RESUMO

One of the initial steps in the preprocessing of digital fundoscopy images is the identification of pixels containing relevant information. This can be achieved through different approaches, one of them is implementing background extraction, reducing the set of pixels to be analyzed later in the process. In this work, we present a background extraction method for digital fundoscopy images based on computational topology. By interpreting binarized images as cubical complexes and extracting their homological groups in 1 and 2 dimensions we identify a subset of luminescence values that can be used to binarize the original grayscale image, obtaining a mask to achieve background extraction. This method is robust to noise and suboptimal image quality, facilitating the analytical pipeline in the context of computer aided diagnosis approaches. This method facilitates the segmentation of the background of a digital fundoscopy image, which allows further methods to focus on pixels with relevant information (eye fundus). This tool is best suited to be implemented in the preprocessing stages of the analytical pipeline by computational ophthalmology specialists.•It is robust to noise and low-quality images.•Output provides an ideal scenario for down-the-line analysis by facilitating only relevant pixels in a digital fundoscopy.

RESUMO

Abstract: Patients' medical records have been originally based on paper and since 1865 the medical field recognized the need to improve the means for storing and retrieving disperse information. Electronic Health Records (EHR) systems face similar problems, with interoperability being one of them, it defined by IEEE standard glossary of software engineering terminology as: the ability among information systems to exchange data. Mainly, two perspectives of interoperability emerge: a) syntactic, which refers to the ability of an information system to import and validate grammar, as well as a set of construction rules utterances created by another system; and b) semantic, the ability to exchange data among systems and understand it in the same way, regardless of the source system, also called Semantic Interoperability on Information and Communication Technologies or SIICT. The use of standards, vocabularies and terminologies is a common practice for sharing data among heterogeneous EHR systems in order to face interoperability problems. This heterogeneity starts with the manner to collect and store data. This paper presents to e-health practitioners and researches relevant tools used to achieve interoperability in heterogeneous EHR systems, as well as challenges and future trends to manage EHRs with the intention to achieve SIICT.

Resumen: Los registros clínicos de pacientes se basaron en papel originalmente, desde el año de 1865 se reconoció en el entorno medico la necesidad de mejorar los medios para el almacenamiento y recuperación de información dispersa. Los Sistemas de Expediente Clínicos Electrónicos (ECE) enfrentan problemas similares, siendo uno de estos problemas, la interoperabilidad. La cual es definida por "IEEE standard glossary of software engineering terminology" como: la habilidad de intercambiar datos entre sistemas de información, donde dos perspectivas de interoperabilidad emergen: a) sintáctica, la cual se refiere a la habilidad de un sistema de información de importar y validar la gramática de datos, así como de un conjunto de reglas de expresiones creadas por otro sistema; y b) semántica, como la habilidad de intercambiar datos entre sistemas y de entenderlos de la misma forma, independientemente del sistema fuente, llamando a esto como Interoperabilidad Semántica sobre Tecnologías De La Información y Comunicación (ISTIC). El uso de estándares, vocabularios y terminologías es una práctica común para poder compartir datos entre sistemas ECE con el fin de enfrentar problemas de interoperabilidad. Esta heterogeneidad se da desde la forma en cómo se colecta y almacenan los datos. Este artículo presenta a los profesionales de salud e investigadores de e-salud acerca de herramientas relevantes utilizadas para lograr la interoperabilidad de sistemas ECE heterogéneos, así como retos y futuras tendencias para administrar sistemas ECE con la intención de lograr ISTIC.