arXiv subjects

Jack Lee

Publications and source records attributed to Jack Lee.

7 recordsLinked to original sources

arXiv2023

High-Resolution Maps of Left Atrial Displacements and Strains Estimated with 3D Cine MRI using Online Learning Neural Networks

The functional analysis of the left atrium (LA) is important for evaluating cardiac health and understanding diseases like atrial fibrillation. Cine MRI is ideally placed for the detailed 3D characterization of LA motion and deformation but is lacking appropriate acquisition and analysis tools. Here, we propose tools for the Analysis for Left Atrial Displacements and DeformatIons using online learning neural Networks (Aladdin) and present a technical feasibility study on how Aladdin can characterize 3D LA function globally and regionally. Aladdin includes an online segmentation and image registration network, and a strain calculation pipeline tailored to the LA. We create maps of LA Displacement Vector Field (DVF) magnitude and LA principal strain values from images of 10 healthy volunteers and 8 patients with cardiovascular disease (CVD), of which 2 had large left ventricular ejection fraction (LVEF) impairment. We additionally create an atlas of these biomarkers using the data from the healthy volunteers. Results showed that Aladdin can accurately track the LA wall across the cardiac cycle and characterize its motion and deformation. Global LA function markers assessed with Aladdin agree well with estimates from 2D Cine MRI. A more marked active contraction phase was observed in the healthy cohort, while the CVD LVEF group showed overall reduced LA function. Aladdin is uniquely able to identify LA regions with abnormal deformation metrics that may indicate focal pathology. We expect Aladdin to have important clinical applications as it can non-invasively characterize atrial pathophysiology. All source code and data are available at: https://github.com/cgalaz01/aladdin_cmr_la.

cs.CV↗

arXiv2022

Unsupervised Domain Adaptation for Automated Knee Osteoarthritis Phenotype Classification

Purpose: The aim of this study was to demonstrate the utility of unsupervised domain adaptation (UDA) in automated knee osteoarthritis (OA) phenotype classification using a small dataset (n=50). Materials and Methods: For this retrospective study, we collected 3,166 three-dimensional (3D) double-echo steady-state magnetic resonance (MR) images from the Osteoarthritis Initiative dataset and 50 3D turbo/fast spin-echo MR images from our institute (in 2020 and 2021) as the source and target datasets, respectively. For each patient, the degree of knee OA was initially graded according to the MRI Osteoarthritis Knee Score (MOAKS) before being converted to binary OA phenotype labels. The proposed UDA pipeline included (a) pre-processing, which involved automatic segmentation and region-of-interest cropping; (b) source classifier training, which involved pre-training phenotype classifiers on the source dataset; (c) target encoder adaptation, which involved unsupervised adaption of the source encoder to the target encoder and (d) target classifier validation, which involved statistical analysis of the target classification performance evaluated by the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity and accuracy. Additionally, a classifier was trained without UDA for comparison. Results: The target classifier trained with UDA achieved improved AUROC, sensitivity, specificity and accuracy for both knee OA phenotypes compared with the classifier trained without UDA. Conclusion: The proposed UDA approach improves the performance of automated knee OA phenotype classification for small target datasets by utilising a large, high-quality source dataset for training. The results successfully demonstrated the advantages of the UDA approach in classification on small datasets.

eess.IV↗

arXiv2021

Haemodynamic analysis using multiphase flow dynamics in tubular lesions

Background and Objective: The role of red blood cell dynamics is emphasised in certain cardiovascular diseases, and thus needs to be closely studied. A multiphase model of blood flow allows the resolution of locally varying density of red blood cells within a complex vessel geometrical domain, and haemodynamic consequences of such build up. Methods: A novel computational fluid dynamics solver for simulating multiphase flows is used for modelling blood flow using level set for a sharp interface representation. Single-phase simulations and reduced order models are used for pressure comparisons. The new solver is used for numerically studying AHA type B lesions. The impact of hematocrit and degree of stenosis on the haemodynamics of coronary arteries is investigated. Results: The comparisons with single-phase flow simulations indicate differences in pressure when considering red blood cell aggregation. Multiphase simulations provide slightly lower pressure drop for the same stenosis severity compared to the single-phase simulations. Secondary flow patterns and the interactions between the two phases leads to the red blood cell aggregation at the end of the diastole cycle, which significantly changes the red blood cell distribution, the shear stresses and velocity in tubular lesions. Conclusions: Neither pressure drop nor mean velocity are not strongly changed in the multiphase modelling, but particle buildup significantly changes which is only revealed by the multiphase approach.

physics.flu-dyn↗

arXiv2021

A finite volume coupled level set and volume of fluid method with a mass conservation step for simulating two-phase flows

This paper presents a finite volume method for simulating two-phase flows using a level set approach coupled with volume of fluid method capable of simulating sharp fluid interfaces. The efficiency of the method is a result of the fact that the interface is calculated in order to satisfy mass conservation with no explicit interface reconstruction step and the mass fluxes across cell-faces are corrected to respect the recovered volume fraction. The mass-conservation correction step proposed here, is utilised using an iterative algorithm which solves a reaction-diffusion equation for the mass correction of the level set. The re-sharpened volume fraction is used for the new volumetric fluxes at each cell which are calculated through the proposed algorithm that guarantees that they satisfy mass conservation. The algorithm is not limited in representing the interface with the 0.5-contour and is applicable for arbitrary polyhedral cells. Good accuracy and mass conservation are achieved when compared to other conservative approaches.

physics.comp-ph↗

arXiv2020

A Survey of Pathways for Mechano-Electric Coupling in the Atria

Mechano-electric coupling (MEC) in atrial tissue has received sparse investigation to date, despite the well-known association between chronic atrial dilation and atrial fibrillation (AF). Of note, no fewer than six different mechanisms pertaining to stretch-activated channels, cellular capacitance and geometric effects have been identified in the literature as potential players. In this mini review, we briefly survey each of these pathways to MEC. We then perform computational simulations using single cell and tissue models in presence of various stretch regimes and MEC pathways. This allows us to assess the relative significance of each pathway in determining action potential duration, conduction velocity and rotor stability. For chronic atrial stretch, we find that stretch-induced alterations in membrane capacitance decrease conduction velocity and increase action potential duration, in agreement with experimental findings. In the presence of time-dependent passive atrial stretch, stretch-activated channels play the largest role, leading to after-depolarizations and rotor hypermeandering. These findings suggest that physiological atrial stretches, such as passive stretch during the atrial reservoir phase, may play an important part in the mechanisms of atrial arrhythmogenesis.

q-bio.QM↗

arXiv2019

Hierarchical Bayesian myocardial perfusion quantification

Purpose: Tracer-kinetic models can be used for the quantitative assessment of contrast-enhanced MRI data. However, the model-fitting can produce unreliable results due to the limited data acquired and the high noise levels. Such problems are especially prevalent in myocardial perfusion MRI leading to the compromise of constrained numerical deconvolutions and segmental signal averaging being commonly used as alternatives to the more complex tracer-kinetic models. Methods: In this work, the use of hierarchical Bayesian inference for the parameter estimation is explored. It is shown that with Bayesian inference it is possible to reliably fit the two-compartment exchange model to perfusion data. The use of prior knowledge on the ranges of kinetic parameters and the fact that neighbouring voxels are likely to have similar kinetic properties combined with a Markov chain Monte Carlo based fitting procedure significantly improves the reliability of the perfusion estimates with compared to the traditional least-squares approach. The method is assessed using both simulated and patient data. Results: The average (standard deviation) normalised mean square error for the distinct noise realisations of a simulation phantom falls from 0.32 (0.55) with the least-squares fitting to 0.13 (0.2) using Bayesian inference. The assessment of the presence of coronary artery disease based purely on the quantitative MBF maps obtained using Bayesian inference matches the visual assessment in all 24 slices. When using the maps obtained by the least-squares fitting, a corresponding assessment is only achieved in 16/24 slices. Conclusion: Bayesian inference allows a reliable, fully automated and user-independent assessment of myocardial perfusion on a voxel-wise level using the two-compartment exchange model.

eess.IV↗

arXiv2019

Deep learning-based prediction of kinetic parameters from myocardial perfusion MRI

The quantification of myocardial perfusion MRI has the potential to provide a fast, automated and user-independent assessment of myocardial ischaemia. However, due to the relatively high noise level and low temporal resolution of the acquired data and the complexity of the tracer-kinetic models, the model fitting can yield unreliable parameter estimates. A solution to this problem is the use of Bayesian inference which can incorporate prior knowledge and improve the reliability of the parameter estimation. This, however, uses Markov chain Monte Carlo sampling to approximate the posterior distribution of the kinetic parameters which is extremely time intensive. This work proposes training convolutional networks to directly predict the kinetic parameters from the signal-intensity curves that are trained using estimates obtained from the Bayesian inference. This allows fast estimation of the kinetic parameters with a similar performance to the Bayesian inference.

eess.IV↗