Dominik Neumann

An Artificial Agent for Anatomical Landmark Detection in Medical Images

Fast and robust detection of anatomical structures or pathologies represents a fundamental task in medical image analysis. Most of the current solutions are however suboptimal and unconstrained by learning an appearance model and exhaustively scanning the space of parameters to detect a specific anatomical structure. In addition, typical feature computation or estimation of meta-parameters related to the appearance model or the search strategy, is based on local criteria or predefined approximation schemes. We propose a new learning method following a fundamentally different paradigm by simultaneously modeling both the object appearance and the parameter search strategy as a unified behavioral task for an artificial agent. The method combines the advantages of behavior learning achieved through reinforcement learning with effective hierarchical feature extraction achieved through deep learning. We show that given only a sequence of annotated images, the agent can automatically and strategically learn optimal paths that converge to the sought anatomical landmark location as opposed to exhaustively scanning the entire solution space. The method significantly outperforms state-of-the-art machine learning and deep learning approaches both in terms of accuracy and speed on 2D magnetic resonance images, 2D ultrasound and 3D CT images, achieving average detection errors of 1-2 pixels, while also recognizing the absence of an object from the image.

Data-driven estimation of cardiac electrical diffusivity from 12-lead ECG signals

Diagnosis and treatment of dilated cardiomyopathy (DCM) is challenging due to a large variety of causes and disease stages. Computational models of cardiac electrophysiology (EP) can be used to improve the assessment and prognosis of DCM, plan therapies and predict their outcome, but require personalization. In this work, we present a data-driven approach to estimate the electrical diffusivity parameter of an EP model from standard 12-lead electrocardiograms (ECG). An efficient forward model based on a mono-domain, phenomenological Lattice-Boltzmann model of cardiac EP, and a boundary element-based mapping of potentials to the body surface is employed. The electrical diffusivity of myocardium, left ventricle and right ventricle endocardium is then estimated using polynomial regression which takes as input the QRS duration and electrical axis. After validating the forward model, we computed 9500 EP simulations on 19 different DCM patients in just under three seconds each to learn the regression model. Using this database, we quantify the intrinsic uncertainty of electrical diffusion for given ECG features and show in a leave-one-patient-out cross-validation that the regression method is able to predict myocardium diffusion within the uncertainty range. Finally, our approach is tested on the 19 cases using their clinical ECG. 84% of them could be personalized using our method, yielding mean prediction errors of 18.7ms for the QRS duration and 6.5° for the electrical axis, both values being within clinical acceptability. By providing an estimate of diffusion parameters from readily available clinical data, our data-driven approach could therefore constitute a first calibration step toward a more complete personalization of cardiac EP.

Towards Personalized Cardiology: Multi-Scale Modeling of the Failing Heart

Background Despite modern pharmacotherapy and advanced implantable cardiac devices, overall prognosis and quality of life of HF patients remain poor. This is in part due to insufficient patient stratification and lack of individualized therapy planning, resulting in less effective treatments and a significant number of non-responders. Methods and Results State-of-the-art clinical phenotyping was acquired, including magnetic resonance imaging (MRI) and biomarker assessment. An individualized, multi-scale model of heart function covering cardiac anatomy, electrophysiology, biomechanics and hemodynamics was estimated using a robust framework. The model was computed on n=46 HF patients, showing for the first time that advanced multi-scale models can be fitted consistently on large cohorts. Novel multi-scale parameters derived from the model of all cases were analyzed and compared against clinical parameters, cardiac imaging, lab tests and survival scores to evaluate the explicative power of the model and its potential for better patient stratification. Model validation was pursued by comparing clinical parameters that were not used in the fitting process against model parameters. Conclusion This paper illustrates how advanced multi-scale models can complement cardiovascular imaging and how they could be applied in patient care. Based on obtained results, it becomes conceivable that, after thorough validation, such heart failure models could be applied for patient management and therapy planning in the future, as we illustrate in one patient of our cohort who received CRT-D implantation.

Robust Image-Based Estimation of Cardiac Tissue Parameters and Their Uncertainty from Noisy Data

Clinical applications of computational cardiac models require precise personalization, i.e. fitting model parameters to capture patients physiology. However, due to parameter non-identifiability, limited data, uncertainty in the clinical measurements, and modeling assumptions, various combinations of parameter values may exist that yield the same quality of fit. Hence, there is a need for quantifying the uncertainty in estimated parameters and to ascertain the uniqueness of the found solution. This paper presents a stochastic method to estimate the parameters of an image-based electromechanical model of the heart and their uncertainty due to noise in measurements. First, Bayesian inference is applied to fully estimate the posterior probability density function (PDF) of the model. To that end, Markov Chain Monte Carlo sampling is used, which is made computationally tractable by employing a fast surrogate model based on Polynomial Chaos Expansion, instead of the true forward model. Then, we use the mean-shift algorithm to automatically find the modes of the PDF and select the most likely one while being robust to noise. The approach is used to estimate global active stress and passive stiffness from invasive pressure and image-based volume quantification. Experiments on eight patients showed that not only our approach yielded goodness of fits equivalent to a well-established deterministic method, but we could also demonstrate the non-uniqueness of the problem and report uncertainty estimates, crucial information for subsequent clinical assessments of the personalized models.

Automatic region-of-interest segmentation and pathology detection in magnetically guided capsule endoscopy.

Magnetically-guided capsule endoscopy (MGCE) was introduced in 2010 as a procedure where a capsule in the stomach is navigated via an external magnetic field. The quality of the examination depends on the operators ability to detect aspects of interest in real time. We present a novel two step computer-assisted diagnostic-procedure (CADP) algorithm for indicating gastritis and gastrointestinal bleedings in the stomach during the examination. First, we identify and exclude subregions of bubbles which can interfere with further processing. Then we address the challenge of lesion localization in an environment with changing contrast and lighting conditions. After a contrast-normalized filtering, feature extraction is performed. The proposed algorithm was tested on 300 images of different patients with uniformly distributed occurrences of the target pathologies. We correctly segmented 84.72% of bubble areas. A mean detection rate of 86% for the target pathologies was achieved during a 5-fold leave-one-out cross-validation.

Automatic image-to-model framework for patient-specific electromechanical modeling of the heart

A key requirement for recent advances in computational modeling to be clinically applicable is the ability to fit models to patient data. Various personalization techniques have been proposed for isolated sub-components of complex models of heart physiology. However, no work has been presented that focuses on personalizing full electromechanical (EM) models in a streamlined, consistent and automatic fashion, which has been evaluated on a large population. We present an integrated system for full EM personalization from routinely acquired clinical data. The importance of mechanical parameters is analyzed in a comprehensive sensitivity study, revealing that myocyte contraction and Youngs modulus are the main determinants of model output variation, what lead to the proposed personalization strategy. On a large, physiologically diverse set of 15 patients, we demonstrate the effectiveness of our framework by comparing measured and calculated parameters, yielding left ventricular ejection fraction and stroke volume errors of 6.6% and 9.2 mL, respectively.

Propagation of Myocardial Fibre Architecture Uncertainty on Electromechanical Model Parameter Estimation: A Case Study

Computer models of the heart are of increasing interest for clinical applications due to their discriminative and predictive power. However the personalisation step to go from a generic model to a patient-specific one is still a scientific challenge. In particular it is still difficult to quantify the uncertainty on the estimated parameters and predicted values. In this manuscript we present a new pipeline to evaluate the impact of fibre uncertainty on the personalisation of an electromechanical model of the heart from ECG and medical images. We detail how we estimated the variability of the fibre architecture among a given population and how the uncertainty generated by this variability impacts the following personalisation. We first show the variability of the personalised simulations, with respect to the principal variations of the fibres. Then discussed how the variations in this (small) healthy population of fibres impact the parameters of the personalised simulations.

Personalized Computer Simulation of Diastolic Function in Heart Failure

The search for a parameter representing left ventricular relaxation from non-invasive and invasive diagnostic tools has been extensive, since heart failure (HF) with preserved ejection fraction (HF-pEF) is a global health problem. We explore here the feasibility using patient-specific cardiac computer modeling to capture diastolic parameters in patients suffering from different degrees of systolic HF. Fifty eight patients with idiopathic dilated cardiomyopathy have undergone thorough clinical evaluation, including cardiac magnetic resonance imaging (MRI), heart catheterization, echocardiography, and cardiac biomarker assessment. A previously-introduced framework for creating multi-scale patient-specific cardiac models has been applied on all these patients. Novel parameters, such as global stiffness factor and maximum left ventricular active stress, representing cardiac active and passive tissue properties have been computed for all patients. Invasive pressure measurements from heart catheterization were then used to evaluate ventricular relaxation using the time constant of isovolumic relaxation Tau (τ). Parameters from heart catheterization and the multi-scale model have been evaluated and compared to patient clinical presentation. The model parameter global stiffness factor, representing diastolic passive tissue properties, is correlated significantly across the patient population with τ. This study shows that multi-modal cardiac models can successfully capture diastolic (dys) function, a prerequisite for future clinical trials on HF-pEF.

Multi-modal Validation Framework of Mitral Valve Geometry and Functional Computational Models

Computational models of the mitral valve (MV) exhibit significant potential for patient-specific surgical planning. Recently, these models have been advanced by incorporating MV tissue structure, non-linear material properties, and more realistic chordae tendineae architecture. Despite advances, only limited ground-truth data exists to validate their ability to accurately simulate MV closure and function. The validation of the underlying models will enhance modeling accuracy and confidence in the simulated results. A necessity towards this aim is to develop an integrated pipeline based on a comprehensive in-vitro flow loop setup including echocardiography techniques (Echo) and micro-computed tomography. Building on [1] we improved the acquisition protocol of the proposed experimental setup for in-vitro Echo imaging, which enables the extraction of more reproducible and accurate geometrical models, using state-of-the art image processing and geometric modeling techniques. Based on the geometrical parameters from the Echo MV models captured during diastole, a bio-mechanical model is derived to estimate MV closure geometry. We illustrate the framework on two data sets and show the improvements obtained from the novel Echo acquisition protocol and improved bio-mechanical model.

Estimation of Regional Electrical Properties of the Heart from 12-Lead ECG and Images

Computational models of cardiac electrophysiology are being investigated for improved patient selection and planning of therapies like cardiac resynchronization therapy (CRT). However, their clinical applicability is limited unless their parameters are fitted to the physiology of an individual patient. In this paper, a method that estimates spatially-varying electrical diffusivities from routine ECG data and dynamic cardiac images is presented. Contrary to current methods based on invasive electrophysiology studies or body surface potential mapping, our approach relies on widely available 12-lead ECG and motion information obtained from clinical images. First, a map of mechanical activation time is derived from a cardiac strain map. Then, regional electrical diffusivities are personalized such that the computed cardiac depolarization matches both the mechanical activation map and measured ECG features. The fit between measured and computed electrocardiography data after model personalization is evaluated on 14 dilated cardiomyopathy patients, exhibiting low mean errors in terms of the diagnostic ECG features QRS duration (0.1 ms) and electrical axis (10.6\(^{\circ }\)). The proposed regional approach outperforms global personalization when 12-lead ECG is the only electrophysiology data available. Furthermore, promising results of a preliminary CRT study on one patient demonstrate the predictive power of the personalized model.