Projects
Our Fields of Interest
Augmented Surgery
Augmented fluoroscopy
We propose a deep learning approach for the visualization of vessels during image-guided procedures without the need for contrast agents or pre-operative 4D CTs.
Augmented Endovascular Surgery
Endovascular surgery is a medical specialty of minimally invasive procedures which treats pathologies affecting the blood vessels relying on the use of catheters, guide-wires and other endovascular devices. During the intervention, the clinician relies entirely on...
Augmented Reality for Liver Surgery
Despite the improvements of surgical techniques and tools, some surgical interventions, such as Augmented Reality for Liver Surgery, remain very challenging for surgeons. Especially for abdominal minimally invasive surgery where haptic and visual feedback are limited....
Augmented Ultrasound
Ultrasound (US) imaging is ideal for hepatic surgery guidance, but it has the disadvantage of limited field of view besides poor image quality. Fusing intraoperative US with preoperative data (multi modality registration) will solve these disadvantages and would be...
Kidney Augmented Reality Surgery
Kidney Augmented Reality Surgery project focused on the capability of AR to achieve this fusion in real-time and to compute the tumor position with high accuracy (less than 2mm). To achieve this accuracy, three studies are necessary: 1. Identification of salient...
Scientific Machine Learning
Augmented fluoroscopy
We propose a deep learning approach for the visualization of vessels during image-guided procedures without the need for contrast agents or pre-operative 4D CTs.
DeepPhysX
The purpose of DeepPhysX framework is to provide an interface between deep learning algorithms and numerical simulations. It is a full Python project with two main pipelines, allowing both to train artificial neural networks with simulated data and to use trained...
Optimus
The Optimus plugin was created to provide a testing environment for data-driven physics-based modeling (typically based on the finite element method). While the plugin currently implements only stochastic methods based on Kalman filtering, its architecture allows for...
Robotic Control
Cryoablation Planning
In interventional radiology, cryoablation is a growing technique for tumor ablation. Method: Several hollow needles are percutaneously inserted in the target area under image guidance and a gas (usually argon) is then de-compressed inside the needles. Based on the...
Robotic Needle Insertion
Needle insertion is a key procedure in minimally invasive surgery including percutaneous (through the skin) therapies. It is seemingly very simple: a surgeon aims the needle at the anatomical target (with the target position determined from high-quality medical image...
Neuroscience
Stochastic neuronal networks
Biological neuonal networks exhibit a strongly random structure and receives strongly fluctuating inputs. We investigate the impact of additive fluctuations on the dynamics of random networks and aim to explain synchronization observed in the mammalian brain.
Neurostimulation
According to the World Health Organization (WHO), the burden of mental disorders (MDs) continues to grow with significant impact on health and major social and human rights and economic consequences in all countries of the world. Today, there are effective prevention...
Finite Element Method
Caribou
The caribou project is aimed at multiphysics computation. It brings a plugin that complements SOFA multiphysics framework. It also provides generic C++ utilities, and SOFA components such as solvers and forcefields. The project is composed of two modules: the Caribou...
Liver Modeling
This project aims at developing accurate, real-time, patient-specific biomechanical liver and kidney models. These deformable models will be based on an optimal choice of material constitutive laws, patient-specific surface and volumetric meshes, and advanced...
Training
Everest
EVEREST research project funded by ANR (l’Agence National de la Recherche) is a project that aims at creation of Virtual Platform for Surgical Training. In this context, Flexible endoscopy is a minimally invasive surgical technique that remains very challenging to...
REBOA Training System
REBOA (Resuscitative Endovascular Balloon Occlusion of the Aorta) is a potentially life saving procedure to stem bleeding into the abdomen and lower body. A balloon catheter is inserted through into the common femoral artery in the groin specific zones in the aorta...
Open Source Softwares
Caribou
The caribou project is aimed at multiphysics computation. It brings a plugin that complements SOFA multiphysics framework. It also provides generic...
DeepPhysX
The purpose of DeepPhysX framework is to provide an interface between deep learning algorithms and numerical simulations. It is a full Python...
Optimus
The Optimus plugin was created to provide a testing environment for data-driven physics-based modeling (typically based on the finite element...
SOFA Framework
SOFA is an efficient and accurate simulation framework written in C++, developed by our team and researchers from a couple of other Inria teams. It...
Sofa Python 3
The objective of this plugin is to embed a python interpreter into a SOFA based simulation. It includes several python modules that expose many C++...