Journal articles (8)

This paper describes a novelmethod for shape representation and robust image segmentation. The proposed method combines two well known methodologies, namely, statistical shape models and active contours implemented in level set framework. The shape detection is achieved by maximizing a posterior function that consists of a prior shape probability model and image likelihood function conditioned on shapes. The statistical shape model is built as a result of a learning process based on nonparametric probability estimation in a PCA reduced feature space formed by the Legendre moments of training silhouette images. A greedy strategy is applied to optimize the proposed cost function by iteratively evolving an implicit active contour in the image space and subsequent constrained optimization of the evolved shape in the reduced shape feature space. Experimental results presented in the paper demonstrate that the proposed method, contrary to many other active contour segmentation methods, is highly resilient to severe random and structural noise that could be present in the data.

---

It is progressively realized that noise can play a constructive role in the domain of nonlinear information processing. This phenomenon, also known as stochastic resonance (SR) effect, has experienced large varieties of extensions with variations concerning the type of noise, the type of information carrying signal or the type of nonlinear system interacting with the signal-noise mixture. In this article, we propose an interpretation for the mechanism of noise-enhanced image restoration with nonlinear PDE (Partial Differential Equation) recently demonstrated in literature. More precisely, a link is established between the action of noise in a nonlinear PeronaÐMalik anisotropic diffusion and stochastic resonance in memoryless nonlinear systems for 1-D signals. For illustration some preliminary results are presented on classical ÒcameramanÓ image and the inner of SR mechanism is theoretically and practically studied using a simple set of parameters regarding the PDE used and the modeling of boundaries within images.

---

Purpose: Noninvasive imaging assessment of cardiac function is important in cardiovascular disease diagnosis, especially for evaluation of local cardiac motion. Tagged Cardiac MRI has been developed for this purpose, but evaluation of the results requires quantification and automation. Method: Two methods utilizing active contour modeling for wall motion extraction based on tagged cardiac MRI scans were evaluated based on properties of tracking methods in the image domain and frequency domain. Three criteria were used: accuracy, inter-subject and intra-subject sensitivity. The tracking results were evaluated by a medical expert. The evaluation methodology and its possible generalization to other diagnostic methods were considered. Results: Image-domain and frequency-domain analysis of tagged cardiac MRI data sets were evaluated demonstrating that the image domain method provides better results. The image-domain method method is much more resistant to changes in the data, this time, due to a different subject being scanned. The frequency domain approach is not suitable for clinical applications, as the global error is significantly increased (more than 20%). Conclusion: The image-domain method was found most effective, and it can generate a set of clearly identified parameters. The evaluation approach can be an interesting alternative to classical psychovisual studies which are time consuming and often fastidious for clinicians.

Anisotropic regularization PDE’s (Partial Differential Equation) raised a strong interest in the field of image processing. The benefit of PDE-based regularization methods lies in the ability to smooth data in a nonlinear way, allowing the preservation of important image features (contours, corners or other discontinuities). In this article, a selective diffusion approach based on the framework of Extreme Physical Information theory is presented. It is shown that this particular framework leads to a particular regularization PDE which makes the integration of prior knowledge possible within the diffusion scheme. As a proof of feasibility, results of oriented pattern extractions are first presented on ad hoc images and second on a particular medical application: Tagged cardiac MRI (Magnetic Resonance Imaging) enhancement.

The non invasive assessment of cardiac function is of first importance for the diagnosis of cardiovascular diseases. Among all medical scanners only a few enables radiologists to evaluate the local cardiac motion: Tagged Cardiac MRI is one of them. This protocol generates on Short-Axis (SA) sequences a dark grid which is deformed in accordance with the cardiac motion. Tracking the grid allows specialists a local estimation of cardiac geometrical parameters within myocardium. The work described in this paper aims to automate the myocardial contours detection in order to optimize the detection and the tracking of the grid of tags within myocardium. The method we have developed for endocardial and epicardial contours detection is based on the use of texture analysis and active contours models. Texture analysis allows us to define energy maps more efficient than those usually used in active contours methods where attractor is often based on gradient and which were useless in our case of study, for quality of tagged cardiac MRI is very poor.

The noninvasive evaluation of the cardiac function presents a great interest for the diagnosis of cardiovascular diseases. Cardiac tagged MRI allows the measurement of anatomical and functional myocardial parameters. This protocol generates a dark grid which is deformed with the myocardium. As a consequence, the tracking of the grid allows the displacement estimation in the myocardium. The work described in this paper aims to automate the myocardial contours detection and the following of the grids of tags on Short-Axis time sequences, in order to firstly optimize the 2D+T study of the parietal contractions and secondly make possible its clinical use. The method we have developed for endocardial and epicardial contours detection is based on the use of texture analysis and active contours models. Texture analysis allows us to define energy maps more efficient than those usually used in active contours methods where attractor is often based on gradient and which were useless in our case of study. The follow-up of the grid of tags that we have implemented is based on a grid of active contours (B-snakes) which part of the energy is issued from a particular selective diffusion process which leading equation is based on the recent work of [8]. The results obtained with our method is fully automatic and correct on Short-Axis sequences, when previous works on cardiac tagged MR images analysis always used manual contours detection.

We propose a nonlinear variational approach to remove impulsive noise in scalar images. Taking benefit from recent studies on the use of stochastic resonance and the constructive role of noise in nonlinear processes, our process is based on the classical restoration process of Perona-Malik in which a Gaussian noise is purposely injected. We show that this new process can outperform the original restoration process of Perona-Malik from which it is inspired.

The noninvasive evaluation of the cardiac function presents a great interest for the diagnosis of cardiovascular diseases. Tagged cardiac MRI allows the measurement of anatomical and functional myocardial parameters. This protocol generates a dark grid which is deformed with the myocardium displacement on both Short-Axis (SA) and Long-Axis (LA) frames in a time sequence. Visual evaluation of the grid deformation allows the estimation of the displacement inside the myocardium. The work described in this paper aims to make robust and reliable the visual enhancement of the grid tags on cardiac MRI sequences, thanks to an informational formalism based on Extreme Physical Informational (EPI). This approach leads to the development of an original diffusion pre-processing allowing us to make better the robustness of the visual detection and the following of the grid of tags.