A5014952217- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- 3D Shape Modeling and Analysis
- Surgical Simulation and Training
- Optical measurement and interference techniques
- Computer Graphics and Visualization Techniques
- Anatomy and Medical Technology
- Augmented Reality Applications
- Optical Imaging and Spectroscopy Techniques
- 3D Surveying and Cultural Heritage
- Infrared Thermography in Medicine
- Advanced Neural Network Applications
- Medical Image Segmentation Techniques
- Advanced Image and Video Retrieval Techniques
- Radiomics and Machine Learning in Medical Imaging
- Artificial Intelligence in Healthcare and Education
- Colorectal Cancer Screening and Detection
- Photoacoustic and Ultrasonic Imaging
- Medical Imaging and Analysis
- Cardiac, Anesthesia and Surgical Outcomes
- Pelvic and Acetabular Injuries
- Minimally Invasive Surgical Techniques
- Spectroscopy Techniques in Biomedical and Chemical Research
- AI in cancer detection
- Bariatric Surgery and Outcomes
Institut de Recherche contre les Cancers de l’Appareil Digestif
2017-2025
Institut de Chimie de Clermont-Ferrand
2023
Institut Pascal
2016-2023
Université de Strasbourg
2020
Université Clermont Auvergne
2010-2019
Centre National de la Recherche Scientifique
2012-2019
Sigma Clermont
2019
University of Edinburgh
2008-2016
Universidad Blas Pascal
2016
Clermont Université
2015
Contemporary endoscopic simultaneous localization and mapping (SLAM) methods accurately compute endoscope poses; however, they only provide a sparse 3-D reconstruction that poorly describes the surgical scene. We propose novel dense SLAM method whose qualities are: 1) monocular, requiring RGB images of handheld monocular endoscope; 2) fast, providing positional tracking scene reconstruction, running in parallel threads; 3) dense, yielding an accurate reconstruction; 4) robust, to severe...
We study a problem that we call Shape-from-Template, which is the of reconstructing shape deformable surface from single image and 3D template. Current methods in literature address case isometric deformations, relax isometry constraint to convex inextensibility constraint, solved using so-called maximum depth heuristic. these zeroth-order since they use point locations (the differential structure) solve inference perspective image. propose novel class first-order. The key idea both their...
A major research area in Computer Assisted Intervention (CAI) is to aid laparoscopic surgery teams with Augmented Reality (AR) guidance. This involves registering data from other modalities such as MR and fusing it the video real-time, reveal location of hidden critical structures. We present first system for AR guided uterus. works pre-operative or CT monocular laparoscopes, without requiring any additional interventional hardware optical trackers. novel robust solutions two main...
There are approximately 1.8 million diagnoses of colorectal cancer, 1 stomach and 0.6 esophageal cancer each year globally. An automatic computer-assisted diagnostic (CAD) tool to rapidly detect esophagogastric tissue in optical images would be hugely valuable a surgeon during an intervention. Based on colon dataset with 12 patients 10 patients, several state-of-the-art machine learning methods have been trained using hyperspectral imaging (HSI), including Support Vector Machines (SVM)...
Recovering a deformable surface's 3D shape from single view registered to template requires one provide additional constraints. A recent approach has been constrain the surface deform quasi-isometrically. This is applicable surfaces of materials such as paper and cloth. Current `closed-form' solutions solve convex approximation original problem whereby depth maximized under isometry constraints (this known maximum heuristic). No yet proposed for conformal case. We give unified formulation...
We aimed to evaluate the knowledge, attitude, and practices in application of AI emergency setting among international acute care surgeons.An online questionnaire composed 30 multiple choice open-ended questions was sent members World Society Emergency Surgery between 29th May 28th August 2021. The developed by a panel 11 experts approved WSES steering committee.200 participants answered survey, 32 were females (16%). 172 (86%) surgeons thought that will improve surgery. Fifty (25%) trained,...
Shape-from-Template (SfT) reconstructs the shape of a deforming surface from single image, 3D template and deformation prior. For isometric deformations, this is well-posed problem. However, previous methods which require no initialization break down when perspective effects are small, happens object small or viewed larger distances. That is, they do not handle all projection geometries. We propose stable SfT that accurately reconstruct for follow existing approach using first-order...
An active research objective in Computer Assisted Intervention (CAI) is to develop guidance systems aid surgical teams laparoscopic Minimal Invasive Surgery (MIS) using Augmented Reality (AR). This involves registering and fusing additional data from other modalities overlaying it onto the video realtime. We present first AR-based image system for assisted myoma localisation uterine laparosurgery. a framework semi-automatically pre-operative Magnetic Resonance Image (MRI) with deformable...
Thermal ablation is an acceptable alternative treatment for primary liver cancer, of which laser (LA) one the least invasive approaches, especially tumors in high-risk locations. Precise control LA effect required to safely destroy tumor. Although temperature imaging techniques provide indirect measurement thermal damage, a degree uncertainty remains about effect. Optical are currently emerging as tools directly assess tissue damage. Among them, hyperspectral (HSI) has shown promising...
Nerves are critical structures that may be difficult to recognize during surgery. Inadvertent nerve injuries can have catastrophic consequences for the patient and lead life-long pain a reduced quality of life. Hyperspectral imaging (HSI) is non-invasive technique combining photography with spectroscopy, allowing intraoperative biological tissue property quantification. We show, first time, HSI combined deep learning allows nerves other types automatically recognized in vivo hyperspectral...
Hyperspectral imaging (HSI) is a non-invasive modality already applied to evaluate hepatic oxygenation and discriminate different models of ischemia. Nevertheless, the ability HSI detect predict reperfusion damage intraoperatively was not yet assessed. Hypoxia caused by artery occlusion (HAO) in liver brings about dreadful vascular complications known as ischemia-reperfusion injury (IRI). Here, we show evaluation viability an HAO model with artificial intelligence-based analysis HSI. We have...