Visible Patient

Institut De Recherche Sur Les Cancers De I

Institut Hospitalo-universitaire De Strasbourg

Institut De Recherche Contre Les Cancers De L'appareil Digestif

Institut De Recherche Sur Les Cancers De L'appareil Digestif (ircad)

Institut De Recherche Sur Les Cancers De L'appareil Digestif—ircad (Association Regie Par Les Articles 21 A 79 Du Code Civil Et Local Et Inscrite Au Registre Des Associations Du Tribunal D'instance De Strasbourg)

Institut De Recherche Sur Les Cancers De L'appareil Degestif (ircad)

Cnam-conservatoire National Des Arts Et Metiers

Alexandre Hostettler

Jacques Marescaux

Luc Soler

Nicolas Thome

Clément Forest

Stephane Nicolau

Caroline Trompf

Toby Collins

Leonardo Sosa Valencia

Stéphane Nicolau

A system for medical navigation includes an echo-endoscope configured to acquire a real-time ultrasound signal and/or a video signal; a tracking system or device configured to track a distal tip of the echo-endoscope in space; a user interface and a display; computing and storing system containing pre-operative radiologic data of a patient; wherein the computing and storing system is configured to perform a registration between real-time intra-operative data and the pre-operative radiologic data and the display is configured to provide to the user a navigation view integrating real-time intra-operative data view within the pre-operative radiologic data based on said registration.

System and method for medical navigation

This invention concerns an automatic segmentation method of features, such as anatomical and pathological structures or instruments, which are visible in a 3D medical image of a subject, composed of voxels.

Automatic segmentation process of a 3D medical image by several neural networks through structured convolution according to the geometry of the 3D medical image

This invention concerns an automatic segmentation method of a medical image making use of a knowledge database containing information about the anatomical and pathological structures or instruments, that can be seen in a 3D medical image of a&#xd7;b&#xd7;n dimension, i.e. composed of n different 2D images each of a&#xd7;b dimension. Said method being characterised in that it mainly comprises three process steps, namely: a first step consisting in extracting from said medical image nine sub-images (to) of a/2&#xd7;b/2&#xd7;n dimensions, i.e. nine partially overlapping a/2&#xd7;b/2 sub-images from each 2D image; a second step consisting in nine convolutional neural networks (CNNs) analysing and segmenting each one of these nine sub-images (to) of each 2D image; a third step consisting in combining the results of the nine analyses and segmentations of the n different 2D images, and therefore of the nine segmented sub-images with a/2&#xd7;b/2&#xd7;n dimensions, into a single image with a&#xd7;b&#xd7;n dimension, corresponding to a single segmentation of the initial medical image.

Automatic segmentation process of a 3D medical image by one or several neural networks through structured convolution according to the anatomic geometry of the 3D medical image

An automatic process of predictive determination of the position and movements of the skin of a subject in a zone of interest, with the subject breathing freely or in an assisted manner, includes preliminarily acquiring multiple configurations of the skin profile in axial planes, at given successive times, in different respiratory positions, and for each axial plane, constructing at least one deformable digital model starting from different skin profiles, then noting, in a repetitive manner, the actual position of a point on the skin at the level of each axial plane, whose position is significantly modified during inhalation and exhalation phases, and providing, essentially in real time, a simulation of the skin profile in each axial plane, as a function of the actual position noted, and an evolving three-dimensional representation of the skin at the level of the zone of interest, by interpolation between the different axial planes.

Automatic method of predictive determination of the position of the skin

The invention relates to a method for the simulation or digital synthesis of echographic images, characterised by the direct transformation in real time, or quasi real time, of the information contained in a 3D scanographic (or tomodensitometric) medical or veterinary image, without delimitation or segmentation of the bodies or structures contained in the volume of scanographic data, according to at least one two-dimensional observation window which can be modified in real time, or quasi real time, in terms of the dimension, position, directions and orientation thereof, the characteristics thereof depending on the type of virtual echographic probe determined, and reproducing all of the attenuation, reflection, refraction and dispersion effects, and the regulation effects of a real echographic image, each echographic image supplied cumulating the results of the simulations of the pre-cited effects.

Process and system for simulation or digital synthesis of sonographic images

The invention relates to a method for the simulation or digital synthesis of echographic images, characterized by the direct transformation in real time, or quasi real time, of the information contained in an IRM-type medical or veterinary image, without delimitation or segmentation of the bodies or structures contained in the volume of data of the IRM image, according to at least one two-dimensional observation window which can be modified in real time, or quasi real time, in terms of the dimension, position, direction and orientation thereof, the characteristics thereof depending on the type of virtual echographic probe determined, and reproducing all of the attenuation, reflection, refraction and dispersion effects, and the regulation effects of a real echographic image, each echographic image supplied cumulating the results of the simulations of the pre-cited effects.

Growing community of inventors

Strasbourg, France

Alexandre Hostettler