Filters








30 Hits in 1.3 sec

Tubular Anisotropy Segmentation [chapter]

Fethallah Benmansour, Laurent D. Cohen
2009 Lecture Notes in Computer Science  
Dans cet article, nous considérons le problème de la calibration géométrique dt'un projecteur vidéo à l'aide dt'un plan (mur) non marqué et dt'une caméra partiellement calibrés. Au lieu dt'utiliser des points de contrôle pour estimer lt'orientation mur-caméra, nous retrouvons cette relation en échantillonnant lt'hémisphère des orientations possibles. Ce processus est tellement rapide qut'il est même possible dt'intégrer lt'estimation de la focale de la caméra dans le processus
more » ... . Notre méthode est simple et donne de bons résultats tel que démontré par nos expérimentations. Mots Clef Calibration de projecteurs, calibration par plans, estimation de focal, vision active. Abstract In this paper we address the problem of geometric video projector calibration using a markerless planar surface (wall) and a partially calibrated camera. Instead of using control points to infer the camera-wall orientation, we find such relation by efficiently sampling the hemisphere of possible orientations. This process is so fast that even the focal of the camera can be estimated during the sampling process. Hence, physical grids and full knowledge of camera parameters are no longer necessary to calibrate a video projector.
doi:10.1007/978-3-642-02256-2_2 fatcat:lnea2o537vfmdojpkh6gp4mhhq

Numerical approximation of continuous traffic congestion equilibria

Fethallah Benmansour, Guillaume Carlier, Gabriel Peyré, Filippo Santambrogio
2009 Networks and Heterogeneous Media  
Starting from a continuous congested traffic framework recently introduced in [8], we present a consistent numerical scheme to compute equilibrium metrics. We show that equilibrium metric is the solution of a variational problem involving geodesic distances. Our discretization scheme is based on the Fast Marching Method. Convergence is proved via a Γ-convergence result and numerical results are given. 2000 Mathematics Subject Classification. Primary: 49M25, 65K10, 90C25.
doi:10.3934/nhm.2009.4.605 fatcat:6m2y3vyqajdgln7xbtq4jjpfju

From a Single Point to a Surface Patch by Growing Minimal Paths [chapter]

Fethallah Benmansour, Laurent D. Cohen
2009 Lecture Notes in Computer Science  
We introduce a novel implicit approach for surface patch segmentation in 3D images starting from a single point. Since the boundary surface of an object is locally homeomorphic to a disc, we know that the boundary of a small neighboring domain intersects the surface of interest on a single closed curve. Similarly to active surfaces, we use a cost potential which penalizes image regions of low interest. First, Using a front propagation approach from the source point chosen by the user, one can
more » ... e that the closed curve corresponds to valley line of the arrival time from the source point. Next, we use an implicit 3D segmentation method. It assumes that the object boundary contains two known constraining curves. In our case, the first curve is reduced to a point and the other one is automatically detected by our approach. A partial differential equation is introduced and its solution is used for segmentation. The zero level set of this solution contains valley line and the source point as well as the set of minimal paths joining them. We present a fast implementation which has been successfully applied to 3D biomedical and synthetic images.
doi:10.1007/978-3-642-02256-2_54 fatcat:mptlz6a7pbcz7ooppo4m6ek7be

Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation [article]

Alvaro Gomariz, Huanxiang Lu, Yun Yvonna Li, Thomas Albrecht, Andreas Maunz, Fethallah Benmansour, Alessandra M.Valcarcel, Jennifer Luu, Daniela Ferrara, Orcun Goksel
2022 arXiv   pre-print
Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail for images that do not resemble labeled examples, e.g. for images acquired using different devices. We hereby propose a novel semi-supervised learning framework for segmentation of volumetric images from new unlabeled domains. We jointly use supervised and
more » ... astive learning, also introducing a contrastive pairing scheme that leverages similarity between nearby slices in 3D. In addition, we propose channel-wise aggregation as an alternative to conventional spatial-pooling aggregation for contrastive feature map projection. We evaluate our methods for domain adaptation from a (labeled) source domain to an (unlabeled) target domain, each containing images acquired with different acquisition devices. In the target domain, our method achieves a Dice coefficient 13.8% higher than SimCLR (a state-of-the-art contrastive framework), and leads to results comparable to an upper bound with supervised training in that domain. In the source domain, our model also improves the results by 5.4% Dice, by successfully leveraging information from many unlabeled images.
arXiv:2203.03664v1 fatcat:uyqhp4fn4zak5punawhshp2a7e

Tubular Structure Segmentation Based on Minimal Path Method and Anisotropic Enhancement

Fethallah Benmansour, Laurent D. Cohen
2010 International Journal of Computer Vision  
We present a new interactive method for tubular structure extraction. The main application and motivation for this work is vessel tracking in 2D and 3D images. The basic tools are minimal paths solved using the fast marching algorithm. This allows interactive tools for the physician by clicking on a small number of points in order to obtain a minimal path between two points or a set of paths in the case of a tree structure. Our method is based on a variant of the minimal path method that models
more » ... the vessel as a centerline and surface. This is done by adding one dimension for the local radius around the centerline. The crucial step of our method is the definition of the local metrics to minimize. We have chosen to exploit the tubular structure of the vessels one wants to extract to built an anisotropic metric. The designed metric is well oriented along the direction of the vessel, admits higher velocity on the centerline, and provides a good estimate of the vessel radius. Based on the optimally oriented flux this measure is required to be robust against the disturbance introduced by noise or adjacent structures with intensity similar to the target vessel. We obtain promising results on noisy synthetic and real 2D and 3D images and we present a clinical validation.
doi:10.1007/s11263-010-0331-0 fatcat:p3rbxglsvjhapai36ckfm2adnm

Tubular anisotropy for 2D vessel segmentation

Fethallah Benmansour, Laurent D. Cohen, Max W. K. Law, Albert C. S. Chung
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we present a new approach for segmentation of tubular structures in 2D images providing minimal interaction. The main objective is to extract centerlines and boundaries of the vessels at the same time. The first step is to represent the trajectory of the vessel not as a 2D curve but to go up a dimension and represent the entire vessel as a 3D curve, where each point represents a 2D disc (two coordinates for the center point and one for the radius). The 2D vessel structure is then
more » ... obtained as the envelope of the family of discs traversed along this 3D curve. Since this 2D shape is defined simply from a 3D curve, we are able to fully exploit minimal path techniques to obtain globally minimizing trajectories between two or more user supplied points using front propagation. The main contribution of our approach consists on building a multi-resolution metric that guides the propagation in this 3D space. We have chosen to exploit the tubular structure of the vessels one wants to extract to built an anisotropic metric giving higher speed on the center of the vessels and also when the minimal path tangent is coherent with the vessel's direction. This measure is required to be robust against the disturbance introduced by noise or adjacent structures with intensity similar to the target vessel. Indeed, if we examine the flux of the projected image gradient along a given direction on a circle of a given radius (or scale), one can prove that this flux is maximal at the center of the vessel, in its direction and with its exact radius. This approach is called optimally oriented flux. Combining anisotropic minimal paths techniques and optimally oriented flux we obtain promising results on noisy synthetic and real data.
doi:10.1109/cvpr.2009.5206703 dblp:conf/cvpr/BenmansourCLC09 fatcat:4e5odurpfbfq7htqfbq2bbe4fm

Reconstructing Loopy Curvilinear Structures Using Integer Programming

Engin Turetken, Fethallah Benmansour, Bjoern Andres, Hanspeter Pfister, Pascal Fua
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We propose a novel approach to automated delineation of linear structures that form complex and potentially loopy networks. This is in contrast to earlier approaches that usually assume a tree topology for the networks. At the heart of our method is an Integer Programming formulation that allows us to find the global optimum of an objective function designed to allow cycles but penalize spurious junctions and early terminations. We demonstrate that it outperforms state-of-the-art techniques on a wide range of datasets.
doi:10.1109/cvpr.2013.238 dblp:conf/cvpr/TuretkenBAPF13 fatcat:p465dceyqbeyxelqduedj7tfry

Deep learning algorithm predicts diabetic retinopathy progression in individual patients

Filippo Arcadu, Fethallah Benmansour, Andreas Maunz, Jeff Willis, Zdenka Haskova, Marco Prunotto
2019 npj Digital Medicine  
The global burden of diabetic retinopathy (DR) continues to worsen and DR remains a leading cause of vision loss worldwide. Here, we describe an algorithm to predict DR progression by means of deep learning (DL), using as input color fundus photographs (CFPs) acquired at a single visit from a patient with DR. The proposed DL models were designed to predict future DR progression, defined as 2-step worsening on the Early Treatment Diabetic Retinopathy Diabetic Retinopathy Severity Scale, and were
more » ... trained against DR severity scores assessed after 6, 12, and 24 months from the baseline visit by masked, well-trained, human reading center graders. The performance of one of these models (prediction at month 12) resulted in an area under the curve equal to 0.79. Interestingly, our results highlight the importance of the predictive signal located in the peripheral retinal fields, not routinely collected for DR assessments, and the importance of microvascular abnormalities. Our findings show the feasibility of predicting future DR progression by leveraging CFPs of a patient acquired at a single visit. Upon further development on larger and more diverse datasets, such an algorithm could enable early diagnosis and referral to a retina specialist for more frequent monitoring and even consideration of early intervention. Moreover, it could also improve patient recruitment for clinical trials targeting DR.
doi:10.1038/s41746-019-0172-3 pmid:31552296 pmcid:PMC6754451 fatcat:ptaki76lufcsdjnlfwqtwkde5a

Author Correction: Deep learning algorithm predicts diabetic retinopathy progression in individual patients

Filippo Arcadu, Fethallah Benmansour, Andreas Maunz, Jeff Willis, Zdenka Haskova, Marco Prunotto
2020 npj Digital Medicine  
A Correction to this paper has been published: https://doi.org/10.1038/s41746-020-00365-5.
doi:10.1038/s41746-020-00365-5 pmid:33293570 fatcat:y4kpqlpeyzdbnbqdhv263mnysm

On the relevance of sparsity for image classification

Roberto Rigamonti, Vincent Lepetit, Germán González, Engin Türetken, Fethallah Benmansour, Matthew Brown, Pascal Fua
2014 Computer Vision and Image Understanding  
In this paper we analyze empirically the importance of sparsifying representations for classification purposes. We focus on those obtained by convolving images with linear filters, which can be either hand designed or learned, and perform extensive experiments on two important Computer Vision problems, image categorization and pixel classification. To this end, we adopt a simple modular architecture that encompasses many recently proposed models. The key outcome of our investigations is that
more » ... orcing sparsity constraints on features extracted in a convolutional architecture does not improve classification performance, whereas it does so when redundancy is artificially introduced. This is very relevant for practical purposes, since it implies that the expensive run-time optimization required to sparsify the representation is not always justified, and therefore that computational costs can be drastically reduced.
doi:10.1016/j.cviu.2014.03.009 fatcat:oiyrvclhtfbm3og5nkpv4n6gte

A new interactive method for coronary arteries segmentation based on tubular anisotropy

Fethallah Benmansour, Laurent D. Cohen
2009 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
In this paper we present a new interactive method for tubular structure extraction. The main application and motivation for this work is vessel tracking in 3D medical images. The basic tools are minimal paths solved using the fast marching algorithm. This leads to interactive tools for the physician by clicking on a small number of points in order to obtain a minimal path between two points or a set of paths in the case of a tree structure. Our method is based on a variant of the minimal path
more » ... thod that models the vessel as a centerline and surface by adding one dimension for the local radius around the centerline. The crucial step of our method is the definition of the local metrics to minimize (based on the local orientation using a Riemannian Metric). This approach is made available for the physician using an Object Oriented Language (OOL) interface. We show results on two CT cardiac images for coronary arteries segmentation.
doi:10.1109/isbi.2009.5192978 dblp:conf/isbi/BenmansourC09 fatcat:b5rx4jmelnfvtfxmr3b4swqfsy

Automated quantification of morphodynamics for high-throughput live cell time-lapse datasets

German Gonzalez, Ludovico Fusco, Fethallah Benmansour, Pascal Fua, Olivier Pertz, Kevin Smith
2013 2013 IEEE 10th International Symposium on Biomedical Imaging  
We present a fully automatic method to track and quantify the morphodynamics of differentiating neurons in fluorescence time-lapse datasets. Previous high-throughput studies have been limited to static analysis or simple behavior. Our approach opens the door to rich dynamic analysis of complex cellular behavior in high-throughput time-lapse data. It is capable of robustly detecting, tracking, and segmenting all the components of the neuron including the nucleus, soma, neurites, and filopodia.
more » ... was designed to be efficient enough to handle the massive amount of data from a high-throughput screen. Each image is processed in approximately two seconds on a notebook computer. To validate the approach, we applied our method to over 500 neuronal differentiation videos from a small-scale RNAi screen. Our fully automated analysis of over 7,000 neurons quantifies and confirms with strong statistical significance static and dynamic behaviors that had been previously observed by biologists, but never measured.
doi:10.1109/isbi.2013.6556562 dblp:conf/isbi/GonzalezFBFPS13 fatcat:cz73dusmznhnhnnuties2nncwi

Reconstructing Curvilinear Networks Using Path Classifiers and Integer Programming

Engin Turetken, Fethallah Benmansour, Bjoern Andres, Przemyslaw Glowacki, Hanspeter Pfister, Pascal Fua
2016 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We propose a novel approach to automated delineation of curvilinear structures that form complex and potentially loopy networks. By representing the image data as a graph of potential paths, we first show how to weight these paths using discriminatively-trained classifiers that are both robust and generic enough to be applied to very different imaging modalities. We then present an Integer Programming approach to finding the optimal subset of paths, subject to structural and topological
more » ... nts that eliminate implausible solutions. Unlike earlier approaches that assume a tree topology for the networks, ours explicitly models the fact that the networks may contain loops, and can reconstruct both cyclic and acyclic ones. We demonstrate the effectiveness of our approach on a variety of challenging datasets including aerial images of road networks and micrographs of neural arbors, and show that it outperforms state-of-the-art techniques.
doi:10.1109/tpami.2016.2519025 pmid:26891482 fatcat:ss7fc7jpizasrcnr3f5epcg3iq

Fast Object Segmentation by Growing Minimal Paths from a Single Point on 2D or 3D Images

Fethallah Benmansour, Laurent D. Cohen
2008 Journal of Mathematical Imaging and Vision  
In this paper, we present a new method for segmenting closed contours and surfaces. Our work builds on a variant of the minimal path approach. First, an initial point on the desired contour is chosen by the user. Next, new keypoints are detected automatically using a front propagation approach. We assume that the desired object has a closed boundary. This a-priori knowledge on the topology is used to devise a relevant criterion for stopping the keypoint detection and front propagation. The
more » ... domain visited by the front will yield a band surrounding the object of interest. Linking pairs of neighboring keypoints with minimal paths allows us to extract a closed contour from a 2D image. This approach can also be used for finding an open curve giving extra information as stopping criteria. Detection of a variety of objects on real images is demonstrated. Using a similar idea, we can extract networks of minimal paths from a 3D image called Geodesic Meshing. The proposed method is applied to 3D data with promising results.
doi:10.1007/s10851-008-0131-0 fatcat:v6dscwu47far3htfafvgbtz56y

Finding a Closed Boundary by Growing Minimal Paths from a Single Point on 2D or 3D Images

Fethallah Benmansour, Stephane Bonneau, Laurent D. Cohen
2007 2007 IEEE 11th International Conference on Computer Vision  
In this paper, we present a new method for segmenting closed contours and surfaces. Our work builds on a variant of the Fast Marching algorithm. First, an initial point on the desired contour is chosen by the user. Next, new keypoints are detected automatically using a front propagation approach. We assume that the desired object has a closed boundary. This a-priori knowledge on the topology is used to devise a relevant criterion for stopping the keypoint detection and front propagation. The
more » ... al domain visited by the front will yield a band surrounding the object of interest. Linking pairs of neighboring keypoints with minimal paths allows us to extract a closed contour from a 2D image. Detection of a variety of objects on real images is demonstrated. Using a similar same idea, we can extract networks of minimal paths from a 3D image called Geodesic Meshing. The proposed method is applied to 3D data with promising results. 978-1-4244-1631-8/07/$25.00 ©2007 IEEE Authorized licensed use limited to: IEEE Xplore. Downloaded on December 4, 2008 at 05:24 from IEEE Xplore. Restrictions apply. Authorized licensed use limited to: IEEE Xplore. Downloaded on December 4, 2008 at 05:24 from IEEE Xplore. Restrictions apply.
doi:10.1109/iccv.2007.4409156 dblp:conf/iccv/BenmansourBC07 fatcat:llanudz4lfgstbjgslxhsbpdlu
« Previous Showing results 1 — 15 out of 30 results