Purchase this article with an account.
Jeffrey Wigdahl, Enea Poletti, Pedro Guimaraes, Alfredo Ruggeri; CANE (CORNEAL NERVE EDITOR): A User-Friendly Unified Computerized System for Recognizing, Editing and Analyzing Corneal Sub-Basal Nerves Images. Invest. Ophthalmol. Vis. Sci. 2014;55(13):4864.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
To provide ophthalmologists with a user-friendly computerized system for the analysis of corneal nerve images. It will allow clinicians and researchers to recover quantitative assessment of clinical parameters in an objective and user-friendly way.
The application provides the user with several tools: image file management system, fully automatic detection of nerves, fast editing of the results, and clinical parameters computation. - The file management system allows the user to effectively organize images of the patients under analysis. The data extracted with the other tools (nerve tracings and clinical parameters) are linked to the original image and saved automatically. - When a new image file is uploaded, a totally automated procedure performs nerve detection. - The user can then evaluate these tracings and, when necessary, apply corrections via a user-friendly editing interface. Even the most complex operations (e.g., insertion, splitting) can be performed via only a single mouse click. - In the upper-left panel of the interface (see Fig. 1) the clinical parameters are showed in real-time: even during editing, these parameters are instantly computed and updated in the display. Number of nerves and their density, as well as single nerve tortuosity, are computed by our previously developed procedures, while whole image tortuosity is derived by combining single-nerve values with a custom weight-averaged procedure. A set of 50 images used to test the system was acquired with a laser scanning in-vivo confocal microscope (IVCM; Heidelberg Retinal Tomograph 3 with Rostock Corneal Module; Heidelberg Engineering, Heidelberg, Germany).
The interface of the developed system is shown in Fig. 1. The system has been used to detect nerves and extract the clinical parameters in a set of 50 image. Several users’ experience confirmed the effectiveness and user friendliness of the system.
A computerized system for the quantitative analysis of nerve density and tortuosity in corneal images has been developed and will be soon available for use. Ease of use and clinical effectiveness were the main criteria underlying its development.
This PDF is available to Subscribers Only