toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Carles Sanchez; Miguel Viñas; Coen Antens; Agnes Borras; Debora Gil edit  url
doi  openurl
  Title Back to Front Architecture for Diagnosis as a Service Type Conference Article
  Year 2018 Publication 20th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing Abbreviated Journal  
  Volume Issue Pages 343-346  
  Keywords  
  Abstract (up) Software as a Service (SaaS) is a cloud computing model in which a provider hosts applications in a server that customers use via internet. Since SaaS does not require to install applications on customers' own computers, it allows the use by multiple users of highly specialized software without extra expenses for hardware acquisition or licensing. A SaaS tailored for clinical needs not only would alleviate licensing costs, but also would facilitate easy access to new methods for diagnosis assistance. This paper presents a SaaS client-server architecture for Diagnosis as a Service (DaaS). The server is based on docker technology in order to allow execution of softwares implemented in different languages with the highest portability and scalability. The client is a content management system allowing the design of websites with multimedia content and interactive visualization of results allowing user editing. We explain a usage case that uses our DaaS as crowdsourcing platform in a multicentric pilot study carried out to evaluate the clinical benefits of a software for assessment of central airway obstruction.  
  Address Timisoara; Rumania; September 2018  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference SYNASC  
  Notes IAM; 600.145 Approved no  
  Call Number Admin @ si @ SVA2018 Serial 3360  
Permanent link to this record
 

 
Author Debora Gil; Antonio Esteban Lansaque; Sebastian Stefaniga; Mihail Gaianu; Carles Sanchez edit  url
openurl 
  Title Data Augmentation from Sketch Type Conference Article
  Year 2019 Publication International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging Abbreviated Journal  
  Volume 11840 Issue Pages 155-162  
  Keywords Data augmentation; cycleGANs; Multi-objective optimization  
  Abstract (up) State of the art machine learning methods need huge amounts of data with unambiguous annotations for their training. In the context of medical imaging this is, in general, a very difficult task due to limited access to clinical data, the time required for manual annotations and variability across experts. Simulated data could serve for data augmentation provided that its appearance was comparable to the actual appearance of intra-operative acquisitions. Generative Adversarial Networks (GANs) are a powerful tool for artistic style transfer, but lack a criteria for selecting epochs ensuring also preservation of intra-operative content.

We propose a multi-objective optimization strategy for a selection of cycleGAN epochs ensuring a mapping between virtual images and the intra-operative domain preserving anatomical content. Our approach has been applied to simulate intra-operative bronchoscopic videos and chest CT scans from virtual sketches generated using simple graphical primitives.
 
  Address Shenzhen; China; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CLIP  
  Notes IAM; 600.145; 601.337; 600.139; 600.145 Approved no  
  Call Number Admin @ si @ GES2019 Serial 3359  
Permanent link to this record
 

 
Author Joel Barajas; Jaume Garcia; Francesc Carreras; Sandra Pujades; Petia Radeva edit   pdf
url  isbn
openurl 
  Title Angle Images Using Gabor Filters in Cardiac Tagged MRI Type Conference Article
  Year 2005 Publication Proceeding of the 2005 conference on Artificial Intelligence Research and Development Abbreviated Journal  
  Volume Issue Pages 107-114  
  Keywords Angle Images, Gabor Filters, Harp, Tagged Mri  
  Abstract (up) Tagged Magnetic Resonance Imaging (MRI) is a non-invasive technique used to examine cardiac deformation in vivo. An Angle Image is a representation of a Tagged MRI which recovers the relative position of the tissue respect to the distorted tags. Thus cardiac deformation can be estimated. This paper describes a new approach to generate Angle Images using a bank of Gabor filters in short axis cardiac Tagged MRI. Our method improves the Angle Images obtained by global techniques, like HARP, with a local frequency analysis. We propose to use the phase response of a combination of a Gabor filters bank, and use it to find a more precise deformation of the left ventricle. We demonstrate the accuracy of our method over HARP by several experimental results.  
  Address Amsterdam; The Netherlands  
  Corporate Author Thesis  
  Publisher IOS Press Place of Publication Amsterdam, The Netherlands Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 1-58603-560-6 Medium  
  Area Expedition Conference CAIRD  
  Notes IAM;MILAB Approved no  
  Call Number BCNPCL @ bcnpcl @ BGC2005; IAM @ iam Serial 595  
Permanent link to this record
 

 
Author David Roche; Debora Gil; Jesus Giraldo edit   pdf
doi  isbn
openurl 
  Title Detecting loss of diversity for an efficient termination of EAs Type Conference Article
  Year 2013 Publication 15th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing Abbreviated Journal  
  Volume Issue Pages 561 - 566  
  Keywords EA termination; EA population diversity; EA steady state  
  Abstract (up) Termination of Evolutionary Algorithms (EA) at its steady state so that useless iterations are not performed is a main point for its efficient application to black-box problems. Many EA algorithms evolve while there is still diversity in their population and, thus, they could be terminated by analyzing the behavior some measures of EA population diversity. This paper presents a numeric approximation to steady states that can be used to detect the moment EA population has lost its diversity for EA termination. Our condition has been applied to 3 EA paradigms based on diversity and a selection of functions
covering the properties most relevant for EA convergence.
Experiments show that our condition works regardless of the search space dimension and function landscape.
 
  Address Timisoara; Rumania;  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-1-4799-3035-7 Medium  
  Area Expedition Conference SYNASC  
  Notes IAM; 600.044; 600.060; 605.203 Approved no  
  Call Number Admin @ si @ RGG2013c Serial 2299  
Permanent link to this record
 

 
Author Aura Hernandez-Sabate; Debora Gil; Petia Radeva; E.N.Nofrerias edit   pdf
doi  openurl
  Title Anisotropic processing of image structures for adventitia detection in intravascular ultrasound images Type Conference Article
  Year 2004 Publication Proc. Computers in Cardiology Abbreviated Journal  
  Volume 31 Issue Pages 229-232  
  Keywords  
  Abstract (up) The adventitia layer appears as a weak edge in IVUS images with a non-uniform grey level, which difficulties its detection. In order to enhance edges, we apply an anisotropic filter that homogenizes the grey level along the image significant structures (ridges, valleys and edges). A standard edge detector applied to the filtered image yields a set of candidate points prone to be unconnected. The final model is obtained by interpolating the former line segments along the tangent direction to the level curves of the filtered image with an anisotropic contour closing technique based on functional extension principles  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Chicago (USA) Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes IAM; MILAB Approved no  
  Call Number IAM @ iam @ HGR2004 Serial 1555  
Permanent link to this record
 

 
Author Paula Fritzsche; C.Roig; Ana Ripoll; Emilio Luque; Aura Hernandez-Sabate edit   pdf
doi  openurl
  Title A Performance Prediction Methodology for Data-dependent Parallel Applications Type Conference Article
  Year 2006 Publication Proceedings of the IEEE International Conference on Cluster Computing Abbreviated Journal  
  Volume Issue Pages 1-8  
  Keywords  
  Abstract (up) The increase in the use of parallel distributed architectures in order to solve large-scale scientific problems has generated the need for performance prediction for both deterministic applications and non-deterministic applications. In particular, the performance prediction of data dependent programs is an extremely challenging problem because for a specific issue the input datasets may cause different execution times. Generally, a parallel application is characterized as a collection of tasks and their interrelations. If the application is time-critical it is not enough to work with only one value per task, and consequently knowledge of the distribution of task execution times is crucial. The development of a new prediction methodology to estimate the performance of data-dependent parallel applications is the primary target of this study. This approach makes it possible to evaluate the parallel performance of an application without the need of implementation. A real data-dependent arterial structure detection application model is used to apply the methodology proposed. The predicted times obtained using the new methodology for genuine datasets are compared with predicted times that arise from using only one execution value per task. Finally, the experimental study shows that the new methodology generates more precise predictions.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes IAM Approved no  
  Call Number IAM @ iam @ FRR2006 Serial 1497  
Permanent link to this record
 

 
Author Petia Radeva; Enric Marti edit   pdf
doi  openurl
  Title An improved model of snakes for model-based segmentation Type Conference Article
  Year 1995 Publication Proceedings of Computer Analysis of Images and Patterns Abbreviated Journal  
  Volume Issue Pages 515-520  
  Keywords  
  Abstract (up) The main advantage of segmentation by snakes consists in its ability to incorporate smoothness constraints on the detected shapes that can occur. Likewise, we propose to model snakes with other properties that reflect the information provided about the object of interest in a different extent. We consider different kinds of snakes, those searching for contours with a certain direction, those preserving an object’s model, those seeking for symmetry, those expanding open, etc. The availability of such a collection of snakes allows not only the more complete use of the knowledge about the segmented object, but also to solve some problems of the existing snakes. Our experiments on segmentation of facial features justify the usefulness of snakes with different properties.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CAIP  
  Notes MILAB;IAM Approved no  
  Call Number IAM @ iam @ RaM1995b Serial 1632  
Permanent link to this record
 

 
Author Jaume Garcia; David Rotger; Francesc Carreras; R.Leta; Petia Radeva edit   pdf
doi  isbn
openurl 
  Title Contrast echography segmentation and tracking by trained deformable models Type Conference Article
  Year 2003 Publication Proc. Computers in Cardiology Abbreviated Journal  
  Volume 30 Issue Pages 173-176  
  Keywords  
  Abstract (up) The objective of this work is to segment the human left ventricle myocardium (LVM) in contrast echocardiography imaging and thus track it along a cardiac cycle in order to extract quantitative data about heart function. Ultrasound images are hard to work with due to their speckle appearance. To overcome this we report the combination of active contour models (ACM) or snakes and active shape models (ASM). The ability of ACM in giving closed and smooth curves in addition to the power of the ASM in producing shapes similar to the ones learned, evoke to a robust algorithm. Meanwhile the snake is attracted towards image main features, ASM acts as a correction factor. The algorithm was tested independently on 180 frames and satisfying results were obtained: in 95% the maximum difference between automatic and experts segmentation was less than 12 pixels.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Centre de Visió per Computador – Dept. Informàtica, UAB Edifici O – Campus UAB, 08193 Bellater Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 0276-6547 ISBN 0-7803-8170-X Medium  
  Area Expedition Conference  
  Notes IAM;MILAB Approved no  
  Call Number IAM @ iam @ GRC2003 Serial 1512  
Permanent link to this record
 

 
Author David Roche; Debora Gil; Jesus Giraldo edit   pdf
url  openurl
  Title Assessing agonist efficacy in an uncertain Em world Type Conference Article
  Year 2012 Publication 40th Keystone Symposia on mollecular and celular biology Abbreviated Journal  
  Volume Issue Pages 79  
  Keywords  
  Abstract (up) The operational model of agonism has been widely used for the analysis of agonist action since its formulation in 1983. The model includes the Em parameter, which is defined as the maximum response of the system. The methods for Em estimation provide Em values not significantly higher than the maximum responses achieved by full agonists. However, it has been found that that some classes of compounds as, for instance, superagonists and positive allosteric modulators can increase the full agonist maximum response, implying upper limits for Em and thereby posing doubts on the validity of Em estimates. Because of the correlation between Em and operational efficacy, τ, wrong Em estimates will yield wrong τ estimates.
In this presentation, the operational model of agonism and various methods for the simulation of allosteric modulation will be analyzed. Alternatives for curve fitting will be presented and discussed.
 
  Address Fairmont Banff Springs, Banff, Alberta, Canada  
  Corporate Author Keystone Symposia Thesis  
  Publisher Keystone Symposia Place of Publication Editor A. Christopoulus and M. Bouvier  
  Language english Summary Language english Original Title  
  Series Editor Keystone Symposia Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference KSMCB  
  Notes IAM Approved no  
  Call Number IAM @ iam @ RGG2012 Serial 1855  
Permanent link to this record
 

 
Author Gemma Sanchez; Josep Llados; Enric Marti edit  url
openurl 
  Title Segmentation and analysis of linial texture in plans Type Conference Article
  Year 1997 Publication Intelligence Artificielle et Complexité. Abbreviated Journal  
  Volume Issue Pages  
  Keywords Structural Texture, Voronoi, Hierarchical Clustering, String Matching.  
  Abstract (up) The problem of texture segmentation and interpretation is one of the main concerns in the field of document analysis. Graphical documents often contain areas characterized by a structural texture whose recognition allows both the document understanding, and its storage in a more compact way. In this work, we focus on structural linial textures of regular repetition contained in plan documents. Starting from an atributed graph which represents the vectorized input image, we develop a method to segment textured areas and recognize their placement rules. We wish to emphasize that the searched textures do not follow a predefined pattern. Minimal closed loops of the input graph are computed, and then hierarchically clustered. In this hierarchical clustering, a distance function between two closed loops is defined in terms of their areas difference and boundary resemblance computed by a string matching procedure. Finally it is noted that, when the texture consists of isolated primitive elements, the same method can be used after computing a Voronoi Tesselation of the input graph.  
  Address Paris, France  
  Corporate Author Thesis  
  Publisher Place of Publication Paris Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference AERFAI  
  Notes DAG;IAM; Approved no  
  Call Number IAM @ iam @ SLM1997 Serial 1649  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: