Tag: Hospital Clínic

  • ENDOSCOPY

    ENDOSCOPY

    Project Description

    iVENDIS: Intelligent In-vivo Endoscopy Navigation, Diagnosis and Intervention Support systems.

    One of the main limitations of endoscopic procedures is the impossibility to get accurate 3D measures and location of the injured tissue which may lead to the repetition of some interventions with an additional cost for the healthcare system. Another limitation is the lack of objective tissue characterization to allow in-vivo diagnosis, delaying decision taking and patient treatment beginning. Therefore, clinicians are in urgent need of systems able to provide on-line 3D measurements, 3D positioning and objective tissue characterization tools during the endoscopic intervention. iVENDIS aims at on-line extraction of physiological data from endoscopy interventional videos for building up better lesion detection, diagnosis and treatment planning systems.

    iVENDIS is composed by three main products: SENSA, 3DEND and SAIPHIC.

    Machine Vision group is also involved in this project.


    CLINICAL PARTNERS

    Hospital Clínic de Barcelona, Hospital de Bellvitge

    FUNDING

    Fundació La Marató de TV3, TIN2012-33116, 2014PROD00065, DPI2015-65286-R


    SENSA

    A system for Endoscopic Stenosis Assessment (SENSA) for real- time segmentation of tracheal main anatomical structures in videobronchoscopy to provide accurate standardized measurement of tracheal obstructions.

    3DEND

    3D Bronchoscopy Navigation and Diagnosis system (3DEND) for increasing the yield of lung biopsy that incorporates a virtual bronchoscopy planner taking into account the bronchoscope’s kinematic constraints as well as bronchi breathing dynamics in order to guide the bronchoscope operator in real-time to peripheral pulmonary lesions that currently cannot be reached.

    SAIPHIC

    A system for automatic in-vivo polyp histology characterization (SAIPHIC) for providing the first on-line objective lesion diagnosis system considering both tissue visual features and an estimation of polyp size.

  • MEDIAL SURFACE COMPUTATION

    MEDIAL SURFACE COMPUTATION

    Project Description

    Medial branching is usually associated to perturbations of the object bound- ary rather than to its main geometric features. Such instability of the medial surface is a main obstacle for its confident application in shape recognition and description. Medial branches correspond to singularities of the medial surface and, thus, they are problematic for existing morphological and energy-based al- gorithms. In this paper, we use algebraic geometry concepts in an energy-based approach to compute a medial surface presenting a stable branching topology. We also present an efficient GPU-CPU implementation using standard image processing tools. The higher performance of our method in terms of compu- tational cost and medial surface quality is shown on a home-made synthetic database. Finally, we present some results on a medical imaging application for localization of abdominal pathologies.


    PARTNERS

    Hospital Sant Pau, AlmaITSystems, Universitat Pompeu Fabra, Hospital Clínic

    FUNDING

    TIN2012-33116