to dashboard Cite

Amyloid-β (Aβ) plaques and tau protein tangles in the brain are now widely recognized as the defining hallmarks of Alzheimer’s disease (AD), followed by structural atrophy detectable on brain magnetic resonance imaging (MRI) scans. One of the particular neurodegenerative regions is the hippocampus to which the influence of Aβ/tau on has been one of the research focuses in the AD pathophysiological progress. This work proposes a novel framework, Federated Morphometry Feature Selection (FMFS) model, to examine subtle aspects of hippocampal morphometry that are associated with Aβ/tau burden in the brain, measured using positron emission tomography (PET). FMFS is comprised of hippocampal surface-based feature calculation, patch-based feature selection, federated group LASSO regression, federated screening rule-based stability selection, and region of interest (ROI) identification. FMFS was tested on two Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohorts to understand hippocampal alterations that relate to Aβ/tau depositions. Each cohort included pairs of MRI and PET for AD, mild cognitive impairment (MCI), and cognitively unimpaired (CU) subjects. Experimental results demonstrated that FMFS achieves an 89× speedup compared to other published state-of-the-art methods under five independent hypothetical institutions. In addition, the subiculum and cornu ammonis 1 (CA1 subfield) were identified as hippocampal subregions where atrophy is strongly associated with abnormal Aβ/tau. As potential biomarkers for Aβ/tau pathology, the features from the identified ROIs had greater power for predicting cognitive assessment and for survival analysis than five other imaging biomarkers. All the results indicate that FMFS is an efficient and effective tool to reveal associations between Aβ/tau burden and hippocampal morphometry.

show abstract

Section: Introductionmentioning

confidence: 99%

Federated Morphometry Feature Selection for Hippocampal Morphometry Associated Beta-Amyloid and Tau Pathology

Dong

Zhang

et al. 2021

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Our evaluation testbed consists of three federated learning environments * with diverse data distributions across 8 learners. 8 Each learner runs on a dedicated GPU card on a single server. In terms of data distribution, we investigate two distinct cases: IID, where each learner holds training examples that follow the global data distribution, and Non-IID, where local distributions may differ substantially from the global.…”

Section: Discussionmentioning

confidence: 99%

“…Deep learning methods have been used to predict an individual's brain age both in centralized [16][17][18][19][20] and federated learning settings. 8 In our study, we perform the BrainAge prediction task using a 2D Convolutional Neural Network (CNN), which was shown 20 to yield better predictive performance compared to its 2D-Slice-RNN 18 and 3D-CNN 16, 19 counterparts.…”

Section: Neuroimaging Analysismentioning

confidence: 99%

“…Recent workshops on distributed and collaborative learning in biomedical imaging have focused on federated gradient averaging and multivariate linear modeling, 4, 5 learning from non-IID or unbalanced data at the participating sites, 6 as well as adaptive weighting, asynchronous and semi-synchronous schemes that allow distributed learning in heterogeneous computing environments. 7,8 Other works focus on personalized FL, 9 where models are trained on distributed data but customized to perform well on a specific dataset; in this context, the federation offers an auxiliary source of relevant data for a given task, similar in spirit to transfer learning or pre-training on auxiliary data. A similar approach based on Batch-Normalization (BN) has also been proposed, 10 where only the BN-transformation parameters are shared during federated training, leading to learn a per-site model instead of a single global model, and thereby accounting for heterogeneity via model personalization.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryption

Stripelis¹,

Saleem²,

Ghai³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Federated learning (FL) enables distributed computation of machine learning models over various disparate, remote data sources, without requiring to transfer any individual data to a centralized location. This results in an improved generalizability of models and efficient scaling of computation as more sources and larger datasets are added to the federation. Nevertheless, recent membership attacks show that private or sensitive personal data can sometimes be leaked or inferred when model parameters or summary statistics are shared with a central site, requiring improved security solutions. In this work, we propose a framework for secure FL using fullyhomomorphic encryption (FHE). Specifically, we use the CKKS construction, an approximate, floating point compatible scheme that benefits from ciphertext packing and rescaling. In our evaluation on large-scale brain MRI datasets, we use our proposed secure FL framework to train a deep learning model to predict a person's age from distributed MRI scans, a common benchmarking task, and demonstrate that there is no degradation in the learning performance between the encrypted and non-encrypted federated models.

show abstract

“…However, most ENIGMA meta-analytic studies currently focus on univariate measures derived from brain MRI, diffusion tensor imaging (DTI), electroencephalogram (EEG), or other data modalities, and relatively few have studied multivariate imaging measures. Federated learning models, such as decentralized independent component analysis (Baker et al, 2015), sparse regression (Plis et al, 2016), and distributed deep learning (Kaissis et al, 2021;Stripelis et al, 2021;Warnat-Herresthal et al, 2021), have made solid progress with leveraging multivariate image features for statistical inferences, allowing iterative computation on remote datasets. Some other recent studies focus on multivariate linear modeling (Silva et al, 2020), federated gradient averaging (Remedios et al, 2020), and unbalanced data for multi-site (Yeganeh et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Federated Morphometry Feature Selection for Hippocampal Morphometry Associated Beta-Amyloid and Tau Pathology

Dong

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Amyloid-β (Aβ) plaques and tau protein tangles in the brain are now widely recognized as the defining hallmarks of Alzheimer's disease (AD), followed by structural atrophy detectable on brain magnetic resonance imaging (MRI) scans. One of the particular neurodegenerative regions is the hippocampus to which the influence of Aβ/tau on has been one of the research focuses in the AD pathophysiological progress. This work proposes a novel framework, Federated Morphometry Feature Selection (FMFS) model, to examine subtle aspects of hippocampal morphometry that are associated with Aβ/tau burden in the brain, measured using positron emission tomography (PET). FMFS is comprised of hippocampal surface-based feature calculation, patch-based feature selection, federated group LASSO regression, federated screening rule-based stability selection, and region of interest (ROI) identification. FMFS was tested on two ADNI cohorts to understand hippocampal alterations that relate to Aβ/tau depositions. Each cohort included pairs of MRI and PET for AD, mild cognitive impairment (MCI) and cognitively unimpaired (CU) subjects. Experimental results demonstrated that FMFS achieves an 89x speedup compared to other published state-of-the-art methods under five independent hypothetical institutions. In addition, the subiculum and cornu ammonis 1 (CA1 subfield) were identified as hippocampal subregions where atrophy is strongly associated with abnormal Aβ/tau. As potential biomarkers for Aβ/tau pathology, the features from the identified ROIs had greater power for predicting cognitive assessment and for survival analysis than five other imaging biomarkers. All the results indicate that FMFS is an efficient and effective tool to reveal associations between Aβ/tau burden and hippocampal morphometry.

show abstract

Scaling Neuroscience Research Using Federated Learning

Cited by 21 publications

References 12 publications

Federated Morphometry Feature Selection for Hippocampal Morphometry Associated Beta-Amyloid and Tau Pathology

Federated Morphometry Feature Selection for Hippocampal Morphometry Associated Beta-Amyloid and Tau Pathology

Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryption

Federated Morphometry Feature Selection for Hippocampal Morphometry Associated Beta-Amyloid and Tau Pathology

Contact Info

Product

Resources

About