Surgical data science: mission de l'équipe

Le département Surgical Data Science (SDS) a pour but d’améliorer les résultats de la chirurgie grâce à des systèmes logiciels basés sur l’IA et pilotés par des données cliniques. La mission de notre équipe est de créer des systèmes innovants qui améliorent les capacités des équipes chirurgicales grâce à l’IA, pour réduire les complications, démocratiser la chirurgie et obtenir de meilleurs résultats pour les patients.

Disrumpere

L’échographie est une technologie clé pour détecter le cancer de l’abdomen tôt et le traiter avec une intervention minimale. Le projet disrumpere vise à combiner des appareils à ultrasons à faible coût avec des technologies innovantes d’IA et de robotique, afin de rendre les échographie plus faciles, plus rapides et plus largement utilisés.   

Systèmes de guidage de chirurgie laparoscopique avec réalité augmentée

Nous créons des systèmes informatiques pour améliorer la chirurgie laparoscopique grâce à la technologie de la réalité augmentée (RA). Il s’agit de fusionner des données d’images médicales en 3D, comme la tomographie ou l’imagerie par résonance magnétique, avec la vidéo laparoscopique, afin de montrer en temps réel l’emplacement des structures critiques telles que les tumeurs et les vaisseaux principaux. La réalité augmentée peut améliorer la sécurité, réduire la durée des opérations, simplifier les procédures complexes et rendre la chirurgie plus accessible dans les pays en développement.

Systèmes de guidage chirurgical percutané

La chirurgie percutanée est une technique très peu invasive permettant de biopsier et de traiter des lésions à l’aide de petites aiguilles passées à travers la peau. Nous créons des systèmes informatiques pour rendre la chirurgie percutanée plus facile, plus sûre, moins dépendante de l’opérateur, et pour étendre son utilisation aux tumeurs précoces et avancées, en utilisant une combinaison d’algorithmes logiciels innovants et de technologies de suivi des instruments en 3D.

Systèmes d'enseignement de l'échographie et de l'endoscopie flexible

Objective skill assessment is becoming an increasingly important component of surgery education and high-stakes skill assessment for accreditation. Our goal is to combine low-cost mechanical simulators with AI to make these tools broadly accessible.

Logiciels

Sight

Sight, the Surgical Image Guidance and Healthcare Toolkit facilitates the creation of software based on medical imaging.

It includes various features such as 2D and 3D medical image processing (CT/MRI/US), video processing, visualization, augmented reality, and connectivity with tracking systems. It can be used to write navigation systems, simulators, planning software, or even simple video filtering applications.

Sight is written in C++ and built on top of the best open-source libraries in the field such as OpenCV, ITK, VTK, PCL, and Qt and makes their usage easier by providing data common formats and wrappers. It is based on a modular object/service architecture, making building software application as simple as connecting together data, algorithms and user interface. It runs on Windows and Linux and is freely available under the LGPL.

Visualisation

  • Multi-Planar Reconstruction
  • Direct volume rendering
  • Mixed Rendering (Volume + Surfaces)
  • OpenGL 4.x programmable pipeline
  • Fast rendering pipeline

Formats and protocols

  • DICOM CT/MRI images
  • SCP/SCU
  • OpenIGTLink
  • Video files: MP4/AVI/MKV/…
  • Cameras: Intel Realsense, most USB webcams.
  • RTP/RTSP streaming

Fast prototyping

  • Interface and application design with XML or QML files
  • Reusable algorithms and widgets as services
  • Modular code, dynamic library loading
  • Easy application packaging
  • Prebuilt binaries for 3rd part libraries

Augmented reality

  • Camera calibration
  • Lens distortion and undistortion compensation
  • Virtual 2D/3D scene superimposition onto video
  • Precise synchronisation of the video and the virtual layer
  • Optical tracking with Aruco tags

Software applications

SightViewer

Medical image and segmentation viewer. It supports many popular formats including DICOM and VTK.

SightCalibrator

User-friendly application to calibrate mono and stereo cameras. Very handy since camera calibration is a prerequisite in any AR application.

Publications cliniques et techniques

Automatic Anatomical Segmentation of the Liver by Separation Planes

An Interactive Medical Segmentation System Based on the Optimal Management of Regions of Interest Using Topological Medical Knowledge

Virtual Reality Applied to Planning for Laparoscopic Adrenalectomy (video)

Evaluation of Virtual Reality Patient Reconstruction in the Assessment of Volume of Adrenal Tumors: An Initial Experience of 15 Cases

Set de données

Liver segmentation

3D-IRCADb-01

This dataset is composed of the CT-scans of 10 women and 10 men with hepatic tumors in 75% of cases.

Where appropriate, the Couinaud segment number corresponding to the location of tumors is also provided.

Respiratory cycle

3D-IRCADb-02

This dataset is composed of 2 anonymized CT-scans.

The first one has been realized during the arterial phase in inhaled position, whereas the second one has been realized during the portal phase in exhaled position.

The patient has a hepatic focal nodular hyperplasia in segment VII according to Couinaud’s description.

The DEPOLL dataset for evaluating registration accuracy in AR-guided liver surgery

DePoLL (the Deformable Porcine Laparoscopic Liver) dataset was created to quantitatively evaluate registration accuracy for AR-guided liver surgery using a pre-operative CT model.

Équipe SDS

Dr. Alexandre HOSTETTLER

Head of Research & Development Department

Sneakers addict

Dr. Flavien BRIDAULT

Director of Software Development

Computer Graphics, Software Engineering, Agile Methodology, Mindfulness, Vegetables Addict

Dr. Toby COLLINS

Director of Research

Research Communication, Machine Learning, Computer Vision, Medical Image Analysis, Project Management, The English Guy

Josiane UWINEZA

Research Engineer

Python, Data science, Machine Learning, Deep Learning, Computer Vision, Prayer

Dr. Alexandre ANCEL

Research Engineer

Software Engineering, Surgical Navigation Systems, Medical Image Analysis, Computer Graphics, Deep Learning, Emacs Evangelist

Marc SCHWEITZER

Senior Software Developer

Computer Vision, C++, CMake Developer, Bicycle Commuter²

Mathieu HALLER

Research Engineer

Data Science, Deep Learning, Python, C++, Scotland-Lover

Didier WECKMANN

Senior Software Developer

C++, Python, JavaScript, Software Architecture, Continuous Integration, Science Fanboy

Flavio MILANA

Fellow

Cyriaque ZIRIMWABAGABO

Research Engineer

Yvonne KEEZA

Medical Imaging Annotator

Medical Image Data Analysis, Radiology, Ultrasound, Project Management, Image Protocol and Annotations, Medical Technology Enthusiast, Salsa Dancer

Jean De Dieu NIYONTEZE

Research Engineer

Grace UFITINEMA

Medical Imaging Annotator

Medical Image Analysis, Radiography, Ultrasound, Annotation, Basketball-Lover

Luis MENDOZA

Senior Software Developer

Qt, C++, Computer Vision, Another guitar-playing, Football-loving latino

Baptiste PODVIN

Phd. Student

Shamim SEDGHI

Master Student

Nicolas PAPIER

Senior Software Developer

Florien UJEMURWEGO

Medical Imaging Annotator

Medical Image Analysis, Radiography, Ultrasound, Annotation, Medical Image Management, Swimming-Love

Güinther SAIBRO

Research Engineer

Python, Deep Learning, Statistics, Medical Image Analysis, Ultrasound, Cycling

Partenaires