Ítem
Acceso Abierto

Determinación de la concordancia del daño del nervio optico entre un Glaucomatologo y un algoritmo de aprendizaje

Mostrar el registro sencillo de la publicación
dc.contributorPerdomo, Oscar J.
dc.contributorRíos, Hernán Andrés
dc.contributor.advisorBelalcazar Rey, Sandra
dc.contributor.advisorRosenstiehl Colón, Shirley Margarita
dc.contributor.tutorBELALCAZAR REY, SANDRA
dc.contributor.tutorROSENSTIEHL COLON, SHIRLEY
dc.creatorCarpio Rosso Delgado, Vanessa
dc.creator.degreeEspecialista en Oftalmologíaspa
dc.creator.degreetypeFull timespa
dc.date.accessioned2021-02-26T17:49:24Z
dc.date.available2021-02-26T17:49:24Z
dc.date.created2021-02-09
dc.descriptionPropósito: Determinar la concordancia entre la interpretación de las fotos a color de polo posterior de un especialista en glaucoma y un algoritmo de aprendizaje no supervisado para determinar el daño del nervio óptico. Metodología: Se realizó un estudio de concordancia diagnóstica entre la interpretación de las fotos a color de polo posterior de un especialista en glaucoma y un algoritmo de aprendizaje no supervisado con respecto a la identificación del daño del nervio óptico según el sistema de clasificación de Armaly y usando el coeficiente de kappa de Cohen. Resultados: El algoritmo de aprendizaje no supervisado evaluó 689 fotos a color de polo posterior, clasificadas como con nervio óptico sano (sin daño) y con daño leve, moderado y severo. Posteriormente un clasificador K-means, agrupó las características extraídas en los cuatro grupos mencionados y se obtuvo un coeficiente kappa de Cohen de 0.037. Cuando se clasificaron las imágenes en dos grupos, sanos y con daño, se evidenció un estadístico kappa para la clasificación dicotómica de 0.03. Conclusión: El Algoritmo de aprendizaje no supervisado usado para la clasificación de daño del nervio óptico en fotos a color de polo posterior, mostró una mala concordancia con la realizada por el especialista en glaucoma según el sistema de clasificación de Armaly.spa
dc.description.abstractPurpose: To determine the concordance between an Unsupervised Learning Algorithm and eye fundus color photos interpretation by a specialist for the identification of the optic disc damage. Methodology: A concordance study between an Unsupervised Learning Algorithm and a glaucoma specialist was made. The Cohen's kappa coefficient was calculated for identification of the optic disc damage in eye fundus color photos and were assessed according to Armaly´s cup/disc ratio classification. Results: The Unsupervised Learning Algorithm evaluated 689 color optic disc images classified as: healthy (no damage), mild, moderate and severe damage. A k-means classifier clustered the extracted features in four groups and obtained a Cohen's kappa coefficient of 0.037 While classifying the images in two groups: Healthy and with damage, we found a Cohen's kappa coefficient of 0.03. Conclusion: The Unsupervised Learning Algorithm for the classification of optic disc damage on color fundus photos showed a bad concordance with the one done by the glaucoma specialist, using Armaly`s cup/disc ratio classification.spa
dc.format.extent29spa
dc.format.mimetypeapplication/pdf
dc.identifier.doihttps://doi.org/10.48713/10336_30989
dc.identifier.urihttps://repository.urosario.edu.co/handle/10336/30989
dc.language.isospaspa
dc.publisherUniversidad del Rosariospa
dc.publisher.departmentEscuela de Medicina y Ciencias de la Saludspa
dc.publisher.programEspecialización en Oftalmologíaspa
dc.rights.accesRightsinfo:eu-repo/semantics/openAccess
dc.rights.accesoAbierto (Texto Completo)spa
dc.rights.licenciaEL AUTOR, manifiesta que la obra objeto de la presente autorización es original y la realizó sin violar o usurpar derechos de autor de terceros, por lo tanto la obra es de exclusiva autoría y tiene la titularidad sobre la misma. PARGRAFO: En caso de presentarse cualquier reclamación o acción por parte de un tercero en cuanto a los derechos de autor sobre la obra en cuestión, EL AUTOR, asumirá toda la responsabilidad, y saldrá en defensa de los derechos aquí autorizados; para todos los efectos la universidad actúa como un tercero de buena fe. EL AUTOR, autoriza a LA UNIVERSIDAD DEL ROSARIO, para que en los términos establecidos en la Ley 23 de 1982, Ley 44 de 1993, Decisión andina 351 de 1993, Decreto 460 de 1995 y demás normas generales sobre la materia, utilice y use la obra objeto de la presente autorización. -------------------------------------- POLITICA DE TRATAMIENTO DE DATOS PERSONALES. Declaro que autorizo previa y de forma informada el tratamiento de mis datos personales por parte de LA UNIVERSIDAD DEL ROSARIO para fines académicos y en aplicación de convenios con terceros o servicios conexos con actividades propias de la academia, con estricto cumplimiento de los principios de ley. Para el correcto ejercicio de mi derecho de habeas data cuento con la cuenta de correo habeasdata@urosario.edu.co, donde previa identificación podré solicitar la consulta, corrección y supresión de mis datos.spa
dc.source.bibliographicCitationShaikh Y, Yu F, Coleman AL. Burden of undetected and untreated glaucoma in the United States. Am J Ophthalmol [Internet]. 2014;158(6):1121-1129.e1. Available from: http://dx.doi.org/10.1016/j.ajo.2014.08.023spa
dc.source.bibliographicCitationTham YC, Li X, Wong TY, Quigley HA, Aung T, Cheng CY. Global prevalence of glaucoma and projections of glaucoma burden through 2040: A systematic review and meta-analysis. Ophthalmology [Internet]. 2014;121(11):2081–90. Available from: http://dx.doi.org/10.1016/j.ophtha.2014.05.013spa
dc.source.bibliographicCitationHenderer JD. Disc damage likelihood scale. Br J Ophthalmol. 2006;90(4):395–6.spa
dc.source.bibliographicCitationShickle D, Todkill D, Chisholm C, Rughani S, Griffin M, Cassels-Brown A, et al. Addressing inequalities in eye health with subsidies and increased fees for General Ophthalmic Services in socio-economically deprived communities: A sensitivity analysis. Public Health. 2015;129(2):131–7spa
dc.source.bibliographicCitationHattenhauer MG, Johnson DH, Ing HH, Herman DC, Hodge DO, Yawn BP, et al. The probability of blindness from open-angle glaucoma. Ophthalmology. 1998;105(11):2099–104spa
dc.source.bibliographicCitationStevens GA, White RA, Flaxman SR, Price H, Jonas JB, Keeffe J, et al. Global prevalence of vision impairment and blindness: Magnitude and temporal trends, 1990-2010. Ophthalmology. 2013;120(12):2377–84.spa
dc.source.bibliographicCitationVarma R, Ying-Lai M, Francis BA, Nguyen BBT, Deneen J, Wilson MR, et al. Prevalence of open-angle glaucoma and ocular hypertension in Latinos: The Los Angeles Latino Eye Study. Ophthalmology. 2004;111(8):1439–48.spa
dc.source.bibliographicCitationQuigley HA, West SK, Rodriguez J, Munoz B, Klein R, Snyder R. The prevalence of glaucoma in a population-based study of Hispanic subjects: Proyecto VER. Arch Ophthalmol. 2001;119(12):1819–26.spa
dc.source.bibliographicCitationCaprioli J. Clinical evaluation of the optic nerve in glaucoma. Trans Am Ophthalmol Soc. 1994;92:589–641.spa
dc.source.bibliographicCitationGordon MO, Torri V, Miglior S, Beiser JA, Floriani I, Miller JP, et al. Validated prediction model for the development of primary open-angle glaucoma in individuals with ocular hypertension. Ophthalmology. 2007;114(1):10-19.e2.spa
dc.source.bibliographicCitationMyers JS, Fudemberg S LD. Evolution of optic nerve photography for glaucoma screening: a review. Clin Exp Ophthalmol. 2018;13(3):287–8.spa
dc.source.bibliographicCitationChakrabarty L, Joshi GD, Chakravarty A, Raman G V., Krishnadas SR, Sivaswamy J. Automated Detection of Glaucoma from Topographic Features of the Optic Nerve Head in Color Fundus Photographs. J Glaucoma. 2016;25(7):590–7.spa
dc.source.bibliographicCitationCook C, Foster P. Epidemiology of glaucoma: What’s new? Can J Ophthalmol. 2012;47(3):223–6.spa
dc.source.bibliographicCitationBock R, Meier J, Nyúl LG, Hornegger J, Michelson G. Glaucoma risk index: Automated glaucoma detection from color fundus images. Med Image Anal. 2010;14(3):471–81.spa
dc.source.bibliographicCitationSpaeth GL, Reddy SC. Imaging of the optic disk in caring for patients with glaucoma: Ophthalmoscopy and photography remain the gold standard. Surv Ophthalmol [Internet]. 2014;59(4):454–8. Available from: http://dx.doi.org/10.1016/j.survophthal.2013.10.004spa
dc.source.bibliographicCitationHasanreisoglu M, Priel E, Naveh L, Lusky M, Weinberger D, Benjamini Y, et al. Screening for glaucoma with stereo disc photopgraphy. J Glaucoma. 1995;22(3):238–42.spa
dc.source.bibliographicCitationVijaya L, George R, Paul PG, Baskaran M, Arvind H, Raju P, et al. Prevalence of open-angle glaucoma in a rural south Indian population. Investig Ophthalmol Vis Sci. 2005;46(12):4461–7.spa
dc.source.bibliographicCitationRamakrishnan R, Nirmalan PK, Krishnadas R, Thulasiraj RD, Tielsch JM, Katz J, et al. Glaucoma in a rural population of Southern India: The Aravind Comprehensive Eye Survey. Ophthalmology. 2003;110(8):1484–90.spa
dc.source.bibliographicCitationHaleem MS, Han L, van Hemert J, Li B. Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: A review. Comput Med Imaging Graph [Internet]. 2013;37(7–8):581–96. Available from: http://dx.doi.org/10.1016/j.compmedimag.2013.09.005spa
dc.source.bibliographicCitationRahimy E. Deep learning applications in ophthalmology. Curr Opin Ophthalmol. 2018;29(3):254–60.spa
dc.source.bibliographicCitationLee A, Taylor P, Kalpathy-Cramer J. Machine Learning Has Arrived! Ophthalmology. 2017;124(12):1726–8.spa
dc.source.bibliographicCitationKotowski J, Wollstein G IH. Imaging of the optic nerve and retinal nerve fiber layer: an essential part of glaucoma diagnosis and monitoring. Surv Ophthalmol. 2014;23(1):1–7.spa
dc.source.bibliographicCitationQuigley H, Broman AT. The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol. 2006;90(3):262–7.spa
dc.source.bibliographicCitationBourne RRA, Taylor HR, Flaxman SR, Keeffe J, Leasher J, Naidoo K, et al. Number of people blind or visually impaired by glaucoma worldwide and in world regions 1990 - 2010: A meta-analysis. PLoS One. 2016;11(10):1–16.spa
dc.source.bibliographicCitationFoster PJ, Buhrmann R, Quigley HA, Johnson GJ. The definition and classification of glaucoma in prevalence surveys. Br J Ophthalmol. 2002;86(2):238–42.spa
dc.source.bibliographicCitationCaprioli J, Prum B, Zeyen T. Comparison of methods to evaluate the optic nerve head and nerve fiber layer for glaucomatous change. Am J Ophthalmol. 1996;121(6):659–67.spa
dc.source.bibliographicCitationLiu JHK, Zhang X, Kripke DF, Weinreb RN. Twenty-four-hour intraocular pressure pattern associated with early glaucomatous changes. Investig Ophthalmol Vis Sci. 2003;44(4):1586–90.spa
dc.source.bibliographicCitationLeske MC. Distribution of Intraocular Pressure. Arch Ophthalmol. 1997;115(8):1051.spa
dc.source.bibliographicCitationWall M, Stanek KE, Chauhan BC. Variability in patients with glaucomatous visual field damage is reduced using size V stimuli. Investig Ophthalmol Vis Sci. 1996;37(3).spa
dc.source.bibliographicCitationReus NJ, Lemij HG, Garway-Heath DF, Airaksinen PJ, Anton A, Bron AM, et al. Clinical Assessment of Stereoscopic Optic Disc Photographs for Glaucoma: The European Optic Disc Assessment Trial. Ophthalmology [Internet]. 2010;117(4):717–23. Available from: http://dx.doi.org/10.1016/j.ophtha.2009.09.026spa
dc.source.bibliographicCitationErvin A, Boland M, Myrowitz E, Prince J, Hawkins B, Vollenweider D, et al. Treatment for Glaucoma: Comparative Effectiveness. Comparative Effectiveness Review. AHRQ Publ No 12-EHC038-EF [Internet]. 2012;Review No.(60):443. Available from: www.effectivehealthcare.ahrq.gov/reports/final.cfm.%5Cnwww.effectivehealthcare.ahrq.gov/reports/final.cfmspa
dc.source.bibliographicCitationLee CS, Baughman DM, Lee AY. Deep Learning Is Effective for Classifying Normal versus Age-Related Macular Degeneration OCT Images. Kidney Int Reports [Internet]. 2017;1(4):322–7. Available from: http://dx.doi.org/10.1016/j.oret.2016.12.009spa
dc.source.bibliographicCitationGargeya R, Leng T. Automated Identification of Diabetic Retinopathy Using Deep Learning. Ophthalmology [Internet]. 2017;124(7):962–9. Available from: http://dx.doi.org/10.1016/j.ophtha.2017.02.008spa
dc.source.bibliographicCitationChristopher M, Belghith A, Bowd C, Proudfoot JA, Goldbaum MH, Weinreb RN, et al. Performance of Deep Learning Architectures and Transfer Learning for Detecting Glaucomatous Optic Neuropathy in Fundus Photographs. Sci Rep. 2018;8(1):1–13.spa
dc.source.bibliographicCitationMedeiros FA, Jammal AA, Thompson AC. From Machine to Machine: An OCT-Trained Deep Learning Algorithm for Objective Quantification of Glaucomatous Damage in Fundus Photographs. Ophthalmology [Internet]. 2019;126(4):513–21. Available from: https://doi.org/10.1016/j.ophtha.2018.12.033spa
dc.source.bibliographicCitationSimonyan K ZA. Very Deep Convolutional Networks for Large-Scale Image Recognition. Int Conf Learn Represent. 2015;75(6):398–406.spa
dc.source.bibliographicCitationSivaswamy J, Gopal SRK, Joshi D, Jain M, Syed U, Hospital AE. DRISHTI-GS : Retinal image dataset for optic nerve head segmentation. 2014;53–6.spa
dc.source.bibliographicCitationFumero F, Alayon S, Sanchez JL, Sigut J, Gonzalez-Hernandez M. RIM-ONE: An open retinal image database for optic nerve evaluation. Proc - IEEE Symp Comput Med Syst. 2011;2–7.spa
dc.source.bibliographicCitationAssociation WM. WorldMedical Association Declaration of Helsinki Ethical Principles for Medical Research Involving Human Subjects. JAMA - J Am Med Assoc. 2013;310.spa
dc.source.bibliographicCitationColombia R de. Ministerio de Salud. Resolucion Numero 8430 de 1993. RN 008430. 2012;32(4):471–3.spa
dc.source.bibliographicCitationTing DSW, Cheung CYL, Lim G, Tan GSW, Quang ND, Gan A, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA - J Am Med Assoc. 2017;318(22):2211–23.spa
dc.source.bibliographicCitationLi Z, He Y, Keel S, Meng W, Chang RT, He M. Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs. Ophthalmology [Internet]. 2018;125(8):1199–206. Available from: https://doi.org/10.1016/j.ophtha.2018.01.023spa
dc.source.bibliographicCitationPhene S, Dunn RC, Hammel N, Liu Y, Krause J, Kitade N, et al. Deep Learning and Glaucoma Specialists: The Relative Importance of Optic Disc Features to Predict Glaucoma Referral in Fundus Photographs. Ophthalmology [Internet]. 2019;126(12):1627–39. Available from: https://doi.org/10.1016/j.ophtha.2019.07.024spa
dc.source.bibliographicCitationChristopher M, Belghith A, Weinreb RN, Bowd C, Goldbaum MH, Saunders LJ, et al. Retinal nerve fiber layer features identified by unsupervised machine learning on optical coherence tomography scans predict glaucoma progression. Investig Ophthalmol Vis Sci. 2018;59(7):2748–56.spa
dc.source.bibliographicCitationGoldbaum MH, Sample PA, Zhang Z, Chan K, Lee T, Boden C, et al. Using Unsupervised Learning with Independent Component Analysis to Identify Patterns of Glaucomatous Visual Field Defects. Invest Ophthalmol. 2005;46(10):3676–83.spa
dc.source.instnameinstname:Universidad del Rosariospa
dc.source.reponamereponame:Repositorio Institucional EdocURspa
dc.subjectUso de algoritmos de aprendizaje no supervisados en diagnostico medicospa
dc.subjectDiagnóstico del daño del nervio ópticospa
dc.subjectTecnología médicaspa
dc.subjectInterpretación de fotos a color de polo posterior en detección de daño ópticospa
dc.subjectDaño del nervio óptico según clasificación de Armalyspa
dc.subject.ddcMedicina experimentalspa
dc.subject.keywordUse of unsupervised learning algorithms in medical diagnosisspa
dc.subject.keywordDiagnosis of optic disc damagespa
dc.subject.keywordMedical technologyspa
dc.subject.keywordInterpretation of back pole color photos in detection of optical disc damagespa
dc.subject.keywordOptic nerve damage according to Armaly classificationspa
dc.titleDeterminación de la concordancia del daño del nervio optico entre un Glaucomatologo y un algoritmo de aprendizajespa
dc.title.TranslatedTitleDetermination of the concordance of optic nerve damage between a Glaucomatologist and a learning algorithmspa
dc.title.alternativeDETERMINATION OF THE CONCORDANCE OF OPTIC NERVE DAMAGE BETWEEN A GLAUCOMATOLOGIST AND A LEARNING ALGORITHMspa
dc.typebachelorThesiseng
dc.type.documentRevisión sistemáticaspa
dc.type.hasVersioninfo:eu-repo/semantics/acceptedVersion
dc.type.spaTrabajo de gradospa
Archivos
Bloque original
Mostrando1 - 1 de 1
Miniatura
Nombre:
TRABAJO DE GRADO .pdf
Tamaño:
306.06 KB
Formato:
Adobe Portable Document Format
Descripción:
ARTICULO PRINCIPAL
Descargar
Colecciones
Especialización en Oftalmología