Siemens Healthcare Gmbh

Institut National De Recherche En Informatique Et En Automatique

Inria Institut National De Recherche En Informatique Et En Automatique

Inria

Herve Delingette

Nicholas Ayache

Tommaso Mansi

Dorin Comaniciu

Ali Kamen

Saikiran Rapaka

Viorel Mihalef

Julian Krebs

Chloe Audigier

Puneet Sharma

Shun P Miao

Guillaume Picinbono

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

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

Growing community of inventors

La Colle sur Loup, France

Herve Delingette