Markerless monocular tracking system for guided external eye surgery

This paper presents a novel markerless monocular tracking system aimed at guiding ophthalmologists during external eye surgery. This new tracking system performs a very accurate tracking of the eye by detecting invariant points using only textures that are present in the sclera, i.e., without using...

Descripción completa

Detalles Bibliográficos
Autores: Monserrat C, Rupérez MJ, Alcañiz M, Mataix J
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2014
País:España
Institución:Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunitat Valenciana (FISABIO)
Repositorio:r-FISABIO. Repositorio Institucional de Producción Científica
OAI Identifier:oai:fisabio.fundanetsuite.com:p5234
Acceso en línea:https://fisabio.portalinvestigacion.com/publicaciones/5234
Access Level:acceso abierto
Palabra clave:Eye tracking
External eye surgery
Markerless video tracking
SIFT
SURF
Computer aided surgery
Descripción
Sumario:This paper presents a novel markerless monocular tracking system aimed at guiding ophthalmologists during external eye surgery. This new tracking system performs a very accurate tracking of the eye by detecting invariant points using only textures that are present in the sclera, i.e., without using traditional features like the pupil and/or cornea reflections, which remain partially or totally occluded in most surgeries. Two known algorithms that compute invariant points and correspondences between pairs of images were implemented in our system: Scalable Invariant Feature Transforms (SIFT) and Speed Up Robust Features (SURF). The results of experiments performed on phantom eyes show that, with either algorithm, the developed system tracks a sphere at a 360 degrees rotation angle with an error that is lower than 0.5%. Some experiments have also been carried out on images of real eyes showing promising behavior of the system in the presence of blood or surgical instruments during real eye surgery. (C) 2014 Elsevier Ltd. All rights reserved.