Accurate brain age prediction using recurrent slice-based networks

Lam, Pradeep; Santhalingam, Vigneshwaran; Suresh, Parth; Baboota, Rahul; Zhu, Alyssa H.; Thomopoulos, Sophia I.; Jahanshad, Neda; Thompson, Paul M.

doi:10.1117/12.2579630

Cited by 17 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…UKBB Dataset. For our evaluation, we use as a total of 10,446 MRI scans 18 from subjects with no psychiatric diagnosis as defined by ICD-10 criteria out of the 16,356 available subjects in the UK Biobank dataset. 38 The scans were processed using a standard preprocessing pipeline with non-parametric intensity normalization for bias field correction1 and brain extraction using FreeSurfer and linear registration to a (2mm) 3 UKBB minimum deformation template using FSL FLIRT, with the final dimension of the images being equal to 91×109×91.…”

Section: Discussionmentioning

confidence: 99%

“…15 Recently, this task has been used for benchmarking, as ground truth (the person's real age) is known. 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%

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

Section: Discussionmentioning

confidence: 99%

Section: Neuroimaging Analysismentioning

confidence: 99%

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

show abstract

“…The difference between the true chronological age and the predicted age of the brain is considered an important biomarker for early detection of age-associated neurodegenerative and neuropsychiatric diseases [33], [34], such as cognitive impairements [35], schizophrenia [36], chronic pain [37]. Recently, deep learning methods based on RNN [38], [39] and CNN [40]- [43] architectures have demonstrated accurate brain age predictions.…”

Section: A Predicting Brainagementioning

confidence: 99%

Secure Federated Learning for Neuroimaging

Stripelis¹,

Gupta²,

Saleem³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The amount of biomedical data continues to grow rapidly. However, the ability to collect data from multiple sites for joint analysis remains challenging due to security, privacy, and regulatory concerns.We present a Secure Federated Learning architecture, MetisFL, which enables distributed training of neural networks over multiple data sources without sharing data. Each site trains the neural network over its private data for some time, then shares the neural network parameters (i.e., weights, gradients) with a Federation Controller, which in turn aggregates the local models, sends the resulting community model back to each site, and the process repeats.Our architecture provides strong security and privacy. First, sample data never leaves a site. Second, neural parameters are encrypted before transmission and the community model is computed under fully-homomorphic encryption. Finally, we use information-theoretic methods to limit information leakage from the neural model to prevent a "curious" site from performing membership attacks.We demonstrate this architecture in neuroimaging. Specifically, we investigate training neural models to classify Alzheimer's disease, and estimate Brain Age, from magnetic resonance imaging datasets distributed across multiple sites, including heterogeneous environments where sites have different amounts of data, statistical distributions, and computational capabilities.

show abstract

“…Franke et al [3] used principal component analysis and relevance vector machine to predict age reliably. Studies since then primarily used neural network models for data-driven feature extraction going beyond an arbitrary selection of features [4][5][6][7][8][9][10][11]. The convolutional neural network (CNN) models have been used with a satisfactory level of accuracy.…”

Section: Introductionmentioning

confidence: 99%

Investigation of Genetic Variants and Causal Biomarkers Associated with Brain Aging

Kim

Lee

2022

Preprint

View full text Add to dashboard Cite

Delta age is a biomarker of brain aging that captures differences between the actual age and the predicted age from brain MRI. This study investigates an explainable and causal basis of high delta age by analyzing UK Biobank data in three steps. A visual saliency map of brain regions showed that lower volumes in the fornix and the lower part of the thalamus are key predictors of high delta age. Genetic association analysis on both the single variants and the gene regions identified that genes related to carcinogenesis, immune response, and neuron survival are associated with high delta age. Mendelian randomization (MR) for all metabolomic biomarkers and blood-related phenotypes showed that immune-related phenotypes have a causal impact on increasing delta age. Taken together, these observations revealed regions in the brain that are susceptible to the aging process and provided evidence of the causal and genetic connection between immune responses and brain aging.

show abstract

Accurate brain age prediction using recurrent slice-based networks

Cited by 17 publications

References 16 publications

Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryption

Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryption

Secure Federated Learning for Neuroimaging

Investigation of Genetic Variants and Causal Biomarkers Associated with Brain Aging

Contact Info

Product

Resources

About