Search

We present an open-source software pipeline to create patient-specific left atrial (LA) models with fibre orientations and a fibrosis map, suitable for electrophysiology simulations. The semi-automatic pipeline takes as input a contrast enhanced magnetic resonance angiogram, and a late gadolinium enhanced (LGE) contrast magnetic resonance (CMR). Five operators were allocated 20 cases each from a set of 50 CMR datasets to create a total of 100 models to evaluate inter/intra-operator variability. Each output model consisted of (1) a labelled surface mesh open at the pulmonary veins (PV) and mitral valve (MV), (2) fibre orientations mapped from a diffusion tensor MRI human atlas, (3) fibrosis map from the LGE-CMR scan, and (4) simulation of local activation time (LAT) and phase singularity (PS) mapping. We evaluated reproducibility in our pipeline by comparing agreement in shape of the output meshes, fibrosis distribution in the LA body, and fibre orientations; simulations outputs were evaluated comparing total activation times of LAT maps, mean conduction velocity (CV), and structural similarity index measure (SSIM) of PS maps. Our workflow allows a single model to be created in 16.72 +/- 12.25 minutes. Results in this abstract are reported as inter/intra. Shape only differed noticeably with users' selection of the MV and the length of the PV from the ostia to the distal end; fibrosis agreement (0.91/0.99 ICC) and fibre orientation agreement (60.63/71.77 %) were high. LAT maps showed good agreement, the median of the absolute difference of the total activation times was 2.02ms/1.37ms. The average of the mean CV difference was -4.04mm/s / 2.1mm/s. PS maps showed a moderately good agreement with SSIM of 0.648/0.608. Although we found notable differences in the models due to user input, our tests show that operator variability was comparable to that of image resolution or fibre estimation., Comment: 17 pages, 7 figures, submitted for review at Journal of Computers in Biology and Medicine (in press)

Computational Fluid Dynamics (CFD) is used to assist in designing artificial valves and planning procedures, focusing on local flow features. However, assessing the impact on overall cardiovascular function or predicting longer-term outcomes may require more comprehensive whole heart CFD models. Fitting such models to patient data requires numerous computationally expensive simulations, and depends on specific clinical measurements to constrain model parameters, hampering clinical adoption. Surrogate models can help to accelerate the fitting process while accounting for the added uncertainty. We create a validated patient-specific four-chamber heart CFD model based on the Navier-Stokes-Brinkman (NSB) equations and test Gaussian Process Emulators (GPEs) as a surrogate model for performing a variance-based global sensitivity analysis (GSA). GSA identified preload as the dominant driver of flow in both the right and left side of the heart, respectively. Left-right differences were seen in terms of vascular outflow resistances, with pulmonary artery resistance having a much larger impact on flow than aortic resistance. Our results suggest that GPEs can be used to identify parameters in personalized whole heart CFD models, and highlight the importance of accurate preload measurements., Comment: 8 pages plus 15 pages supplement, 6 figures, 3 tables, submitted to IEEE Transactions on Biomedical Engineering

The "curse of dimensionality" is a well-known problem in pattern recognition. A widely used approach to tackling the problem is a group of subspace methods, where the original features are projected onto a new space. The lower dimensional subspace is then used to approximate the original features for classification. However, most subspace methods were not originally developed for classification. We believe that direct adoption of these subspace methods for pattern classification should not be considered best practice. In this paper, we present a new information theory based algorithm for selecting subspaces, which can always result in superior performance over conventional methods. This paper makes the following main contributions: i) it improves a common practice widely used by practitioners in the field of pattern recognition, ii) it develops an information theory based technique for systematically selecting the subspaces that are discriminative and therefore are suitable for pattern recognition/classification purposes, iii) it presents extensive experimental results on a variety of computer vision and pattern recognition tasks to illustrate that the subspaces selected based on maximum mutual information criterion will always enhance performance regardless of the classification techniques used.

Classifiers embedded within human in the loop visual object recognition frameworks commonly utilise two sources of information: one derived directly from the imagery data of an object, and the other obtained interactively from user interactions. These computer vision frameworks exploit human high-level cognitive power to tackle particularly difficult visual object recognition tasks. In this paper, we present innovative techniques to combine the two sources of information intelligently for the purpose of improving recognition accuracy. We firstly employ standard algorithms to build two classifiers for the two sources independently, and subsequently fuse the outputs from these classifiers to make a conclusive decision. The two fusion techniques proposed are: i) a modified naive Bayes algorithm that adaptively selects an individual classifier's output or combines both to produce a definite answer, and ii) a neural network based algorithm which feeds the outputs of the two classifiers to a 4-layer feedforward network to generate a final output. We present extensive experimental results on 4 challenging visual recognition tasks to illustrate that the new intelligent techniques consistently outperform traditional approaches to fusing the two sources of information.