Bayesian Optimisation for Neuroimaging Pre-processing in Brain Age Prediction

Mapping Intimacies ◽

10.1101/201061 ◽

2017 ◽

Author(s):

Jenessa Lancaster ◽

Romy Lorenz ◽

Rob Leech ◽

James H Cole

Keyword(s):

Absolute Error ◽

Processing Parameters ◽

Training Dataset ◽

Chronological Age ◽

Support Vector ◽

Voxel Size ◽

Smoothing Kernel ◽

And Performance ◽

Brain Age ◽

Age Prediction

AbstractNeuroimaging-based age predictions using machine learning have been shown to relate to cognitive performance, health outcomes and progression of neurodegenerative disease. However, even leading age-prediction algorithms contain measurement error, motivating efforts to improve experimental pipelines. T1-weighted MRI is commonly used for age prediction, and the pre-processing of these scans involves normalisation to a common template and resampling to a common voxel size, followed by spatial smoothing. Resampling parameters are often selected arbitrarily. Here, we sought to improve brain-age prediction accuracy by optimising resampling parameters using Bayesian optimisation.Using data on N=2001 healthy individuals (aged 16-90 years) we trained support vector machines to i) distinguish between young (<50 years) and old (>50 years) brains and ii) predict chronological age, with accuracy assessed using cross-validation. We also evaluated model generalisability to the Cam-CAN dataset (N=648, aged 18-88 years). Bayesian optimisation was used to identify optimal voxel size and smoothing kernel size for each task. This procedure adaptively samples the parameter space to evaluate accuracy across a range of possible parameters, using independent sub-samples to iteratively assess different parameter combinations to arrive at optimal values.When distinguishing between young and old brains a classification accuracy of 96.25% was achieved, with voxel size = 11.5mm3 and smoothing kernel = 2.3mm. For predicting chronological age, a mean absolute error (MAE) of 5.08 years was achieved, with voxel size = 3.73mm3 and smoothing kernel = 3.68mm. This was compared to performance using default values of 1.5mm3 and 4mm respectively, which gave a MAE = 5.48 years, a 7.3% improvement. When assessing generalisability, best performance was achieved when applying the entire Bayesian optimisation framework to the new dataset, out-performing the parameters optimised for the initial training dataset.Our study demonstrates the proof-of-principle that neuroimaging models for brain age prediction can be improved by using Bayesian optimisation to select more appropriate pre-processing parameters. Our results suggest that different parameters are selected and performance improves when optimisation is conducted in specific contexts. This motivates use of optimisation techniques at many different points during the experimental process, which may result in improved statistical sensitivity and reduce opportunities for experimenter-led bias.

Reliable longitudinal brain age prediction in stroke patients: Associations with cognitive function and response to cognitive training

10.1101/687079 ◽

2019 ◽

Cited By ~ 1

Author(s):

Geneviève Richard ◽

Knut Kolskår ◽

Kristine M. Ulrichsen ◽

Tobias Kaufmann ◽

Dag Alnæs ◽

...

Keyword(s):

Cognitive Training ◽

Outcome Prediction ◽

Cognitive Intervention ◽

Chronological Age ◽

Double Blind Study ◽

Stroke Patients ◽

Brain Morphometry ◽

Age Gap ◽

Brain Age ◽

Age Prediction

AbstractCognitive deficits are important predictors for outcome, independence and quality of life after stroke, but often remain unnoticed and unattended because other impairments are more evident. Computerized cognitive training (CCT) is among the candidate interventions that may alleviate cognitive difficulties, but the evidence supporting its feasibility and effectiveness is scarce, partly due to the lack of tools for outcome prediction and monitoring. Magnetic resonance imaging (MRI) provides candidate markers for disease monitoring and outcome prediction. By integrating information not only about lesion extent and localization, but also regarding the integrity of the unaffected parts of the brain, advanced MRI provides relevant information for developing better prediction models in order to tailor cognitive intervention for patients, especially in a chronic phase.Using brain age prediction based on MRI based brain morphometry and machine learning, we tested the hypotheses that stroke patients with a younger-appearing brain relative to their chronological age perform better on cognitive tests and benefit more from cognitive training compared to patients with an older-appearing brain. In this randomized double-blind study, 54 patients who suffered mild stroke (>6 months since hospital admission, NIHSS<7 at hospital discharge) underwent 3-weeks CCT and MRI before and after the intervention. In addition, patients were randomized to one of two groups receiving either active or sham transcranial direct current stimulation (tDCS). We tested for main effects of brain age gap (estimated age – chronological age) on cognitive performance, and associations between brain age gap and task improvement. Finally, we tested if longitudinal changes in brain age gap during the intervention were sensitive to treatment response. Briefly, our results suggest that longitudinal brain age prediction based on automated brain morphometry is feasible and reliable in stroke patients. However, no significant association between brain age and both performance and response to cognitive training were found.

Optimal Method for Fetal Brain Age Prediction Using Multiplanar Slices From Structural Magnetic Resonance Imaging

Frontiers in Neuroscience ◽

10.3389/fnins.2021.714252 ◽

2021 ◽

Vol 15 ◽

Author(s):

Jinwoo Hong ◽

Hyuk Jin Yun ◽

Gilsoon Park ◽

Seonggyu Kim ◽

Yangming Ou ◽

...

Keyword(s):

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Single Channel ◽

Fetal Brain ◽

Absolute Error ◽

Resonance Imaging ◽

Optimal Method ◽

Most Frequent Value ◽

Brain Age ◽

Age Prediction

The accurate prediction of fetal brain age using magnetic resonance imaging (MRI) may contribute to the identification of brain abnormalities and the risk of adverse developmental outcomes. This study aimed to propose a method for predicting fetal brain age using MRIs from 220 healthy fetuses between 15.9 and 38.7 weeks of gestational age (GA). We built a 2D single-channel convolutional neural network (CNN) with multiplanar MRI slices in different orthogonal planes without correction for interslice motion. In each fetus, multiple age predictions from different slices were generated, and the brain age was obtained using the mode that determined the most frequent value among the multiple predictions from the 2D single-channel CNN. We obtained a mean absolute error (MAE) of 0.125 weeks (0.875 days) between the GA and brain age across the fetuses. The use of multiplanar slices achieved significantly lower prediction error and its variance than the use of a single slice and a single MRI stack. Our 2D single-channel CNN with multiplanar slices yielded a significantly lower stack-wise MAE (0.304 weeks) than the 2D multi-channel (MAE = 0.979, p < 0.001) and 3D (MAE = 1.114, p < 0.001) CNNs. The saliency maps from our method indicated that the anatomical information describing the cortex and ventricles was the primary contributor to brain age prediction. With the application of the proposed method to external MRIs from 21 healthy fetuses, we obtained an MAE of 0.508 weeks. Based on the external MRIs, we found that the stack-wise MAE of the 2D single-channel CNN (0.743 weeks) was significantly lower than those of the 2D multi-channel (1.466 weeks, p < 0.001) and 3D (1.241 weeks, p < 0.001) CNNs. These results demonstrate that our method with multiplanar slices accurately predicts fetal brain age without the need for increased dimensionality or complex MRI preprocessing steps.

Topography of Hippocampal Connectivity with Sensorimotor Cortex Revealed by Optimizing Smoothing Kernel and Voxel Size

10.1101/2020.05.14.096339 ◽

2020 ◽

Author(s):

Douglas D. Burman

Keyword(s):

Sensorimotor Cortex ◽

Longitudinal Axis ◽

Processing Parameters ◽

Voxel Size ◽

Functional Connections ◽

Optimal Analysis ◽

Optimal Processing ◽

Smoothing Kernel ◽

The Mean ◽

Task Conditions

AbstractEvaluating hippocampal connectivity across task conditions can be challenging, especially in the absence of activation to select the size and location of seeds; furthermore, optimal analysis parameters are unknown. Hippocampal task-specific connectivity with sensorimotor cortex was identified from psychophysiological interactions (PPI) during volitional movements; connectivity from a structural seed represented the mean of connectivity maps from all voxels in a hippocampal region, whereas connectivity from a functional seed represented maximal connectivity from an individual voxel. Motor activation and hippocampal connectivity were both evaluated across different processing parameters (3mm vs. 4mm isovoxels, smoothing kernels of 6-10mm). Topography in hippocampal connectivity was apparent along both its longitudinal axis and mediolateral axis, but only with optimal processing. Larger voxels improved signal-to-noise during individual and group analyses, lowering the statistical threshold and increasing the area of activation. The 10mm smoothing kernel was optimal for detecting connectivity from structural seeds, whereas the size of the smoothing kernel had little effect on connectivity from functional seeds. Unlike other approaches, structural seeds in this study allowed task-related connectivity to be examined throughout the hippocampus. By optimizing processing parameters, topography in hippocampal connectivity became demonstrable from both structural seeds and individual voxels. Larger voxels and smoothing kernels improved sensitivity for detecting activation and hippocampal connectivity, with the use of structural / functional seeds uncovering details about the topography of its functional connections.

Correlation Constraints for Regression Models: Controlling Bias in Brain Age Prediction

Frontiers in Psychiatry ◽

10.3389/fpsyt.2021.615754 ◽

2021 ◽

Vol 12 ◽

Author(s):

Matthias S. Treder ◽

Jonathan P. Shock ◽

Dan J. Stein ◽

Stéfan du Plessis ◽

Soraya Seedat ◽

...

Keyword(s):

Regression Models ◽

Optimization Problem ◽

Prediction Models ◽

Chronological Age ◽

Training Procedure ◽

Constrained Optimization Problem ◽

The Difference ◽

Model Training ◽

Brain Age ◽

Age Prediction

In neuroimaging, the difference between chronological age and predicted brain age, also known as brain age delta, has been proposed as a pathology marker linked to a range of phenotypes. Brain age delta is estimated using regression, which involves a frequently observed bias due to a negative correlation between chronological age and brain age delta. In brain age prediction models, this correlation can manifest as an overprediction of the age of young brains and an underprediction for elderly ones. We show that this bias can be controlled for by adding correlation constraints to the model training procedure. We develop an analytical solution to this constrained optimization problem for Linear, Ridge, and Kernel Ridge regression. The solution is optimal in the least-squares sense i.e., there is no other model that satisfies the correlation constraints and has a better fit. Analyses on the PAC2019 competition data demonstrate that this approach produces optimal unbiased predictive models with a number of advantages over existing approaches. Finally, we introduce regression toolboxes for Python and MATLAB that implement our algorithm.

Predicting brain-age from multimodal imaging data captures cognitive impairment

10.1101/085506 ◽

2016 ◽

Author(s):

Franziskus Liem ◽

Gaël Varoquaux ◽

Jana Kynast ◽

Frauke Beyer ◽

Shahrzad Kharabian Masouleh ◽

...

Keyword(s):

Cognitive Impairment ◽

Biological Information ◽

Future Application ◽

Chronological Age ◽

Imaging Data ◽

Adult Lifespan ◽

Training Models ◽

Brain Data ◽

Brain Age ◽

Age Prediction

The disparity between the chronological age of an individual and their brain-age measured based on biological information has the potential to offer clinically-relevant biomarkers of neurological syndromes that emerge late in the lifespan. While prior brain-age prediction studies have relied exclusively on either structural or functional brain data, here we investigate how multimodal brain-imaging data improves age prediction. Using cortical anatomy and whole-brain functional connectivity on a large adult lifespan sample (N = 2354, age 19-82), we found that multimodal data improves brain-based age prediction, resulting in a mean absolute prediction error of 4.29 years. Furthermore, we found that the discrepancy between predicted age and chronological age captures cognitive impairment. Importantly, the brain-age measure was robust to confounding effects: head motion did not drive brain-based age prediction and our models generalized reasonably to an independent dataset acquired at a different site (N = 475). Generalization performance was increased by training models on a larger and more heterogeneous dataset. The robustness of multimodal brain-age prediction to confounds, generalizability across sites, and sensitivity to clinically-relevant impairments, suggests promising future application to the early prediction of neurocognitive disorders.

Topography of hippocampal connectivity with sensorimotor cortex revealed by optimizing smoothing kernel and voxel size

PLoS ONE ◽

10.1371/journal.pone.0260245 ◽

2021 ◽

Vol 16 (12) ◽

pp. e0260245

Author(s):

Douglas D. Burman

Keyword(s):

Sensorimotor Cortex ◽

Longitudinal Axis ◽

Processing Parameters ◽

Cortical Activation ◽

Connectivity Analysis ◽

Optimal Parameters ◽

Voxel Size ◽

Optimal Processing ◽

Smoothing Kernel ◽

The Mean

Studies of the hippocampus use smaller voxel sizes and smoothing kernels than cortical activation studies, typically using a multivoxel seed with specified radius for connectivity analysis. This study identified optimal processing parameters for evaluating hippocampal connectivity with sensorimotor cortex (SMC), comparing effectiveness by varying parameters during both activation and connectivity analysis. Using both 3mm and 4mm isovoxels, smoothing kernels of 0-10mm were evaluated on the amplitude and extent of motor activation and hippocampal connectivity with SMC. Psychophysiological interactions (PPI) identified hippocampal connectivity with SMC during volitional movements, and connectivity effects from multivoxel seeds were compared with alternate methods; a structural seed represented the mean connectivity map from all voxels within a region, whereas a functional seed represented the regional voxel with maximal SMC connectivity. With few exceptions, the same parameters were optimal for activation and connectivity. Larger isovoxels showed larger activation volumes in both SMC and the hippocampus; connectivity volumes from structural seeds were also larger, except from the posterior hippocampus. Regardless of voxel size, the 10mm smoothing kernel generated larger activation and connectivity volumes from structural seeds, as well as larger beta estimates at connectivity maxima; structural seeds also produced larger connectivity volumes than multivoxel seeds. Functional seeds showed lesser effects from voxel size and smoothing kernels. Optimal parameters revealed topography in structural seed connectivity along both the longitudinal axis and mediolateral axis of the hippocampus. These results indicate larger voxels and smoothing kernels can improve sensitivity for detecting both cortical activation and hippocampal connectivity.

Improving Individual Brain Age Prediction Using an Ensemble Deep Learning Framework

Frontiers in Psychiatry ◽

10.3389/fpsyt.2021.626677 ◽

2021 ◽

Vol 12 ◽

Author(s):

Chen-Yuan Kuo ◽

Tsung-Ming Tai ◽

Pei-Lin Lee ◽

Chiu-Wang Tseng ◽

Chieh-Yu Chen ◽

...

Keyword(s):

Deep Learning ◽

Prediction Model ◽

Prediction Accuracy ◽

Analytical Framework ◽

Support Vector ◽

Feature Sets ◽

Input Feature ◽

Brain Age ◽

Analytical Frameworks ◽

Age Prediction

Brain age is an imaging-based biomarker with excellent feasibility for characterizing individual brain health and may serve as a single quantitative index for clinical and domain-specific usage. Brain age has been successfully estimated using extensive neuroimaging data from healthy participants with various feature extraction and conventional machine learning (ML) approaches. Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy. However, the optimal approach to select and assemble appropriate input feature sets for DL analytical frameworks remains to be determined. In the Predictive Analytics Competition 2019, we proposed a hierarchical analytical framework which first used ML algorithms to investigate the potential contribution of different input features for predicting individual brain age. The obtained information then served as a priori knowledge for determining the input feature sets of the final ensemble DL prediction model. Systematic evaluation revealed that ML approaches with multiple concurrent input features, including tissue volume and density, achieved higher prediction accuracy when compared with approaches with a single input feature set [Ridge regression: mean absolute error (MAE) = 4.51 years, R2 = 0.88; support vector regression, MAE = 4.42 years, R2 = 0.88]. Based on this evaluation, a final ensemble DL brain age prediction model integrating multiple feature sets was constructed with reasonable computation capacity and achieved higher prediction accuracy when compared with ML approaches in the training dataset (MAE = 3.77 years; R2 = 0.90). Furthermore, the proposed ensemble DL brain age prediction model also demonstrated sufficient generalizability in the testing dataset (MAE = 3.33 years). In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy. With the increase in large open multiple-modality neuroimaging datasets, ensemble DL strategies with appropriate input feature sets serve as a candidate approach for predicting individual brain age in the future.

Brain-Age Prediction Using Shallow Machine Learning: Predictive Analytics Competition 2019

Frontiers in Psychiatry ◽

10.3389/fpsyt.2020.604478 ◽

2020 ◽

Vol 11 ◽

Author(s):

Pedro F. Da Costa ◽

Jessica Dafflon ◽

Walter H. L. Pinaya

Keyword(s):

Machine Learning ◽

Brain Aging ◽

Predictive Analytics ◽

Neurological Diseases ◽

Absolute Error ◽

Support Vector ◽

Learning Methods ◽

Machine Learning Methods ◽

Neuroimaging Data ◽

Brain Age

As we age, our brain structure changes and our cognitive capabilities decline. Although brain aging is universal, rates of brain aging differ markedly, which can be associated with pathological mechanism of psychiatric and neurological diseases. Predictive models have been applied to neuroimaging data to learn patterns associated with this variability and develop a neuroimaging biomarker of the brain condition. Aiming to stimulate the development of more accurate brain-age predictors, the Predictive Analytics Competition (PAC) 2019 provided a challenge that included a dataset of 2,640 participants. Here, we present our approach which placed between the top 10 of the challenge. We developed an ensemble of shallow machine learning methods (e.g., Support Vector Regression and Decision Tree-based regressors) that combined voxel-based and surface-based morphometric data. We used normalized brain volume maps (i.e., gray matter, white matter, or both) and features of cortical regions and anatomical structures, like cortical thickness, volume, and mean curvature. In order to fine-tune the hyperparameters of the machine learning methods, we combined the use of genetic algorithms and grid search. Our ensemble had a mean absolute error of 3.7597 years on the competition, showing the potential that shallow methods still have in predicting brain-age.

Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort

Scientific Reports ◽

10.1038/s41598-020-80839-4 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Kaori Ishii ◽

Ryo Asaoka ◽

Takashi Omoto ◽

Shingo Mitaki ◽

Yuri Fujino ◽

...

Keyword(s):

Deep Learning ◽

Intraocular Pressure ◽

Mean Absolute Error ◽

Absolute Error ◽

Fundus Photography ◽

Training Dataset ◽

Support Vector ◽

Testing Dataset ◽

The Mean ◽

Systemic Variables

AbstractThe purpose of the current study was to predict intraocular pressure (IOP) using color fundus photography with a deep learning (DL) model, or, systemic variables with a multivariate linear regression model (MLM), along with least absolute shrinkage and selection operator regression (LASSO), support vector machine (SVM), and Random Forest: (RF). Training dataset included 3883 examinations from 3883 eyes of 1945 subjects and testing dataset 289 examinations from 289 eyes from 146 subjects. With the training dataset, MLM was constructed to predict IOP using 35 systemic variables and 25 blood measurements. A DL model was developed to predict IOP from color fundus photographs. The prediction accuracy of each model was evaluated through the absolute error and the marginal R-squared (mR2), using the testing dataset. The mean absolute error with MLM was 2.29 mmHg, which was significantly smaller than that with DL (2.70 dB). The mR2 with MLM was 0.15, whereas that with DL was 0.0066. The mean absolute error (between 2.24 and 2.30 mmHg) and mR2 (between 0.11 and 0.15) with LASSO, SVM and RF were similar to or poorer than MLM. A DL model to predict IOP using color fundus photography proved far less accurate than MLM using systemic variables.

Brain age prediction in schizophrenia: does the choice of machine learning algorithm matter?

10.1101/2020.07.28.224931 ◽

2020 ◽

Author(s):

Won Hee Lee ◽

Mathilde Antoniades ◽

Hugo G Schnack ◽

Rene S. Kahn ◽

Sophia Frangou

Keyword(s):

Machine Learning ◽

Machine Learning Algorithms ◽

Chronological Age ◽

Lasso Regression ◽

Healthy Individuals ◽

Ols Regression ◽

Regional Regression ◽

The Mean ◽

Brain Age ◽

Age Prediction

AbstractBackgroundSchizophrenia has been associated with lifelong deviations in the normative trajectories of brain structure. These deviations can be captured using the brain-predicted age difference (brainPAD), which is the difference between the biological age of an individual’s brain, as inferred from neuroimaging data, and their chronological age. Various machine learning algorithms are currently used for this purpose but their comparative performance has yet to be systematically evaluated.MethodsSix linear regression algorithms, ordinary least squares (OLS) regression, ridge regression, least absolute shrinkage and selection operator (Lasso) regression, elastic-net regression, linear support vector regression (SVR), and relevance vector regression (RVR), were applied to brain structural data acquired on the same 3T scanner using identical sequences from patients with schizophrenia (n=90) and healthy individuals (n=200). The performance of each algorithm was quantified by the mean absolute error (MAE) and the correlation (R) between predicted brain-age and chronological age. The inter-algorithm similarity in predicted brain-age, brain regional regression weights and brainPAD were compared using correlation analyses and hierarchical clustering.ResultsIn patients with schizophrenia, ridge regression, Lasso regression, elastic-net regression, and RVR performed very similarly and showed a high degree of correlation in predicted brain-age (R>0.94) and brain regional regression weights (R>0.66). By contrast, OLS regression, which was the only algorithm without a penalty term, performed markedly worse and showed a lower similarity with the other algorithms. The mean brainPAD was higher in patients than in healthy individuals but varied by algorithm from 3.8 to 5.2 years although all analyses were performed on the same dataset.ConclusionsLinear machine learning algorithms, with the exception of OLS regression, have comparable performance for age prediction on the basis of a combination of cortical and subcortical structural measures. However, algorithm choice introduced variation in brainPAD estimation, and therefore represents an important source of inter-study variability.