Thomas Dietenbeck

B-Spline Explicit Active Surfaces: An Efficient Framework for Real-Time 3-D Region-Based Segmentation

A new formulation of active contours based on explicit functions has been recently suggested. This novel framework allows real-time 3-D segmentation since it reduces the dimensionality of the segmentation problem. In this paper, we propose a B-spline formulation of this approach, which further improves the computational efficiency of the algorithm. We also show that this framework allows evolving the active contour using local region-based terms, thereby overcoming the limitations of the original method while preserving computational speed. The feasibility of real-time 3-D segmentation is demonstrated using simulated and medical data such as liver computer tomography and cardiac ultrasound images.

Creaseg: A free software for the evaluation of image segmentation algorithms based on level-set

This paper describes a free open source software in Matlab (named Creaseg, http://www.creatis.insa-lyon. fr/∼bernard/creaseg) for the evaluation of the performance of different level-set based algorithms in the context of 2D image segmentation. The platform gives access to the implementation of six level-set methods that have been chosen in order to cover a wide range of data attachment terms (contour, region and localized approaches). The software also gives the possibility to compare the performance of the proposed algorithms on any kind of images. The performance can be evaluated either visually, or from similarity measurements between a reference and the results of the segmentation.

Detection of the whole myocardium in 2D-echocardiography for multiple orientations using a geometrically constrained level-set

The segmentation of the myocardium in echocardiographic images is an important task for the diagnosis of heart disease. This task is difficult due to the inherent problems of echographic images (i.e. low contrast, speckle noise, signal dropout, presence of shadows). In this article, we propose a method to segment the whole myocardium (endocardial and epicardial contours) in 2D echographic images. This is achieved using a level-set model constrained by a new shape formulation that allows to model both contours. The novelty of this work also lays in the fact that our framework allows to segment the whole myocardium for the four main views used in clinical routine. The method is validated on a dataset of clinical images and compared with expert segmentation.

Real-time 3D interactive segmentation of echocardiographic data through user-based deformation of B-spline explicit active surfaces.

Image segmentation is an ubiquitous task in medical image analysis, which is required to estimate morphological or functional properties of given anatomical targets. While automatic processing is highly desirable, image segmentation remains to date a supervised process in daily clinical practice. Indeed, challenging data often requires user interaction to capture the required level of anatomical detail. To optimize the analysis of 3D images, the user should be able to efficiently interact with the result of any segmentation algorithm to correct any possible disagreement. Building on a previously developed real-time 3D segmentation algorithm, we propose in the present work an extension towards an interactive application where user information can be used online to steer the segmentation result. This enables a synergistic collaboration between the operator and the underlying segmentation algorithm, thus contributing to higher segmentation accuracy, while keeping total analysis time competitive. To this end, we formalize the user interaction paradigm using a geometrical approach, where the user input is mapped to a non-cartesian space while this information is used to drive the boundary towards the position provided by the user. Additionally, we propose a shape regularization term which improves the interaction with the segmented surface, thereby making the interactive segmentation process less cumbersome. The resulting algorithm offers competitive performance both in terms of segmentation accuracy, as well as in terms of total analysis time. This contributes to a more efficient use of the existing segmentation tools in daily clinical practice. Furthermore, it compares favorably to state-of-the-art interactive segmentation software based on a 3D livewire-based algorithm.

Whole myocardium tracking in 2D-echocardiography in multiple orientations using a motion constrained level-set

The segmentation and tracking of the myocardium in echocardiographic sequences is an important task for the diagnosis of heart disease. This task is difficult due to the inherent problems of echographic images (i.e. low contrast, speckle noise, signal dropout, presence of shadows). In this article, we extend a level-set method recently proposed in Dietenbeck et al. (2012) in order to track the whole myocardium in echocardiographic sequences. To this end, we enforce temporal coherence by adding a new motion prior energy to the existing framework. This motion prior term is expressed as new constraint that enforces the conservation of the levels of the implicit function along the image sequence. Moreover, the robustness of the proposed method is improved by adjusting the associated hyperparameters in a spatially adaptive way, using the available strong a priori about the echocardiographic regions to be segmented. The accuracy and robustness of the proposed method is evaluated by comparing the obtained segmentation with experts references and to another state-of-the-art method on a dataset of 15 sequences (≃ 900 images) acquired in three echocardiographic views. We show that the algorithm provides results that are consistent with the inter-observer variability and outperforms the state-of-the-art method. We also carry out a complete study on the influence of the parameters settings. The obtained results demonstrate the stability of our method according to those values.

Using a geometric formulation of annular-like shape priors for constraining variational level-sets

In this paper we address the segmentation of shapes which may be approximated by two elliptical contours. Such patterns are indeed recurrent in many image processing applications. In this context, we develop a level-set framework especially dedicated to the detection of annular-like shapes. The behavior of this approach is illustrated on images from different fields. An evaluation is then performed for myocardium detection in medical images.

Coupled B-spline active geometric functions for myocardial segmentation: A localized region-based approach

Although echocardiographic image segmentation has been a hot topic for long and several methods exist for robust endocardial segmentation, little attention has been directed to full myocardial segmentation. In fact, full myocardial segmentation is particularly challenging due to the high heterogeneity in the appearance of the epicardial boundary in US images. In the present paper, we propose an extension to the recently introduced Active Geometric Functions segmentation framework in order to cope with data inhomogeneities. This method has been successfully applied to short axis B-mode images acquired in a clinical setting. The mean absolute distance between the algorithm and the reference contours provided by an expert physician is 2.81±0.7 pixels. The computation time per frame is around 1 second, in a non-optimized MATLAB implementation, which shows that this method can be extended to achieve realtime performance.

Multiview myocardial tracking in echocardiographic 2D sequences using shape and motion constrained level-set

Segmentation of the myocardium in echocardiographic images is an important task for the diagnosis of heart disease. This task is difficult due to the inherent problems of echographic images (i.e. low contrast, speckle noise, signal dropout, presence of shadows). In this article, we extend a level-set method recently proposed in [1] in order to track the whole myocardium in echocardiographic sequences. To this end, we formulate a new motion prior energy that constrains the zero-level of the implicit function to satisfy the optical flow hypothesis. The algorithm is then compared to experts references and to another method on a dataset of 12 sequences (more than 700 images) acquired in the four main echocardiographic views.

Fast left ventricle tracking in 3D echocardiographic data using anatomical affine optical flow

Global functional assessment remains a central part of the diagnostic process in daily cardiology practice. Furthermore, real-time 3D echocardiography has been shown to offer superior performance in the assessment of global functional indices, such as stroke volume and ejection fraction, over conventional 2D echo. With this in mind, we present a novel method for tracking the left ventricle (LV) in three-dimensional ultrasound data using a global affine motion model. In order to have a valid region for the underlying assumption of nearly homogeneous motion patterns, we introduce an anatomical region of interest which constrains the global affine motion estimation to a neighborhood around the endocardial surface. This is shown to substantially increase the tracking accuracy and robustness, while simultaneously reducing the required computation time. The proposed anatomical formulation of the optical flow problem is compared with a state-of-the-art real-time tracker and provides competitive performance in the estimation of relevant cardiac volumetric indices used in clinical practice.

Fast and fully automatic 3D echocardiographic segmentation using B-spline explicit active surfaces

We have recently introduced a novel framework to efficiently deal with 3D segmentation of challenging inhomogeneous data in real-time. However, the existing framework still relied on manual initialization, which prevented taking full advantage of the computational speed of the method. In the present manuscript we propose an automatic initialization scheme adapted to 3D echocardiographic data and we couple it with the existing segmentation framework. Moreover, a novel segmentation functional, which explicitly takes the darker appearance of the blood into account, is also proposed in the present manuscript. We show that fully automatic segmentation of the left ventricle using the proposed method provides an efficient, fast and accurate solution for quantification of the main cardiac indices used in routine clinical practice.