Search results for " Segmentation"

showing 10 items of 462 documents

Augmented reality based middle and inner ear surgical procedures

2020

Otologic procedures involve manipulation of small, delicate and complex structures in the temporal bone anatomy which are in close proxmity of critical nerves and blood vessels. Augmented reality (AR) can highly benefit the otological domain by providing supplementary anatomical and navigational information unified on a single display. However, despite being composed of mainly rigid bony structures, the awareness and acceptance of possibilities of AR systems in otology is fairly low. This project aims at developing video-based AR solutions for middle and inner ear surgical procedures.We propose two applications of AR in this regard. In the first application, information about middle ear cle…

Transtympanic proceduresProcédures transtympaniquesCochlear implant surgeryOtologyAugmented realityMedical image segmentationSegmentation d’image de l'oreilleOtologie[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]Minimally invasive surgery[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]Chirurgie mini-InvasiveChirurgie d'implant cochléaireRéalité augmentée
researchProduct

Segmenting the spectators of national team sports: the case of a pre-competition match

2015

It has become common for academics and sports marketing professionals to study and explain the heterogeneity and complexity of sports spectators' behaviours and attitudes, with numerous works addressing this topic But these surveys are more about fans of professional sports clubs (soccer, basketball, baseball, hockey, etc) who attend regular season games in their favourite teams' home stadium or arena. To our knowledge, very few studies have been conducted into spectators of national teams. It is these spectators who are of the focus of this paper.

MarketingCompetition (economics)FavouriteFocus (computing)Sports spectatorsBasketballMarket segmentationAdvertisingSociologyBusiness and International ManagementSports marketingStadiumFinanceInternational Journal of Sports Marketing and Sponsorship
researchProduct

K-nearest neighbor driving active contours to delineate biological tumor volumes

2019

Abstract An algorithm for tumor delineation in positron emission tomography (PET) is presented. Segmentation is achieved by a local active contour algorithm, integrated and optimized with the k-nearest neighbor (KNN) classification method, which takes advantage of the stratified k-fold cross-validation strategy. The proposed approach is evaluated considering the delineation of cancers located in different body districts (i.e. brain, head and neck, and lung), and considering different PET radioactive tracers. Data are pre-processed in order to be expressed in terms of standardized uptake value, the most widely used PET quantification index. The algorithm uses an initial, operator selected re…

0209 industrial biotechnologyK-nearest neighborComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONFDG and MET PET imagingStandardized uptake value02 engineering and technologyImaging phantomk-nearest neighbors algorithmActive contour algorithm020901 industrial engineering & automationArtificial IntelligenceRegion of interest0202 electrical engineering electronic engineering information engineeringSegmentationElectrical and Electronic EngineeringActive contour modelbusiness.industryProcess (computing)Pattern recognitionCancer segmentationBiological target volumeControl and Systems Engineering020201 artificial intelligence & image processingArtificial intelligencebusinessEnergy (signal processing)Engineering Applications of Artificial Intelligence
researchProduct

Hidden Markov Random Fields and Direct Search Methods for Medical Image Segmentation

2016

The goal of image segmentation is to simplify the representation of an image to items meaningful and easier to analyze. Medical image segmentation is one of the fundamental problems in image processing field. It aims to provide a crucial decision support to physicians. There is no one way to perform the segmentation. There are several methods based on HMRF. Hidden Markov Random Fields (HMRF) constitute an elegant way to model the problem of segmentation. This modelling leads to the minimization of an energy function. In this paper we investigate direct search methods that are Nelder-Mead and Torczon methods to solve this optimization problem. The quality of segmentation is evaluated on grou…

Segmentation-based object categorizationbusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-space segmentationImage processing02 engineering and technologyImage segmentationMachine learningcomputer.software_genreSørensen–Dice coefficient0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingSegmentationArtificial intelligenceHidden Markov random fieldHidden Markov modelbusinesscomputerMathematicsProceedings of the 5th International Conference on Pattern Recognition Applications and Methods
researchProduct

Novel VAMPIRE algorithms for quantitative analysis of the retinal vasculature

2013

This paper summarizes three recent, novel algorithms developed within VAMPIRE, namely optic disc and macula detection, arteryvein classification, and enhancement of binary vessel masks, and their performance assessment. VAMPIRE is an international collaboration growing a suite of software tools to allow efficient quantification of morphological properties of the retinal vasculature in large collections of fundus camera images. VAMPIRE measurements are currently mostly used in biomarker research, i.e., investigating associations between the morphology of the retinal vasculature and a number of clinical and cognitive conditions.

retinaRetinaSettore INF/01 - InformaticaContextual image classificationbusiness.industryComputer scienceVampireRetinalImage segmentationClassificationFeature detectionRetina; Feature detection; Segmentation; Classification; Biomarkerschemistry.chemical_compoundSegmentationmedicine.anatomical_structurechemistrymedicineSegmentationComputer visionArtificial intelligencebusinessAlgorithmBiomarkersOptic discFeature detection (computer vision)2013 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC)
researchProduct

Benchmarking Wilms’ tumor in multisequence MRI data: why does current clinical practice fail? Which popular segmentation algorithms perform well?

2019

Wilms' tumor is one of the most frequent malignant solid tumors in childhood. Accurate segmentation of tumor tissue is a key step during therapy and treatment planning. Since it is difficult to obtain a comprehensive set of tumor data of children, there is no benchmark so far allowing evaluation of the quality of human or computer-based segmentations. The contributions in our paper are threefold: (i) we present the first heterogeneous Wilms' tumor benchmark data set. It contains multisequence MRI data sets before and after chemotherapy, along with ground truth annotation, approximated based on the consensus of five human experts. (ii) We analyze human expert annotations and interrater varia…

Image ProcessingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION610 Medicine & healthMachine learningcomputer.software_genre030218 nuclear medicine & medical imagingSet (abstract data type)03 medical and health sciences0302 clinical medicineMedical imagingMedicineRadiology Nuclear Medicine and imagingSegmentationRadiation treatment planningbusiness.industry10042 Clinic for Diagnostic and Interventional RadiologyWilms' tumorBenchmarkingImage segmentationmedicine.disease3. Good healthComputingMethodologies_PATTERNRECOGNITION030220 oncology & carcinogenesisBenchmark (computing)Artificial intelligencebusinesscomputerJournal of Medical Imaging
researchProduct

Fuzzy temporal random sets with an application to cell biology

2007

Total Internal Reflection Fluorescence Microscopy (TIRFM) greatly facilitates to imaging the first steps of endocytosis, a process whereby cells traffic cargo from the cell surface to endosomes. Using TIRFM, fluorescent-tagged endocytic proteins are observed as overlapped areas forming random clumps of different sizes, shapes and durations. A common procedure to segment these objects consists of thresholding the original gray-level images to produce binary sequences in which a pixel is covered or not by a given fluorescent-tagged protein. This binary logic is not appropriate because it leaves a free tuning parameter to be set by the user which can influence on the conclusions of the statist…

business.industryBinary imageFuzzy setPattern recognitionFunction (mathematics)Image segmentationFuzzy logicThresholdingSet (abstract data type)Computer visionArtificial intelligencebusinessIndependence (probability theory)Mathematics2007 IEEE International Fuzzy Systems Conference
researchProduct

Approximation of Pore Space with Ellipsoids: A Comparison of a Geometrical Method with a Statistical one

2018

We work with tomographic images of pore space in soil. The images have large dimensions and so in order to speed-up biological simulations (as drainage or diffusion process in soil), we want to describe the pore space with a number of geometrical primitives significantly smaller than the number of voxels in pore space. In this paper, we use the curve skeleton of a volume to segment it into some regions. We describe the method to compute the curve skeleton and to segment it with a simple segment approximation. We approximate each obtained region with an ellipsoid. The set of final ellipsoids represents the geometry of pore space and will be used in future simulations. We compare this method …

EllipsoidsGeometry02 engineering and technologyImage segmentation010502 geochemistry & geophysicscomputer.software_genreCurve skeleton01 natural sciencesEllipsoidPhysics::GeophysicsSet (abstract data type)SegmentationDiffusion processVoxelSimple (abstract algebra)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingSegmentationCluster analysisPore space approximationcomputer0105 earth and related environmental sciencesMathematics2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)
researchProduct

Automatic Segmentation of HEp-2 Cells Based on Active Contours Model

2018

In the past years, a great deal of effort was put into research regarding Indirect Immunofluorescence techniques with the aim of development of CAD systems. In this work a method for segmenting HEp-2 cells in IIF images is presented. Such task is one of the most challenging of automated IIF analysis, because the segmentation algorithm has to cope with a large heterogeneity of shapes and textures. In order to address this problem, numerous techniques and their combinations were evaluated, in a process aimed at maximizing the figure of merit. The proposed method, for a greater definition of cellular contours, uses the active contours in the last phase of the process. The initial conditions, c…

Active contour modelComputer sciencebusiness.industryHEp-2 cellComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONProcess (computing)Pattern recognitionEllipseDice indexSettore FIS/07 - Fisica Applicata(Beni Culturali Ambientali Biol.e Medicin)Hough transformlaw.inventionRandomized Hough transformHough transformlawPosition (vector)Convergence (routing)SegmentationArtificial intelligencebusinessActive contours modelCells segmentationIIF imagesProceedings of the 2018 3rd International Conference on Biomedical Imaging, Signal Processing
researchProduct

Valutazione quantitativa tridimensionale del parenchima polmonare affetto da fibrosi cistica : risultati preliminari

2007

Purpose. The aim of this study was to assess the feasibility of three-dimensional (3D) reconstructions and quantitative analysis of the volume of each component of the lung with cystic fibrosis (CF). Materials and methods. Twenty-two patients with CF (mean age 17±8 yeas) were included in the study. The patients underwent an unenhanced single-slice spiral computed tomography (CT) chest scan with the following parameters: collimation 3 mm, table feed 6 mm×rot-1, reconstruction interval 1 mm, soft tissue reconstruction kernel. Four image data sets were obtained: native axial slices, cine-mode display, virtual bronchographic volumerendered images with algorithm for tissue transition display and…

Cystic fibrosis CT densitometry Volume rendering three-dimensional Segmentation
researchProduct