High-Dimensional Bayesian Optimization of Personalized Cardiac Model Parameters via an Embedded Generative Model

@article{Dhamala2018HighDimensionalBO,
  title={High-Dimensional Bayesian Optimization of Personalized Cardiac Model Parameters via an Embedded Generative Model},
  author={J. Dhamala and Sandesh Ghimire and John L. Sapp and B. Milan Hor{\'a}{\vc}ek and Linwei Wang},
  journal={ArXiv},
  year={2018},
  volume={abs/2005.07804}
}
The estimation of patient-specific tissue properties in the form of model parameters is important for personalized physiological models. However, these tissue properties are spatially varying across the underlying anatomical model, presenting a significance challenge of high-dimensional (HD) optimization at the presence of limited measurement data. A common solution to reduce the dimension of the parameter space is to explicitly partition the anatomical mesh, either into a fixed small number of… 

Bayesian Optimization on Large Graphs via a Graph Convolutional Generative Model: Application in Cardiac Model Personalization

TLDR
This paper presents a novel graph convolutional VAE to allow generative modeling of non-Euclidean data, and utilizes it to embed Bayesian optimization of large graphs into a small latent space.

Bayesian Active Learning for Personalization and Uncertainty Quantification in Cardiac Electrophysiological Model

TLDR
This dissertation proposes the surrogate modeling of the complex target function containing the forward model – an objective function in deterministic estimation or a posterior probability density function in probabilistic estimation – by actively selecting a set of training samples and a Bayesian update of the prior over the target function.

Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning

TLDR
The presented Bayesian active learning method is evaluated in estimating tissue excitability in a 3D cardiac electrophysiological model in a range of synthetic and real-data experiments and demonstrates its improved accuracy in approximating the posterior pdf compared to Bayesianactive learning using regular acquisition functions.

Deep Generative Model and Analysis of Cardiac Transmembrane Potential

TLDR
The effect of architecture in learning representation and generalizing to new test cases is investigated and it is shown that different sequence autoencoders might be focusing on different aspects of TMP and might perform differently according to the metric used to measure reconstruction.

Innovative Deep Learning Approach for Biomedical Data Instantiation and Visualization

TLDR
This chapter proposes a new method, based on a visual data analysis, to build an efficient classifier with a minimum of labeled data, using an encoder, part of a Convolutional Variational Autoencoder (CVAE), as a data projection for a 2D-visualization.

Deep Learning in the Biomedical Applications: Recent and Future Status

TLDR
This paper reviews the major deep learning concepts pertinent to biomedical applications and concludes with a critical discussion, interpretation and relevant open challenges of the Omics and the BBMI.

Multivariate Time-Series Similarity Assessment via Unsupervised Representation Learning and Stratified Locality Sensitive Hashing: Application to Early Acute Hypotensive Episode Detection

TLDR
This article proposes to eliminate the high cost of engineering hand-crafted features from multivariate time-series of physiologic signals by learning its representation with a sequence-to-sequence autoencoder, and proposes to hash the learned multivariateTime-series representations of labeled dataset to enable signal similarity assessment for the prediction of critical events.

Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects

TLDR
This work develops a novel Bayesian Optimization algorithm that efficiently co-designs the morphology and grasping skills through learned latent-space representations and discovers robust and cost-efficient hand morphologies for grasping novel objects.

Machine Learning in Arrhythmia and Electrophysiology.

TLDR
The current review provides an overview of general ML principles and methodologies that will afford readers of the necessary information on the subject, serving as the foundation for inviting further ML applications in arrhythmia research.

References

SHOWING 1-10 OF 19 REFERENCES

Spatially Adaptive Multi-Scale Optimization for Local Parameter Estimation in Cardiac Electrophysiology

TLDR
A novel framework is presented that, going beyond a uniform low-resolution approach, is able to obtain a higher resolution estimation of tissue properties represented by spatially non-uniform resolution and is evaluated in estimating the local tissue excitability properties of a cardiac EP model on both synthetic and real data experiments.

Spatially-Adaptive Multi-scale Optimization for Local Parameter Estimation: Application in Cardiac Electrophysiological Models

The estimation of local parameter values for a 3D cardiac model is important for revealing abnormal tissues with altered material properties and for building patient-specific models. Existing works

MRI Based Bayesian Personalization of a Tumor Growth Model

TLDR
This work analyzes the uncertainty in the patient specific parameters of a tumor growth model, by sampling from the posterior probability of the parameters knowing the magnetic resonance images of a given patient, using a highly parallelized implementation of the reaction-diffusion equation using the Lattice Boltzmann Method.

Velocity-based cardiac contractility personalization from images using derivative-free optimization.

Quantifying the Uncertainty in Model Parameters Using Gaussian Process-Based Markov Chain Monte Carlo: An Application to Cardiac Electrophysiological Models

TLDR
This paper addresses the issue of unnecessary model simulations at unlikely candidates by integrating surrogate modeling into Metropolis Hasting sampling of the exact posterior pdfs to improve its acceptance rate and shows a significant gain in computational efficiency without compromising the accuracy.

Physiological-Model-Constrained Noninvasive Reconstruction of Volumetric Myocardial Transmembrane Potentials

TLDR
A physiological-model-constrained statistical framework to reconstruct volumetric TMP dynamics inside the 3-D myocardium from noninvasive BSP recordings is presented and phantom experiments on intramural focal activities and an initial real-data study on postmyocardial infarction demonstrate the potential of the framework in reconstructing local arrhythmic details and identifying arrhythmogenic substrates inside theMyocardium.

Noninvasive Personalization of a Cardiac Electrophysiology Model From Body Surface Potential Mapping

TLDR
This work personalized the cardiac EP model and predicted new patient-specific pacing conditions to assist clinicians for CRT patient selection and therapy planning and took an encouraging first step towards a noninvasive preoperative prediction of the response to different pacing conditions.

Fast Data-Driven Calibration of a Cardiac Electrophysiology Model from Images and ECG

TLDR
A novel data-driven approach to calibrate an EP model from standard 12-lead electrocardiograms (ECG) by coupling a mono-domain, Lattice-Boltzmann model of cardiac EP to a boundary element formulation of body surface potentials and is able to predict myocardium diffusion within the uncertainty range.

Model-Based Imaging of Cardiac Apparent Conductivity and Local Conduction Velocity for Diagnosis and Planning of Therapy

TLDR
An adaptive algorithm which uses a fast electrophysiological (EP) model to estimate apparent electrical conductivity and local conduction velocity from noncontact mapping of the endocardial surface potential and demonstrates a qualitative match between the estimated conductivity parameter and pathology locations in the human left ventricle.

Auto-Encoding Variational Bayes

TLDR
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.