Inria Institut National De Recherche En Informatique Et En Automatique

Institut National De Recherche En Informatique Et En Automatique

Siemens Healthcare Gmbh

Mauna Kea Technologies

Inria

Inria Institut National De Recherche

Inria Institut National De Recherche En Informatique Et En Antomatique

Nicholas Ayache

Herve Delingette

Tommaso Mansi

Aymeric Perchant

Xavier Pennec

Gregoire Malandain

Dorin Comaniciu

Ali Kamen

Saikiran Rapaka

Viorel Mihalef

Julian Krebs

Tom Vercauteren

Chloe Audigier

Jean-Philippe Thirion

Puneet Sharma

Shun P Miao

Francois Lacombe

François Lacombe

Georges Le Goualher

Jacques Feldmar

Grégoire Malandain

David Rey

Jonathan Stoeckel

Guillaume Picinbono

Herv&eacute; Delingette

St&eacute;phace Cotin

Alexis Roche

J&egrave;r&ocirc;me Declerck

Alexis Gourdon

Olivier Monga

For registration of medical images with deep learning, a neural network is designed to include a diffeomorphic layer in the architecture. The network may be trained using supervised or unsupervised approaches. By enforcing the diffeomorphic characteristic in the architecture of the network, the training of the network and application of the learned network may provide for more regularized and realistic registration.

Medical imaging diffeomorphic registration based on machine learning

Systems and methods for performing a medical imaging analysis task using a machine learning based motion model are provided. One or more medical images of an anatomical structure are received. One or more feature vectors are determined. The one or more feature vectors are mapped to one or more motion vectors using the machine learning based motion model. One or more deformation fields representing motion of the anatomical structure are determined based on the one or more motion vectors and at least one of the one or more medical images. A medical imaging analysis task is performed using the one or more deformation fields.

Probabilistic motion model for generating medical images or medical image sequences

A method and system for personalized computation of tissue ablation extent based on medical images of a patient is disclosed. A patient-specific anatomical model of the liver and liver vessels is estimated from medical image data of a patient. Blood flow in the liver and liver vessels is simulated. An ablation simulation is performed that uses a bio-heat model to simulate heat diffusion due to an ablation based on the simulated blood flow and a cellular necrosis model to simulate cellular necrosis in the liver based on the simulated heat diffusion. Personalized tissue parameters of the bio-heat model and the cellular necrosis model are estimated based on observed results of a preliminary ablation procedure. Planning of the ablation procedure is then performed using the personalized bio-heat equation and the cellular necrosis model. The model can be subsequently refined as more ablation observations are obtained.

System and method for personalized computation of tissue ablation extent based on medical images

A method and system for tumor ablation planning and guidance based on a patient-specific model of liver tumor ablation is disclosed. A patient-specific anatomical model of the liver and circulatory system of the liver is estimated from 3D medical image data of a patient. Blood flow in the liver and the circulatory system of the liver is simulated based on the patient-specific anatomical model. Heat diffusion due to ablation is simulated based on a virtual ablation probe position and the simulated blood flow in the liver and the venous system of the liver. Cellular necrosis in the liver is simulated based on the simulated heat diffusion. A visualization of a simulated necrosis region is generated and displayed to the user for decision making and optimal therapy planning and guidance.

System and method for patient specific modeling of liver tumor ablation

A method for mosaicing frames from a video sequence is disclosed. Each frame is constituted by a point cloud, and each point in the point cloud is potentially acquired at a different time. The method involves compensating for motion and motion distortion due to acquisition time differences in each frame, applying a global optimization of inter-frame registration to align consistently the frames, and applying a reconstruction algorithm on the registered frames to construct a mosaic.

Robust mosaicing method, notably with correction of motion distortions and tissue deformations for a vivo fibered microscopy

A mosaicing method taking into account motion distortions, irregularly sampled frames and non-rigid deformations of the imaged tissue. The method for mosaicing frames from a video sequence acquired from a scanning device such as a scanning microscope, includes the steps of: a) compensating for motion and motion distortion due to the scanning microscope, b) applying a global optimization of inter-frame registration to align consistently the frames c) applying a construction algorithm on the registered frames to construct a mosaic, and d) applying a fine frame-to-mosaic non rigid registration. The method is based on a hierarchical framework that is able to recover a globally consistent alignment of the input frames, to compensate for the motion distortions and to capture the non-rigid deformations.

Robust mosaicing method, notably with correction of motion distortions and tissue deformations for in vivo fibered microscopy

The invention relates to a method for measuring the speed of a particle such as a red blood cell moving inside a flow such as a flow of the blood, using a light scanning microscope. The inventive method comprises the following steps: acquisition of an image by x and y light scanning on a plane containing the object; detection on the plane (x, y) of a mark on the plane (x, y); estimation of the speed vof the object from the gradient thus determined.

Method and system for measuring the speed of blood flow

The invention concerns an image processing device, including an input for receiving a time series of data sets representing comparable volume digital images, each data having a position component and an intensity component, pre-processing means for modifying the data sets so as to obtain images updated in position and intensity, and comparative processing means for examining sets of time series of image elements and to detect therein signs of variations. The processing means include a modeling function for adjusting a parametric model separately on some of the sets of time series of image elements, to obtain pairs of data (image element, time) and a function for statistical analysis of said pairs of data to isolate the pairs of data representing a significant variation.

Image processing device and method for detecting developing lesions

The invention relates to the simulation of the deformation of materials, notably of soft body tissues. An apparatus comprises a memory (MEM, NT) storing data as to the position of an object, recorded at the vertices of a grid pattern, and data for force to be exerted on the object. A computer (&#x3bc;P, MT) evaluates new positions of the vertices, as a function of a force exerted globally and mechanical parameters of the material. According to the invention, this computer comprises a module for calculating, for each mesh, a deviation between the current length of an edge and its previous length, and the force data at each vertex of the mesh. Another module calculates, for each vertex, new positional data relating to this vertex as a function of the forces exerted thereon and its previous position.

Apparatus for simulating the deformation of materials, notably of soft body tissues

An electronic device for processing image data, particularly image data pertaining to medical procedures, includes a user interface with force feedback ( ) corresponding to tool reactions, a &ldquo;collision&rdquo; module ( ) for estimating a point of intersection between a straight line embodying a displacement derived from the action of the tool and a surface mesh of a given object, and an internal forces module ( ) which estimates internal forces exerted on nodes of a first part of at least a volume mesh of the object, on the basis of a displacement applied on nodes pertaining to the surface mesh containing a point of intersection, of boundary conditions, and of node tensors and link tensors, from matrices of rigidity, and a reaction module ( ) for determining the reaction force of the object corresponding to its deformation estimated on the basis of the internal forces, such that the force generated by the user interface ( ) is balanced by reaction force.

Electronic device for processing image-data, for simulating the behaviour of a deformable object

An electronic data processing device receives first and second data sets representing first and second comparable digital images. It comprises registration means comprising a first module which calculates a main function representative of the correlation ratios between the data of the first and second sets, and a second module which determines a registration transformation between one of the images and the other from the main function.

Electronic device for automatic registration of images

An electronic processing device receives sets of image data representing respectively sequential three-dimensional digital images of the same region. This device comprises means capable of defining a three-dimensional shape of interest on the basis of at least one of the sets of image data, and of extracting from each set image data representing characteristic points of the shape of interest, processing means for establishing on the basis of the image data of the contours a spatial-temporal planispheric transformation making it possible to pass from characteristic points extracted from one image to the characteristic points extracted from another image of the sequence, and means for displaying selected motion data derived from the parameters of the transformation.

Electronic image processing device for the detection of motions

An image is defined, in correspondence with a predetermined polyhedral meshing of a portion of the space, by a numerical value for each vertex of the meshing. Polygon processing includes receiving a representation of a plane polygon with p vertices, p respective values for these p vertices, and a threshold. In correspondence with the polygon, polygon processing supplies a list of oriented segments linking points of the edges of the polygon which are interpolated as being equal to the threshold, with a predetermined direction convention. Polyhedron processing includes receiving a representation of a polyhedron with the values at its vertices and a threshold. Polyhedron processing then invokes polygon processing for all the faces of the polyhedron, which supplies a list of oriented segments. Polyhedron processing then associates with the polyhedron a list of closed and oriented cycles, constituted by segments from the said list of segments. Main processing includes sequentially presenting a plurality of polyhedrons of the polyhedrons meshing for the polyhedron processing, with the values associated with their vertices and a threshold. The cycles thus obtained belong to an iso-surface of the image for the threshold value.

Growing community of inventors

Nice, France

Nicholas Ayache