Automatic segmentation of epidural hematomas using a computational technique based on intelligent operators: a clinical utility

This paper proposes a non-linear computational technique for the segmentation of epidural hematomas (EDH), present in 7 multilayer computed tomography brain imaging databases. This technique consists of 3 stages developed in the three-dimensional domain, namely: pre-processing, segmentation and quantification of the volume occupied by each of the segmented EDHs. To make value judgments about the performance of the proposed technique, the EDH dilated segmentations, obtained automatically, and the EDH segmentations, generated manually by a neurosurgeon, are compared using the Dice coefficient (Dc). The combination of parameters linked to the highest Dc value, defines the optimal parameters of each of the computational algorithms that make up the proposed nonlinear technique. The obtained results allow the reporting of a Dc superior to 0.90 which indicates a good correlation between the manual segmentations and those produced by the computational technique developed. Finally, as an immediate clinical application, considering the automatic segmentations, the volume of each hematoma is calculated considering both the voxel size of each database and the number of voxels that make up the segmented hematomas.

• Autores: Salazar, Juan; Vera, Miguel; Huérfano, Yoleidy; Valbuena, Oscar; Salazar, Williams; Vera, María Isabel; Gelvez, Elkin; Contreras, Yudith; Borrero, Maryury; Vivas, Marisela; Barrera, Doris; Hernández, Carlos; Molina, Ángel Valentín; Martínez, Luis Javier; Sáenz, Frank
• Fecha de publicación: 2018
• Institución: Universidad Simón Bolívar
• Repositorio: Repositorio Digital USB
• Idioma: eng
• OAI Identifier: oai:bonga.unisimon.edu.co:20.500.12442/2522
• Acceso en línea: http://hdl.handle.net/20.500.12442/2522
• Palabra clave: Brain Tomography; Epidural Hematomas; Nonlinear Computational Technique; Smart Operators; Segmentation; Tomografía cerebral; Hematomas epidurales; Técnica computacional no lineal; Operadores inteligentes; Segmentación
• License: Licencia de Creative Commons Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional