Jorge Novo

Sirius: A web-based system for retinal image analysis

PURPOSE Retinal image analysis can lead to early detection of several pathologies such as hypertension or diabetes. Screening processes require the evaluation of a high amount of visual data and, usually, the collaboration between different experts and different health care centers. These usual routines demand new fast and automatic solutions to deal with these situations. This work introduces Sirius (System for the Integration of Retinal Images Understanding Services), a web-based system for image analysis in the retinal imaging field. METHODS Sirius provides a framework for ophthalmologists or other experts in the field to collaboratively work using retinal image-based applications in a distributed, fast and reliable environment. Sirius consists of three main components: the web client that users interact with, the web application server that processes all client requests and the service module that performs the image processing tasks. In this work, we present a service for the analysis of retinal microcirculation using a semi-automatic methodology for the computation of the arteriolar-to-venular ratio (AVR). RESULTS Sirius has been evaluated in different real environments, involving health care systems, to test its performance. First, the AVR service was validated in terms of precision and efficiency and then, the framework was evaluated in different real scenarios of medical centers. CONCLUSIONS Sirius is a web-based application providing a fast and reliable work environment for retinal experts. The system allows the sharing of images and processed results between remote computers and provides automated methods to diminish inter-expert variability in the analysis of the images.

Localisation of the optic disc by means of GA-optimised Topological Active Nets

In this paper we propose a new approach to the optic disc localisation process in digital retinal images by means of Topological Active Nets (TAN). This is a deformable model used for image segmentation that integrates features of region-based and edge-based segmentation techniques, being able to fit the edges of the objects and model their inner topology. In this paper the active nets incorporate new energy terms for the optic disc localisation and their optimisation is performed with a genetic algorithm, with adapted or new ad hoc genetic operators. There is no need of any pre-processing of the images, which allows a quasi automatic localisation of the optic disc. This process also provides a simultaneous segmentation of the disc. We present representative results of optic disc localisations showing the advantages of the approach, with images focusing on the optic disc or on the macula, and with images with different levels of noise and lesion areas.

Topological Active Models optimization with Differential Evolution

The Topological Active Model is an active model focused on segmentation tasks. It provides information about the surfaces and the inside of the detected objects in the scene. The segmentation process turns into a minimization task of the energy functions which control the model deformation. In this work we propose a new optimization method of the segmentation model that uses Differential Evolution as an alternative evolutionary method that minimizes the decisions of the designer with respect to others such as genetic algorithms. Moreover, we hybridized Differential Evolution with a greedy search to integrate the advantages of global and local searches at the same time that the segmentation speed is improved. We also included in the local search the possibility of topological changes to perform a better adjustment in complex surfaces, topological changes that introduce the necessary mechanism to divide the mesh in the case of the presence of several objects in the scene.

Optic Disc Segmentation by Means of GA-Optimized Topological Active Nets

In this paper we propose a new approach to the optic disc segmentation process in digital retinal images by means of Topological Active Nets (TAN). This is a deformable model used for image segmentation that integrates features of region-based and edge-based segmentation techniques, being able to fit the edges of the objects and model their inner topology. The optimization of the Active Nets is performed by a genetic algorithm, with adapted or new ad hoc genetic operators to the problem. The active nets incorporate new energy terms for the optic disc segmentations, without the need of any pre-processing of the images. We present results of optic disc segmentations showing the advantages of the approach.

Hessian based approaches for 3D lung nodule segmentation

Abstract In the design of computer-aided diagnosis systems for lung cancer diagnosis, an appropriate and accurate segmentation of the pulmonary nodules in computerized tomography (CT) is one of the most relevant and difficult tasks. An accurate segmentation is crucial for the posterior measurement of nodule characteristics and for lung cancer diagnosis. This paper proposes different approaches that use Hessian-based strategies for lung nodule segmentation in chest CT scans. We propose a multiscale segmentation process that uses the central medialness adaptive principle, a Hessian-based strategy that was originally formulated for tubular extraction but it also provides good segmentation results in blob-like structures as is the case of lung nodules. We compared this proposal with a well established Hessian-based strategy that calculates the Shape Index (SI) and Curvedness (CV). We adapted the SI and CV approach for multiscale nodule segmentation. Moreover, we propose the combination of both strategies by combining the results, in order to take benefit of the advantages of both strategies. Different cases with pulmonary nodules from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) database were taken and used to analyze and validate the approaches. The chest CT images present a large variability in nodule characteristics and image conditions. Our proposals provide an accurate lung nodule segmentation, similar to radiologists performance. Our Hessian-based approaches were validated with 569 solid and mostly solid nodules demonstrating that these novel strategies have good results when compared with the radiologists segmentations, providing accurate pulmonary nodule volumes for posterior characterization and appropriate diagnosis.

Evolutionary multiobjective optimization of Topological Active Nets

In this work we used the evolutionary multiobjective optimization methodology for the optimization of Topological Active Nets. This is a deformable model that integrates features of region-based and boundary-based segmentation techniques. The model deformation is controlled by energy functions that must be minimized. When the minimization task is performed by means of a greedy local search or a global search method, an experimental tuning of the energy parameters is needed to obtain a correct segmentation. This tuning must be done for each kind of image. Evolutionary multiobjective optimization gives a solution to this problem by considering the optimization of several objectives in parallel. We used the SPEA2 algorithm, adapted to our application, to the search of the Pareto optimal individuals. We tested the improvements and problems between the uses of the multiobjective optimization technique versus the use of a genetic algorithm and a greedy local search in our application of the optimization of the Topological Active Nets deformable model. We used several representative examples with images from different medical domains.

3D Retinal Vessel Tree Segmentation and Reconstruction with OCT Images

Detection and analysis of the arterio-venular tree of the retina is a relevant issue, providing useful information in procedures such as the diagnosis of different pathologies. Classical approaches for vessel extraction make use of 2D acquisition paradigms and, therefore, obtain a limited representation of the vascular structure. This paper proposes a new methodology for the automatic 3D segmentation and reconstruction of the retinal arterio-venular tree in Optical Coherence Tomography (OCT) images. The methodology takes advantage of different image analysis techniques to initially segment the vessel tree and estimate its calibers along it. Then, the corresponding depth for the entire vessel tree is obtained. Finally, with all this information, the method performs the 3D reconstruction of the entire vessel tree.

3D lung nodule candidate detection in multiple scales

Lung cancer is mainly diagnosed by the identification of malignant nodules in the lung parenchyma. For that purpose, the identification of all the possible structures that could be suspicious of lung nodules became a crucial task in any lung cancer computer aided diagnosis (CAD) system. In this paper, a new approach for lung nodule candidate identification is proposed. This method uses a 3D medialness Hessian-based filtering to identify round shape structures that could be identified as nodules. This technique, that demonstrated its accuracy in lung vesselness extraction, provides clearer candidates than other approaches, providing less response in the presence of noise artifacts and returns a better continuity in vessels, mostly responsible for false positives. That way, they will be better distinguishable from the nodules in posterior analysis. This approach was validated in 120 scans from the LIDC/IDRI image database. They include 212 nodules with diameters in the range 3 mm to 30 mm. The results demonstrate that our approach is capable of identifying most of the nodules and include less false positives than other approaches, facilitating a posterior task for false positive removal.

Optimization of topological active nets with differential evolution

The Topological ActiveNetmodel for image segmentation is a deformable model that integrates features of region-based and boundary-based segmentation techniques. The segmentation process turns into a minimization task of the energy functions which control the model deformation. We used Differential Evolution as an alternative evolutionary method that minimizes the decisions of the designer with respect to other evolutionary methods such as genetic algorithms.Moreover, we hybridized Differential Evolution with a greedy search to integrate the advantages of global and local searches at the same time that the segmentation speed is improved.

Cost Function Selection for a Graph-Based Segmentation in OCT Retinal Images

This paper is based on a methodology for segmentation of the main retinal layers in Optical Coherence Tomography (OCT) images. The input image is transformed into a geometric graph and the layers to be detected will be given by its minimum-cost closed set. The main problem in this method is the selection of the appropriate cost functions associated to the graph, because of the variety of anomalies that images from patients might have.