Diego Fiorin

Automatic vessel segmentation in wide-field retina images of infants with Retinopathy of Prematurity

The earliest signs of Retinopathy of Prematurity (ROP) are tortuosity and dilation of retinal vessels. Such vascular changes are considered of primary importance for the diagnosis and the follow-up of the disease. However, a widely accepted computerized system for their quantitative measurement is still missing. Images taken from a preterm babys eye are often low-contrast, noisy, and blurred. Algorithms that have been successfully applied to analyze adult retinal images do not work well in ROP images. We propose here a novel method for the automatic extraction of vessel centerline in wide-field ROP retinal images, based on a sparse tracking scheme. After a set of seed points is identified all over the image, vessels are traced by connecting those seeds by means of minimum cost paths, whose weights depend on similarity features and alignment evaluated by a custom line operator. The performance of the method was assessed on a dataset of 20 images acquired with the RetCam fundus camera. A sensitivity of 0.78 and a false detection rate of 0.15 were obtained with respect to manual ground truth reference.

A Web-Based System for the Quantitative and Reproducible Assessment of Clinical Indexes From the Retinal Vasculature

A novel system for the vascular tree identification and the quantitative estimation of arteriolar venular ratio clinical index in retinal fundus images is presented. The system is composed of a module for automatic vascular tracking, an interactive editing interface to correct errors and set the required parameters of analysis, and a module for the computation of clinical indexes. The system was organized as a client-server structure to allow clinicians and researchers from all over the world to work remotely. The system was evaluated by three graders analyzing 30 fundus images. The evaluation of the Pearsons correlation coefficient and -value of a paired -test for each pair of graders demonstrates the high reproducibility of the measures provided by the system.

In Vivo Three-Dimensional Reconstruction of the Cornea from Confocal Microscopy Images

Confocal microscopy can provide sequences of Images from all cornea layers in a rapid, in vivo and non invasive way. These images are useful to extract important clinical information on cornea state of health. We address the problem of obtaining a 3-dimensional (3D) reconstruction of the cornea starting from a confocal microscope sequence, from endothelium to epithelium. A registration procedure, based on normalized correlation, is applied to each image, because eye movements normally occur during acquisition of the sequence and shifts in x-y plane take place in the sequence of images. Information on shifts along x and y directions comes from registration process, shift along z direction comes from the instrument itself. A 2D image stack is reconstructed by taking into account shifts along x, y, and z directions. If data are missing, we reconstruct them by taking lines from adjacent images and interpolating them. After reconstruction, it is possible to display and analyze corneal structures in the 3D volume and obtain slices in the x, y, or z direction.

Computerized analysis of narrow-field ROP images for the assessment of vessel caliber and tortuosity

Retinopathy of prematurity (ROP) is a disease involving abnormal development of retinal vasculature in premature infants, which might eventually lead to retinal detachment and visual loss. The quantitative assessment of vessel morphological features, such as width and tortuosity, can improve the clinical diagnosis and evaluation of ROP. We propose here a computerized system for the vascular analysis of narrow-field premature infant images. It is based on the manual drafting of the vessel axis, followed by automatic Canny filter edge extraction and automatic caliber and tortuosity estimation. We implemented this method as a web-based tool, ROPnet, which allows the quantitative assessment of vessel width and tortuosity simply using a web browser. To test the accuracy of the estimated parameters, fifteen narrow-field (30°) retinal images were acquired in infants with a non-contact fundus camera and analyzed with ROPnet. We compared the results with the corresponding ground-truth values derived from manual analysis. Average widths and tortuosities estimated with ROPnet vs. manual ones showed a correlation coefficient of 0.96 and 0.90, respectively.

Retinal Vessel Axis Estimation through a Multi-Directional Graph Search Approach

The analysis of blood vessels in images of retinal fundus is an important non-invasive procedure that allows early diagnosis and the effective monitoring of therapies in retinopathy. In order to derive a quantitative evaluation of the clinical features, such as vessel diameter and tortuosity, an accurate segmentation of the vessel network has to be performed. A new system for the automatic extraction of the vascular structure in retinal images is proposed. It is based on a sparse tracking technique via a multi-directional graph search approach. We consider the image as a weighted unoriented graph with arches connecting adjacent pixels and assume that vessels are minimum cost paths connecting remote nodes. An initial seed-finding algorithm based on fast 1- dimensional multi-scale matched filters is run over a regular grid. Simultaneous best-first search graph explorations start from each seed: when two search frontiers meet, the computed shortest path is recorded and exploited for a new search starting from it. New paths are found by iterating the procedure, until the entire vessel network is reconstructed. Lastly, in order to cover the unexplored region with lowcontrast vessels, a custom fixing procedure is run.

Fast adaptive axis-based segmentation of retinal vessels through matched filters

Ocular fundus images provide important information about retinal degeneration, which may be related to acute pathologies or to early signs of systemic diseases. An automatic and quantitative assessment of vessel morphological features, such as diameters and tortuosity, can improve clinical diagnosis and evaluation of retinopathy. We propose a new method to accurately evaluate vessel diameters and centerline starting from an estimated network of vessel axes. The algorithm extracts points laying on the vessel borders by means of an efficient mono-dimensional matched filtering approach. The orientation of the filter kernel is chosen according to the information provided by the network and the appropriate scale is computed by means of an initial diameter estimation performed on the vessels cross section profiles before the filtering process. An adaptive correction step is then run to fix non consistent diameters, in order to obtain a regular and continuous vessel morphology. Vessel border refinement finally yields an accurate representation of the vascular structure. Average calibers were evaluated, for a set of 739 vessel segments, both manually by an expert and automatically by the proposed method and results show high correlation (ρ = 0.97).

From laboratory to clinic: The development of web-based tools for the estimation of retinal diagnostic parameters

Over the years, tools for the analysis of retinal images have been developed by several research groups but their usage has been mainly confined within the developing institutions. One possibility to foster their adoption is to develop them as web-based tools. We present here three such systems we recently developed. They are specifically focused on the estimation of retinal vascular parameters, such as arteriolar narrowing (AVR parameter), vessel tortuosity, and vessel caliber narrowing and tortuosity in retinopathy of prematurity (ROP) images. These systems have been successfully evaluated as regards their reliability and will soon be publicly available to interested health care providers.