Contrast response function estimation with nonparametric Bayesian active learning.

Multidimensional psychometric functions can typically be estimated nonparametrically for greater accuracy or parametrically for greater efficiency. By recasting the estimation problem from regression to classification, however, powerful machine learning tools can be leveraged to provide an adjustable balance between accuracy and efficiency. Contrast sensitivity functions (CSFs) are behaviorally estimated curves that provide insight into both peripheral and central visual function. Because estimation can be impractically long, current clinical workflows must make compromises such as limited sampling across spatial frequency or strong assumptions on CSF shape. This article describes the development of the machine learning contrast response function (MLCRF) estimator, which quantifies the expected probability of success in performing a contrast detection or discrimination task. A machine learning CSF can then be derived from the MLCRF. Using simulated eyes created from canonical CSF curves and actual human contrast response data, the accuracy and efficiency of the machine learning contrast sensitivity function (MLCSF) was evaluated to determine its potential utility for research and clinical applications. With stimuli selected randomly, the MLCSF estimator converged slowly toward ground truth. With optimal stimulus selection via Bayesian active learning, convergence was nearly an order of magnitude faster, requiring only tens of stimuli to achieve reasonable estimates. Inclusion of an informative prior provided no consistent advantage to the estimator as configured. MLCSF achieved efficiencies on par with quickCSF, a conventional parametric estimator, but with systematically higher accuracy. Because MLCSF design allows accuracy to be traded off against efficiency, it should be explored further to uncover its full potential.

BrainImageR: spatiotemporal gene set analysis referencing the human brain.

Motivation: Neuronal analyses such as transcriptomics, epigenetics and genome-wide association studies must be assessed in the context of the human brain to generate biologically meaningful inferences. It is often difficult to access primary human brain tissue; therefore, approximations are made using alternative sources such as peripheral tissues or in vitro-derived neurons. Gene sets from these studies are then assessed for their association with the post-mortem human brain. However, most analyses of post-mortem datasets are achieved by building new computational tools each time in-house, which can cause discrepancies from study to study. The field is in need of a user-friendly tool to examine spatiotemporal expression with respect to the postmortem brain. Such a tool will be of use in the molecular interrogation of neurological and psychiatric disorders, with direct advantages for the disease-modeling and human genetics communities. Results: We have developed brainImageR, an R package that calculates both the spatial and temporal association of a dataset with post-mortem human brain. BrainImageR identifies anatomical regions enriched for candidate gene set expression. It further predicts the developmental time point of the sample, a task that has become increasingly important in the field of in vitro neuronal modeling. These functionalities of brainImageR enable a quick and efficient characterization of a given dataset across normal human brain development. Availability and implementation: BrainImageR is released under the Creative Commons CC BY-SA 4.0 license and can be accessed directly at brainimager.salk.edu or the R code can be downloaded through github at https://github.com/saralinker/brainImageR.

Active Mutual Conjoint Estimation of Multiple Contrast Sensitivity Functions.

Recent advances in nonparametric Contrast Sensitivity Function (CSF) estimation have yielded a new tradeoff between accuracy and efficiency not available to classical parametric estimators. An additional advantage of this new framework is the ability to independently tune multiple aspects of the estimator to seek further improvements. Machine Learning CSF (MLCSF) estimation with Gaussian processes allows for design optimization in the kernel, acquisition function and underlying task representation, to name a few. This paper describes a novel kernel for CSF estimation that is more flexible than a kernel based on strictly functional forms. Despite being more flexible, it can result in a more efficient estimator. Further, trial selection for data acquisition that is generalized beyond pure information gain can also improve estimator quality. Finally, introducing latent variable representations underlying general CSF shapes can enable simultaneous estimation of multiple CSFs, such as from different eyes, eccentricities or luminances. The conditions under which the new procedures perform better than previous nonparametric estimation procedures are presented and quantified.

Contrast Response Function Estimation with Nonparametric Bayesian Active Learning.

Multidimensional psychometric functions can typically be estimated nonparametrically for greater accuracy or parametrically for greater efficiency. By recasting the estimation problem from regression to classification, however, powerful machine learning tools can be leveraged to provide an adjustable balance between accuracy and efficiency. Contrast Sensitivity Functions (CSFs) are behaviorally estimated curves that provide insight into both peripheral and central visual function. Because estimation can be impractically long, current clinical workflows must make compromises such as limited sampling across spatial frequency or strong assumptions on CSF shape. This paper describes the development of the Machine Learning Contrast Response Function (MLCRF) estimator, which quantifies the expected probability of success in performing a contrast detection or discrimination task. A machine learning CSF can then be derived from the MLCRF. Using simulated eyes created from canonical CSF curves and actual human contrast response data, the accuracy and efficiency of the MLCSF was evaluated in order to determine its potential utility for research and clinical applications. With stimuli selected randomly, the MLCSF estimator converged slowly toward ground truth. With optimal stimulus selection via Bayesian active learning, convergence was nearly an order of magnitude faster, requiring only tens of stimuli to achieve reasonable estimates. Inclusion of an informative prior provided no consistent advantage to the estimator as configured. MLCSF achieved efficiencies on par with quickCSF, a conventional parametric estimator, but with systematically higher accuracy. Because MLCSF design allows accuracy to be traded off against efficiency, it should be explored further to uncover its full potential. Precis: Machine learning classifiers enable accurate and efficient contrast sensitivity function estimation with item-level prediction for individual eyes.