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

dc.contributor.authorSalazar, Juan
dc.contributor.authorVera, Miguel
dc.contributor.authorHuérfano, Yoleidy
dc.contributor.authorValbuena, Oscar
dc.contributor.authorSalazar, Williams
dc.contributor.authorVera, María Isabel
dc.contributor.authorGelvez, Elkin
dc.contributor.authorContreras, Yudith
dc.contributor.authorBorrero, Maryury
dc.contributor.authorVivas, Marisela
dc.contributor.authorBarrera, Doris
dc.contributor.authorHernández, Carlos
dc.contributor.authorMolina, Ángel Valentín
dc.contributor.authorMartínez, Luis Javier
dc.contributor.authorSáenz, Frank
dc.date.accessioned2019-01-25T14:15:54Z
dc.date.available2019-01-25T14:15:54Z
dc.date.issued2018
dc.description.abstractThis 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.eng
dc.description.abstractEste artículo propone una técnica computacional no lineal para la segmentación de los hematomas epidurales (EDH), presente en 7 bases de datos de imágenes cerebrales de tomografía multicapa. Esta técnica consta de 3 etapas desarrolladas en el dominio tridimensional, a saber: preprocesamiento, segmentación y cuantificación del volumen ocupado por cada uno de los EDH segmentados. Para hacer juicios de valor sobre el rendimiento de la técnica propuesta, las segmentaciones dilatadas de EDH, obtenidas automáticamente, y las segmentaciones de EDH, generadas manualmente por un neurocirujano, se comparan utilizando el coeficiente de Dice (Dc). La combinación de parámetros vinculados al valor más alto de Dc define los parámetros óptimos de cada uno de los algoritmos computacionales que conforman la técnica no lineal propuesta. Los resultados obtenidos permiten el reporte de un Dc superior a 0.90 que indica una buena correlación entre las segmentaciones manuales y las producidas por la técnica computacional desarrollada. Finalmente, como aplicación clínica inmediata, considerando las segmentaciones automáticas, el volumen de cada hematoma se calcula considerando tanto el tamaño del vóxel de cada base de datos como el número de vóxeles que conforman los hematomas segmentados.spa
dc.identifier.issn26107988
dc.identifier.urihttp://hdl.handle.net/20.500.12442/2522
dc.language.isoengeng
dc.publisherSociedad Venezolana de Farmacología Clínica y Terapéuticaspa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.rights.licenseLicencia de Creative Commons Reconocimiento-NoComercial-CompartirIgual 4.0 Internacionalspa
dc.sourceRevista AVFT-Archivos Venezolanos de Farmacología y Terapéuticaspa
dc.sourceVol. 37, No. 4 (2018)spa
dc.source.urihttp://www.revistaavft.com/images/revistas/2018/avft_4_2018/2_automatic_segmentation_of_epidural.pdfeng
dc.subjectBrain Tomographyeng
dc.subjectEpidural Hematomaseng
dc.subjectNonlinear Computational Techniqueeng
dc.subjectSmart Operatorseng
dc.subjectSegmentationeng
dc.subjectTomografía cerebralspa
dc.subjectHematomas epiduralesspa
dc.subjectTécnica computacional no linealspa
dc.subjectOperadores inteligentesspa
dc.subjectSegmentaciónspa
dc.titleAutomatic segmentation of epidural hematomas using a computational technique based on intelligent operators: a clinical utilityeng
dc.title.alternativeSegmentación automática de hematomas epidurales usando una técnica computacional, basada en operadores inteligentes: utilidad clínicaspa
dc.typearticleeng
dcterms.referencesStippler M. Craniocerebral trauma. In: Daroff RB, Jankovic J, Mazziotta JC, Pomeroy SL, eds. Bradley’s Neurology in Clinical Practice. 7th ed. Philadelphia, PA: Elsevier; 2016: chap 62.eng
dcterms.referencesMezzadri J., Goland J., y Sokolvsky M. Introducción a la Neurocirugía. Capítulo: Patología vascular II. Ediciones Journal. Segunda edición. 2011.spa
dcterms.referencesVera M. Segmentación de estructuras cardiacas en imágenes de tomografía computarizada multi-corte. Ph.D. dissertation, Universidad de los Andes, Mérida-Venezuela, 2014.spa
dcterms.referencesMaiera A, Wigstrm L, Hofmann H, Hornegger J, Zhu L, Strobel N, Fahrig R. Three-dimensional anisotropic adaptive filtering of projection data for noise reduction in cone beam CT. Medical Physics. 2011;38(11):5896–909.eng
dcterms.referencesKroft L, De Roos A, Geleijns J. Artifacts in ECG–synchronized MDCT coronary angiography. American Journal of Roentgenology. 2007;189(3):581–91.eng
dcterms.referencesLiao C., Xiao F., Wong J., Chiang I. Computer-aided diagnosis of intracranial hematoma with brain deformation on computed tomography. Computerized Medical Imaging and Graphics 34 (2010) 563–571.eng
dcterms.referencesDice, L. Measures of the amount of ecologic association between species. Ecology, vol. 26, n. 3, pp. 297-302. 1945.eng
dcterms.referencesKamnitsas K., Lediga C. , Newcombeb V., Simpsonb J. , Kaneb A. , Menonb D., Rueckerta D., Glockera B. Efficient Multi-Scale 3D CNN with fully connected CRF for Accurate Brain Lesion Segmentation. Medical Image Analysis, Vol 23, pp.1603-1659, 2017.eng
dcterms.referencesSezgin M., Sankur B. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging, vol. 13, pp. 146–165, 2004.eng
dcterms.referencesPham D., Xu C., Prince J.Current methods in medical image segmentation, Annual Review of Biomedical Engineering. vol. 2, pp. 315–337, 2000.eng
dcterms.referencesSerra J. Image Analysis Using Mathematical Morphology. London, England: Academic Press, 1982.eng
dcterms.referencesW. Pratt, Digital Image Processing. USA: John Wiley & Sons Inc, 2007.eng
dcterms.referencesMukhopadhyay S., Chanda B. A multiscale morphological approach to local contrast enhancement. Signal Processing, vol. 80, no. 4, pp. 685–696, 2000.eng
dcterms.referencesYu Z., Wei G., Zhen C., Jing T., Ling L. Medical images edge detection based on mathematical morphology. En Proceedings of the IEEE Engineering in Medicine and Biology 27th Annual Conference, Shanghai–China, September 2005, pp. 6492–6495.eng
dcterms.referencesChen T., Wu Q., Rahmani R., Hughes J. A pseudo top-hat mathematical morphological approach to edge detection in dark regions. Pattern Recognition. 2002; 35(1):199–210.eng
dcterms.referencesPassarielo G., Mora F. Imágenes Médicas, Adquisición, Análisis, Procesamiento e Interpretación. Venezuela: Equinoccio Universidad Simón Bolívar. 1995.spa
dcterms.referencesFischer M., Paredes J., Arce G. Weighted median image sharpeners for the world wide web. IEEE Transactions on Image Processing. 2002;11(7):717-27.eng
dcterms.referencesV. Vapnik, Statistical Learning Theory. New York: John Wiley & Sons, 1998.eng
dcterms.referencesE. Osuna, R. Freund, y F. Girosi, “Training support vector machines: an application to face detection.” en Conference on Computer Vision and Pattern Recognition (CVPR ’97), San Juan, Puerto Rico, 1997, pp. 130–136.eng
dcterms.referencesA. Smola, “Learning with kernels,” Tesis de Doctorado, Technische Universitt Berlin,Germany, 1998.eng
dcterms.referencesB. Scholkopf y A. Smola, Learning with Kernels: Support Vector Machines, Regularization,Optimization, and Beyond. Cambridge, MA, USA: The MIT Press, 2002.eng
dcterms.referencesJ. Suykens, T. V. Gestel, y J. D. Brabanter, Least Squares Support Vector Machines.UK: World Scientific Publishing Co., 2002.eng
dcterms.referencesM. Oren, C. Papageorgiou, P. Sinha, E. Osuna, y T. Poggio, “Pedestrian detection using wavelet templates,” en CVPR ’97: Conference on Computer Vision and Pattern Recognition (CVPR ’97). Washington, DC, USA: IEEE Computer Society, 1997, pp. 193–200.eng
dcterms.referencesHu T., Yan L., Yan Peng., Wang X., Yue G. Assessment of the ABC/2 Method of Epidural Hematoma Volume Measurement as Compared to Computer-Assisted Planimetric Analysis. Biological Research for Nursing. 2016, 18(1) 5-11.eng
dcterms.referencesFreeman, W., Barrett, K., Bestic, J.,Meschia, J., Broderick, D., Brott, T. Computer-assisted volumetric analysis compared with ABC/2 method for assessing warfarinrelated intracranial hemorrhage volumes. 2008, Neurocritical Care, 9, 307–312.eng

Archivos

Bloque original
Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
Automatic segmentation of epidural.pdf
Tamaño:
713.39 KB
Formato:
Adobe Portable Document Format
Descripción:
PDF
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
368 B
Formato:
Item-specific license agreed upon to submission
Descripción:

Colecciones