Biomedical subjects

Alessandro Sarti

Publications and source records attributed to Alessandro Sarti.

5 recordsLinked to original sources

PubMed2005

Maximum likelihood segmentation of ultrasound images with Rayleigh distribution.

This study presents a geometric model and a computational algorithm for segmentation of ultrasound images. A partial differential equation (PDE)-based flow is designed in order to achieve a maximum likelihood segmentation of the target in the scene. The flow is derived as the steepest descent of an energy functional taking into account the density probability distribution of the gray levels of the image as well as smoothness constraints. To model gray level behavior of ultrasound images, the classic Rayleigh probability distribution is considered. The steady state of the flow presents a maximum likelihood segmentation of the target. A finite difference approximation of the flow is derived, and numerical experiments are provided. Results are presented on ultrasound medical images as fetal echography and echocardiography.

Algorithms↗

PubMed2003

Binding and segmentation of multiple objects through neural oscillators inhibited by contour information.

Temporal correlation of neuronal activity has been suggested as a criterion for multiple object recognition. In this work, a two-dimensional network of simplified Wilson-Cowan oscillators is used to manage the binding and segmentation problem of a visual scene according to the connectedness Gestalt criterion. Binding is achieved via original coupling terms that link excitatory units to both excitatory and inhibitory units of adjacent neurons. These local coupling terms are time independent, i.e., they do not require Hebbian learning during the simulations. Segmentation is realized by a two-layer processing of the visual image. The first layer extracts all object contours from the image by means of "retinal cells" with an "on-center" receptive field. Information on contour is used to selectively inhibit Wilson-Cowan oscillators in the second layer, thus realizing a strong separation among neurons in different objects. Accidental synchronism between oscillations in different objects is prevented with the use of a global inhibitor, i.e., a global neuron that computes the overall activity in the Wilson-Cowan network and sends back an inhibitory signal. Simulations performed in a 50 x 50 neural grid with 21 different visual scenes (containing up to eight objects + background) with random initial conditions demonstrate that the network can correctly segment objects in almost 100% of cases using a single set of parameters, i.e., without the need to adjust parameters from one visual scene to the next. The network is robust with reference to dynamical noise superimposed on oscillatory neurons. Moreover, the network can segment both black objects on white background and vice versa and is able to deal with the problem of "fragmentation."The main limitation of the network is its sensitivity to static noise superimposed on the objects. Overcoming this problem requires implementation of more robust mechanisms for contour enhancement in the first layer in agreement with mechanisms actually realized in the visual cortex.

Artifacts↗

PubMed2002

Evolutionary partial differential equations for biomedical image processing.

We are presenting here a model for processing space-time image sequences and applying them to 3D echo-cardiography. The non-linear evolutionary equations filter the sequence with keeping space-time coherent structures. They have been developed using ideas of regularized Perona-Malik an-isotropic diffusion and geometrical diffusion of mean curvature flow type (Malladi-Sethian), combined with Galilean invariant movie multi-scale analysis of Alvarez et al. A discretization of space-time filtering equations by means of finite volume method is discussed in detail. Computational results in processing of 3D echo-cardiographic sequences obtained by rotational acquisition technique and by real-time 3D echo volumetrics acquisition technique are presented. Quantitative error estimation is also provided.

Algorithms↗

PubMed2002

Left ventricular volume estimation for real-time three-dimensional echocardiography.

The application of level set techniques to echocardiographic data is presented. This method allows semiautomatic segmentation of heart chambers, which regularizes the shapes and improves edge fidelity, especially in the presence of gaps, as is common in ultrasound data. The task of the study was to reconstruct left ventricular shape and to evaluate left ventricular volume. Data were acquired with a real-time three-dimensional (3-D) echocardiographic system. The method was applied directly in the three-dimensional domain and was based on a geometric-driven scheme. The numerical scheme for solving the proposed partial differential equation is borrowed from numerical methods for conservation law. Results refer to in vitro and human in vivo acquired 3-D + time echocardiographic data. Quantitative validation was performed on in vitro balloon phantoms. Clinical application of this segmentation technique is reported for 20 patient cases providing measures of left ventricular volumes and ejection fraction.

Echocardiography, Three-Dimensional↗

PubMedDate not supplied

From neural oscillations to variational problems in the visual cortex.

Aim of this study is to provide a formal link between connectionist neural models and variational psycophysical ones. We show that the solution of phase difference equation of weakly connected neural oscillators gamma-converges as the dimension of the grid tends to 0, to the gradient flow relative to the Mumford-Shah functional in a Riemannian space. The Riemannian metric is directly induced by the pattern of neural connections. Next, we embed the energy functional in the specific geometry of the functional space of the primary visual cortex, that is described in terms of a subRiemannian Heisenberg space. Namely, we introduce the Mumford-Shah functional with the Heisenberg metric and discuss the applicability of our main gamma-convergence result to subRiemannian spaces.

Animals↗