Publications

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The black void behind the pupil was optically impenetrable before the invention of the ophthalmoscope by von Helmholtz over 150 years ago. Advances in retinal imaging and image processing, especially over the past decade have opened a route to another unexplored landscape, the retinal neurovascular architecture and the retinal ganglion pathways linking to the central nervous system beyond. Exploiting these research opportunities requires multidisciplinary teams to explore the interface sitting at the border between ophthalmology, neurology and computing science. It is from the detail and depth of retinal phenotyping from which novel metrics and candidate disease biomarkers are likely to emerge. Unlocking this hidden potential requires integration of structural and functional datasets, i.e. multimodal mapping and longitudinal studies spanning the natural history of the disease process. And with further advances in imaging, it is likely that this area of retinal research will remain active and clinically relevant for many years to come. It is against this backdrop that the VAMPIRE project was conceived. It is led by imaging scientists and clinicians from the Universities of Edinburgh and Dundee and features collaborative input from 10 other research centres in Italy, Singapore, Australia, Japan and the US. With funding from EPSRC, MRC, Leverhulme Trust, Optos plc and the EU, we are translating cutting-edge image processing and analysis to the clinical research environment to deliver software that users without specialist knowledge can apply easily to their images to generate valuable data that they normally would not have been able to obtain. To date, our software has been used to analyse more than 10,000 images in studies investigating retinal biomarkers for cardiovascular disease, diabetes, stroke, MS, cerebral malaria, and age-related cognitive change. VAMPIRE has been the first software tool ever to analyse retinal images from UK Biobank.
    SINAPSE Annual Scientific Meeting, Edinburgh, UK; 06/2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We aim to describe a new non-parametric methodology to support the clinician during the diagnostic process of oral videocapillaroscopy to evaluate peripheral microcirculation. Our methodology, mainly based on wavelet analysis and mathematical morphology to preprocess the images, segments them by minimizing the within-class luminosity variance of both capillaries and background. Experiments were carried out on a set of real microphotographs to validate this approach versus handmade segmentations provided by physicians. By using a leave-one-patient-out approach, we pointed out that our methodology is robust, according to precision-recall criteria (average precision and recall are equal to 0.924 and 0.923, respectively) and it acts as a physician in terms of the Jaccard index (mean and standard deviation equal to 0.858 and 0.064, respectively).
    Computer methods and programs in biomedicine 01/2014; · 1.56 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a new framework to evaluate feature descriptors on 3D datasets. The proposed method employs the approxi-mated overlap error in order to conform with the reference planar evalu-ation case of the Oxford dataset based on the overlap error. The method takes into account not only the keypoint centre but also the feature shape and it does not require complex data setups, depth maps or an accurate camera calibration. Only a ground-truth fundamental matrix should be computed, so that the dataset can be freely extended by adding further images. The proposed approach is robust to false positives occurring in the evaluation process, which do not introduce any relevant changes in the results, so that the framework can be used unsupervised. Further-more, the method has no loss in recall, which can be unsuitable for testing descriptors. The proposed evaluation compares on the SIFT and GLOH descriptors, used as references, and the recent state-of-the-art LIOP and MROGH descriptors, so that further insight on their behaviour in 3D scenes is provided as contribution too.
    17th International Conference on Image Analysis and Processing (ICIAP 2013); 09/2013
  • Carmen Alina Lupaşcu, Domenico Tegolo, Emanuele Trucco
    [Show abstract] [Hide abstract]
    ABSTRACT: We present an algorithm estimating the width of retinal vessels in fundus camera images. The algorithm uses a novel parametric surface model of the cross-sectional intensities of vessels, and ensembles of bagged decision trees to estimate the local width from the parameters of the best-fit surface. We report comparative tests with REVIEW, currently the public database of reference for retinal width estimation, containing 16 images with 193 annotated vessel segments and 5066 profile points annotated manually by three independent experts. Comparative tests are reported also with our own set of 378 vessel widths selected sparsely in 38 images from the Tayside Scotland diabetic retinopathy screening programme and annotated manually by two clinicians. We obtain considerably better accuracies compared to leading methods in REVIEW tests and in Tayside tests. An important advantage of our method is its stability (success rate, i.e., meaningful measurement returned, of 100% on all REVIEW data sets and on the Tayside data set) compared to a variety of methods from the literature. We also find that results depend crucially on testing data and conditions, and discuss criteria for selecting a training set yielding optimal accuracy.
    Medical image analysis 08/2013; 17(8):1164-1180. · 3.09 Impact Factor
  • Source
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Accurate retinal image registration is essential to track the evolution of eye-related diseases. We propose a semiautomatic method based on features relying upon retinal graphs for temporal registration of retinal images. The features represent straight lines connecting vascular landmarks on the retina vascular tree: bifurcations, branchings, crossings, end points. In the built retinal graph, one straight line between two vascular landmarks indicates that they are connected by a vascular segment in the original retinal image. The locations of the landmarks are manually extracted to avoid the information loss due to errors in a retinal vessels segmentation algorithms. A straight line model is designed to compute a similarity measure to quantify the line matching between images. From the set of matching lines, corresponding points are extracted and a global transformation is computed. The performance of the registration method is evaluated in the absence of ground truth using the cumulative inverse consistency error (CICE).
    26th IEEE International Symposium on Computer-Based Medical Systems (CBMS 2013); 06/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We aim at describing a non-parametric approach to evaluate blood cells velocity in oral capillascopic videos. The proposed methodology is based on the application of standard optical flow algorithms and it is part of a general environment to support during the diagnostic process for evaluating peripheral microcirculation in real time. We validated our approach versus handmade measurements provided by physicians. Results on real data pointed out that our system returns an output coherent to these latter observations.
    26th IEEE International Symposium on Computer-Based Medical Systems (CBMS 2013); 06/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    IEEE Biosignals and Biorobotics Conference; 02/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Objective: The purpose of this paper is to determine a global assessment of the human retinal vascular network for patients with amblyopia. Fractal geometry and lacunarity parameters are used in this study. Materials and methods: A set of 12 segmented and skeletonized human retinal images, corresponding to both normal (6 images) and amblyopia states of the retina (6 images), was analyzed using the Image J software with box-counting method. Statistical analyses were performed for these groups using Microsoft Office Excel 2003 and GraphPad InStat software. Results: The human retinal vascular network architecture can be estimated using the fractal geometry. The average of fractal dimensions D for the amblyopia images (segmented and skeletonized versions) is slightly higher than the corresponding values for normal im - ages (segmented and skeletonized versions). However, the average of lacunarity parameter Λ for the amblyopia images (segmented and skel - etonized versions) is slightly lower than the corresponding values for normal images (segmented and skeletonized versions). Conclusions: The fractal and lacunarity analysis may be used for an early diagnosis of patients with amblyopia.
    Human & Veterinary Medicine International Journal of the Bioflux Society. 01/2013; 5(2):45-51.
  • Source
    C.A. Lupaşcu, D. Tegolo
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a semi-automatic framework for minimal path tracking in the skeleton of the retinal vascular network. The method is based on the graph structure of the vessel network. The vascular network is represented based on the skeleton of the available segmented vessels and using an undirected graph. Significant points on the skeleton are considered nodes of the graph, while the edge of the graph is represented by the vessel segment linking two neighbor- ing nodes. The graph is represented then in the form of a connectivity matrix, using a novel method for defining ver- tex connectivity. Dijkstra and Floyd-Warshall algorithms are applied for detection of minimal paths within the graph. The major contribution of this work is the accurate detec- tion of significant points and the novel definition of vertex connectivity based on a new neighborhood system adopted. The qualitative performance of our method evaluated on the publicly available DRIVE database shows useful results for further purposes.
    IEEE International Symposium on Computer-Based Medical System; 06/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: The objective of this study is to perform an evaluation of representative size and shape parameters that characterise the human red blood cells either exposed to cisplatin or exposed to control solutions containing no cisplatin. A set of fourteen digital images corresponding for the human red blood cells were evaluated. Image processing and analysis of digital images were performed with ImageJ and MRI Cell Image Analyzer (MRI-CIA) softwares. We found for the human red blood cells either exposed to cisplatin or exposed to control solutions containing no cisplatin, a set of representative size and shape parameters for quantification. The central tendency and dispersion measure of the parameters were expressed by the mean value and standard deviation. The computerized geometric morphometric analysis of the human red blood cells is an efficient noninvasive prediction tool that provides important insights into cell states.
    Annals of the Romanian Society for Cell Biology 01/2012; 17(2):105-110.
  • Carmen Alina Lupaşcu, Domenico Tegolo
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper an automatic unsupervised method for the segmentation of retinal vessels is proposed. Three features are extracted from the tested image. The features are scaled down by a factor of 2 and mapped into a Self-Organizing Map. A modified Fuzzy C-Means clustering algorithm is used to divide the neuron units of the map in 2 classes. The entire image is again input for the Self-Organizing Map and the class of each pixel will be the class of its best matching unit in the Self-Organizing Map. Finally, the vessel network is post-processed using a hill climbing strategy on the connected components of the segmented image. The experimental evaluation on the DRIVE database shows accurate extraction of vessels network and a good agreement between our segmentation and the ground truth. The mean accuracy, 0.9482 with a standard deviation of 0.0075, is outperforming the manual segmentation rates obtained by other widely used unsupervised methods. A good kappa value of 0.6565 is comparable with state-of-the-art supervised or unsupervised approaches. KeywordsRetinal Vessels–Self-Organizing Map–Fuzzy C-Means
    08/2011: pages 244-252;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present VAMPIRE, a software application for efficient, semi-automatic quantification of retinal vessel properties with large collections of fundus camera images. VAMPIRE is also an international collaborative project of four image processing groups and five clinical centres. The system provides automatic detection of retinal landmarks (optic disc, vasculature), and quantifies key parameters used frequently in investigative studies: vessel width, vessel branching coefficients, and tortuosity. The ultimate vision is to make VAMPIRE available as a public tool, to support quantification and analysis of large collections of fundus camera images.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2011; 2011:3391-4.
  • Carmen Alina Lupascu, Domenico Tegolo
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper an automatic unsupervised method for the segmentation of retinal vessels is proposed. Three features are extracted from the tested image. The features are scaled down by a factor of 2 and mapped into a Self-Organizing Map. A modified Fuzzy C-Means clustering algorithm is used to divide the neuron units of the map in 2 classes. The entire image is again input for the Self- Organizing Map and the class of each pixel will be the class of its best matching unit in the Self-Organizing Map. Finally, the vessel network is post-processed using a hill climbing strategy on the connected components of the segmented image. The experimental evaluation on the DRIVE database shows accurate extraction of vessels network and a good agreement between our segmentation and the ground truth. The mean accuracy, 0.9482 with a standard deviation of 0.0075, is outperforming the manual segmentation rates obtained by other widely used unsupervised methods. A good kappa value of 0.6565 is comparable with stateof- the-art supervised or unsupervised approaches.
    Fuzzy Logic and Applications - 9th International Workshop, WILF 2011, Trani, Italy, August 29-31,2011. Proceedings; 01/2011
  • Carmen Alina Lupascu, Domenico Tegolo, Emanuele Trucco
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a method for automated vessel segmentation in retinal images. For each pixel in the field of view of the image, a 41-D feature vector is constructed, encoding information on the local intensity structure, spatial properties, and geometry at multiple scales. An AdaBoost classifier is trained on 789 914 gold standard examples of vessel and nonvessel pixels, then used for classifying previously unseen images. The algorithm was tested on the public digital retinal images for vessel extraction (DRIVE) set, frequently used in the literature and consisting of 40 manually labeled images with gold standard. Results were compared experimentally with those of eight algorithms as well as the additional manual segmentation provided by DRIVE.Training was conducted confined to the dedicated training set from the DRIVE database, and feature-basedAdaBoost classifier (FABC)was tested on the 20 images from the test set. FABC achieved an area under the receiver operating characteristic (ROC) curve of 0.9561, in line with state-of-the-art approaches, but outperforming their accuracy (0.9597 versus 0.9473 for the nearest performer).
    IEEE Transactions on Information Technology in Biomedicine 01/2010; 14:1267-1274. · 1.98 Impact Factor
  • Source
    Carmen Alina Lupascu, Domenico Tegolo
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper an automatic unsupervised method for the segmentation of retinal vessels is proposed. A Self-Organizing Map is trained on a portion of the same image that is tested and K-means clustering algorithm is used to divide the map units in 2 classes. The entire image is again input for the Self-Organizing Map, and the class of each pixel will be the class of the best matching unit on the Self-Organizing Map. Finally, the vessel network is post-processed using a hill climbing strategy on the connected components of the segmented image. The experimental evaluation on the publicly available DRIVE database shows accurate extraction of vessels network and a good agreement between our segmentation and the ground truth. The mean accuracy, 0.9459 with a standard deviation of 0.0094, is outperforming the manual segmentation rates obtained by other widely used unsupervised methods. A good kappa value of 0.6562 is inline with state-of-the-art supervised and unsupervised approaches.
    Computational Intelligence Methods for Bioinformatics and Biostatistics - 7th International Meeting, CIBB 2010, Palermo, Italy, September 16-18, 2010, Revised Selected Papers; 01/2010
  • Carmen Alina Lupascu, Domenico Tegolo, Emanuele Trucco
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a comparative study on five feature selection heuristics applied to a retinal image database called DRIVE. Features are chosen from a feature vector (encoding local information, but as well information from structures and shapes available in the image) constructed for each pixel in the field of view (FOV) of the image. After selecting the most discriminatory features, an AdaBoost classifier is applied for training. The results of classifications are used to compare the effectiveness of the five feature selection methods.
    Computer Analysis of Images and Patterns, 13th International Conference, CAIP 2009, Münster, Germany, September 2-4, 2009. Proceedings; 01/2009
  • Source
    Carmen Alina Lupascu, Domenico Tegolo, Luigi Di Rosa
    [Show abstract] [Hide abstract]
    ABSTRACT: This contribution presents an automated method to locate the optic disc in color fundus images. The method uses texture descriptors and a regression based method in order to determine the best circle that fits the optic disc. The best circle is chosen from a set of circles determined with an innovative method, not using the Hough transform as past approaches. An evaluation of the proposed method has been done using a database of 40 images. On this data set, our method achieved 95% success rate for the localization of the optic disc and 70% success rate for the identification of the optic disc contour (as a circle).
    Proceedings of the Twenty-First IEEE International Symposium on Computer-Based Medical Systems, June 17-19, 2008, Jyväskylä, Finland; 01/2008
  • Carmen Alina Lupaşcu, Domenico Tegolo
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper an automatic unsupervised method for the segmentation of retinal vessels is proposed. A Self-Organizing Map is trained on a portion of the same image that is tested and K-means clustering algorithm is used to divide the map units in 2 classes. The entire image is again input for the Self-Organizing Map, and the class of each pixel will be the class of the best matching unit on the Self-Organizing Map. Finally, the vessel network is post-processed using a hill climbing strategy on the connected components of the segmented image. The experimental evaluation on the publicly available DRIVE database shows accurate extraction of vessels network and a good agreement between our segmentation and the ground truth. The mean accuracy, 0.9459 with a standard deviation of 0.0094, is outperforming the manual segmentation rates obtained by other widely used unsupervised methods. A good kappa value of 0.6562 is inline with state-of-the-art supervised and unsupervised approaches. KeywordsRetinal Vessels–Self-Organizing Map–K-means
    01/1970: pages 263-274;

44 Following View all

37 Followers View all