Show simple item record

dc.contributor.advisorGil Romero, Robertspa
dc.contributor.authorAlba Acosta, David Camilospa
dc.date.accessioned2021-02-04T21:01:10Zspa
dc.date.available2021-02-04T21:01:10Zspa
dc.date.issued2021-02-04spa
dc.identifier.citationAlba Acosta, D. C. (2021). Mecanismos de atención e interpretabilidad en el aprendizaje automático para la detección de enfermedades oculares a través del uso de tomografías. [Tesis de Pregrado, Universidad Santo Tomás Colombia]. Repositorio Institucionalspa
dc.identifier.urihttp://hdl.handle.net/11634/31964spa
dc.descriptionEl Deep learning o “aprendizaje profundo” vino para quedarse por mucho tiempo; es así que, en los últimos años producto del desarrollo de la inteligencia artificial, su actuar ha venido aplicándose en varias áreas del conocimiento principalmente en las ciencias de la salud. Ante este fenómeno señalado, la medicina tradicionalmente ha venido desarrollando los diagnósticos de enfermedades como de traumatologías, incorporando el uso de rayos x, resonancias magnéticas y tomografías entre otras. En ese sentido, la ciencia de la medicina ha venido implementando sistemas autónomos, los cuales, han venido a complementar la forma de analizar la información médica. La ciencia médica hoy en día viene desarrollando en sus diferentes áreas del conocimiento la aplicación de la inteligencia artificial mediante el uso del deep learning, como es el caso de la oftalmología y de la optometría. De conformidad con lo explicitado, el trabajo propuesto tiene como objetivo principal: Encontrar la mejor arquitectura CNN “Convolutional neural network” que se adapte a un conjunto de datos que contiene tomografías oculares en la región de la retina, y que sea capaz de clasificar estos cuatro tipos de diagnóstico ocular: Normal, Drusen, CNV (Neurovascularización coroidea) y DME(Edema Macular diabético).spa
dc.description.abstractDeep learning is here to stay for a long time; thus, in recent years, as a result of the development of artificial intelligence, it has been applied in several areas of knowledge, mainly in the health sciences. Faced with this phenomenon, medicine has traditionally been developing the diagnosis of diseases such as traumatology, incorporating the use of x-rays, magnetic resonance imaging and tomography, among others. In this sense, the science of medicine has been implementing autonomous systems, which have come to complement the way of analyzing medical information. Medical science today is developing in its different areas of knowledge the application of artificial intelligence through the use of deep learning, as is the case of ophthalmology and optometry. In accordance with the above, the main objective of the proposed work is: To find the best CNN architecture "Convolutional neural network" that adapts to a dataset containing ocular tomographies in the retina region, and that is able to classify these four types of ocular diagnosis: Normal, Drusen, CNV (Choroidal Neurovascularization) and DME (Diabetic Macular Edema).
dc.format.mimetypeapplication/pdfspa
dc.language.isospaspa
dc.publisherUniversidad Santo Tomásspa
dc.rightsAtribución-NoComercial-SinDerivadas 2.5 Colombia*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.5/co/*
dc.titleMecanismos de atención e interpretabilidad en el aprendizaje automático para la detección de enfermedades oculares a través del uso de tomografíasspa
dc.typeFormación de Recurso Humano para la Ctel: Trabajo de grado de Pregradospa
dc.description.degreenameProfesional en estadísticaspa
dc.publisher.programPregrado Estadísticaspa
dc.publisher.facultyFacultad de Estadísticaspa
dc.subject.keywordDeep learning
dc.subject.keywordCNN
dc.subject.keywordNeural networks
dc.subject.keywordAttention modules
dc.subject.keywordOcular diseases
dc.subject.lembEnfermedades de los ojosspa
dc.subject.lembOftalmologíaspa
dc.subject.lembspa
dc.subject.lembTomografíaspa
dc.rights.localAbierto (Texto Completo)spa
dc.rights.localAbierto (Texto Completo)spa
dc.type.versionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.rights.accessrightshttp://purl.org/coar/access_right/c_abf2spa
dc.coverage.campusCRAI-USTA Bogotáspa
dc.contributor.orcidhttps://orcid.org/0000-0001-8602-6890spa
dc.contributor.googlescholarhttps://scholar.google.com/citations?user=LUEZqaYAAAAJ&hl=esspa
dc.contributor.cvlachttps://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000157060spa
dc.description.domainhttp://unidadinvestigacion.usta.edu.cospa
dc.relation.referencesAlom, M. Z., Taha, T. M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M. S., Hasan, M., Van Essen, B. C., Awwal, A. A., and Asari, V. K. (2019). A state-of-the-art survey on deep learning theory and architectures. Electronics, 8(3):292.spa
dc.relation.referencesBrowning, D. J., Stewart, M. W., and Lee, C. (2018). Diabetic macular edema: evidence-based management. Indian journal of ophthalmology, 66(12):1737–1738.spa
dc.relation.referencesCortes, C. and Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3):273–297.spa
dc.relation.referencesDenker, J. S. and LeCun, Y. (1991). Transforming neural-net output levels to probability distributions. In Advances in neural information processing systems, pages 853–859.spa
dc.relation.referencesGoodfellow, I., Bengio, Y., and Courville, A. (2016a). Deep learning. MIT press.spa
dc.relation.referencesGoodfellow, I., Bengio, Y., and Courville, A. (2016b). Deep Learning. MIT Press. http://www .deeplearningbook.org.spa
dc.relation.referencesHu, J., Shen, L., and Sun, G. (2018). Squeeze-andexcitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7133–7134.spa
dc.relation.referencesHuang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.spa
dc.relation.referencesIoffe, S. and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint ar- Xiv:1502.03167.spa
dc.relation.referencesJaiswal, T. and Jaiswal, S. (2019). Deep learning in medicine.spa
dc.relation.referencesKermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C., Liang, H., Baxter, S. L., McKeown, A., Yang, G., Wu, X., Yan, F., et al. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5):1122– 1131.spa
dc.relation.referencesKingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint ar- Xiv:1412.6980.spa
dc.relation.referencesNielsen, M. A. (2015). Neural networks and deep learning, volume 2018. Determination press San Francisco, CA.spa
dc.relation.referencesRavì, D., Wong, C., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B., and Yang, G.-Z. (2016). Deep learning for health informatics. IEEE journal of biomedical and health informatics, 21(1):4–21.spa
dc.relation.referencesRazzak, M. I., Naz, S., and Zaib, A. (2018). Deep learning for medical image processing: Overview, challenges and the future. In Classification in Bio- Apps, pages 323–350. Springer.spa
dc.relation.referencesRibeiro, M. T., Singh, S., and Guestrin, C. (2016). "why should i trust you?.explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144.spa
dc.relation.referencesRuder, S. (2016). An overview of gradient descent optimization algorithms. arXiv preprint ar- Xiv:1609.04747, page 4.spa
dc.relation.referencesSarkar, D. (2018). A comprehensive hands-on guide to transfer learning with real-world applications in deep learning.spa
dc.relation.referencesWilliams, M., Craig, D., Passmore, P., and Silvestri, G. (2009). Retinal drusen: harbingers of age, safe havens for trouble. Age and ageing, 38(6):648–649.spa
dc.relation.referencesWoo, S., Park, J., Lee, J.-Y., and So Kweon, I. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pages 3–19.spa
dc.relation.referencesYeo, N. J. Y., Chan, E. J. J., and Cheung, C. (2019). Choroidal neovascularization: Mechanisms of endothelial dysfunction. Frontiers in Pharmacology, 10:1–2.spa
dc.relation.referencesZhangLabData (2018). Large dataset of labeled optical coherence tomography (oct) and chest x-ray images.spa
dc.contributor.corporatenameUniversidad Santo Tomás
dc.subject.proposalAprendizaje profundospa
dc.subject.proposalRedes neuronalesspa
dc.subject.proposalCNNspa
dc.subject.proposalMódulos de atenciónspa
dc.subject.proposalEnfermedades ocularesspa
dc.identifier.reponamereponame:Repositorio Institucional Universidad Santo Tomásspa
dc.identifier.instnameinstname:Universidad Santo Tomásspa
dc.description.degreelevelPregradospa
dc.identifier.repourlrepourl:https://repository.usta.edu.cospa


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Atribución-NoComercial-SinDerivadas 2.5 Colombia
Except where otherwise noted, this item's license is described as Atribución-NoComercial-SinDerivadas 2.5 Colombia

Indexado por: