Publicación:
Clasificación de cáncer cervical usando redes neuronales convolucionales, transferencia de aprendizaje y aumento de datos

Vista sencilla de ítem
dc.contributor.authorBravo Ortíz, Mario Alejandrospa
dc.contributor.authorArteaga Arteaga, Harold Brayanspa
dc.contributor.authorTabares Soto, Reinelspa
dc.contributor.authorPadilla Buriticá, Jorge Ivánspa
dc.contributor.authorOrozco-Arias, Simonspa
dc.date.accessioned2020-12-31 14:30:36
dc.date.accessioned2022-06-17T20:21:00Z
dc.date.available2020-12-31 14:30:36
dc.date.available2022-06-17T20:21:00Z
dc.date.issued2020-12-31
dc.description.abstractEl cáncer cervical se forma en las células que revisten el cuello uterino y la parte inferior del útero. Debido a razones de costo y baja oferta de servicios destinados a la detección de este tipo de cáncer, muchas mujeres no tienen acceso a un diagnóstico pronto y preciso, ocasionando un inicio tardío del tratamiento. Para dar solución a este problema se implementó una metodología que clasifica de manera automática el tipo de cáncer cervical, entre leve (Tipo 1 y 2) y agresivo (Tipo 3), utilizando técnicas de procesamiento digital de imágenes y aprendizaje profundo. Se trabajó en la construcción de un modelo computacional con base en redes neuronales convolucionales, transferencia de aprendizaje y aumento de datos, obteniendo precisiones de clasificación de hasta 97,35% sobre los datos de validación, asegurando la confiabilidad de los resultados. Con este trabajo se demostró que el diseño propuesto puede ser usado como un complemento para mejorar la eficiencia de las herramientas del diagnóstico asistido del cáncer.spa
dc.description.abstractCervical cancer is formed in the cells that line the cervix and the lower part of uterus. Due to the cost and low reasons and low supply of services for the detection of this type of cancer many women do not have access to an early an accurate diagnosis. With the purpose of solving this issue ir was created a certain method that helps us to automatically classify the different types of cervical cancer, such as mild type 1 and 2, and aggressive (type 3), using digital image processing techniques and deep learning. We have a built a computational model based on convolutional neural networks, transfer learning and data increase, which help us obtain a classification accuracy up to 97.35% on the validation data, thus, we can ensure the reliability of the results. With this work it was demonstrated that the proposed design can be used as a complement to improve the tools of the assisted diagnosis of cancer.eng
dc.format.mimetypeapplication/pdfspa
dc.identifier.doi10.24050/reia.v18i35.1462
dc.identifier.eissn2463-0950
dc.identifier.issn1794-1237
dc.identifier.urihttps://repository.eia.edu.co/handle/11190/5132
dc.identifier.urlhttps://doi.org/10.24050/reia.v18i35.1462
dc.language.isospaspa
dc.publisherFondo Editorial EIA - Universidad EIAspa
dc.relation.bitstreamhttps://revistas.eia.edu.co/index.php/reveia/article/download/1462/1391
dc.relation.citationeditionNúm. 35 , Año 2021spa
dc.relation.citationendpage12
dc.relation.citationissue35spa
dc.relation.citationstartpage35008 pp. 1
dc.relation.citationvolume18spa
dc.relation.ispartofjournalRevista EIAspa
dc.relation.referencesMcGuire S. World cancer report 2014. Geneva, Switzerland: World Health Organization, international agency for research on cancer, WHO Press, 2015. Advances in Nutrition: An International Review Journal, 7, 418-419, 2016.spa
dc.relation.referencesAkshaya R., Manie R., Monisha B., Ranichadra V. Convolutional Neural Networks Aiding Colposcopy Image Classification. International Journal of Trend in Research and development, 5, 270-274, 2018.spa
dc.relation.referencesAlmonte M., Sánchez G.I., Jerónimo J., Ferreción C., Lazcano E., Herrera R. Nuevos Paradigmas en la Prevención y Control de Cáncer de Cuello Uterino en América Latina. Salud Pública de México, 52, No 6, 2010.spa
dc.relation.referencesLorena M., Villate S., Jiménez D., Conduct in regard to the papanicolaou test: The voice of the patients in face of abnormal growth in the cervix, Revista Colombiana de Enfermería, Vol. 18, páginas 1-13, 2019spa
dc.relation.referencesKaur N., Panagrahi N., Mittal A. Automated Cervical Cancer Screening Using Transfer Learning. International Journal Of Advanced Research in Science and Engineering, 6, 2110-2119, 2017.spa
dc.relation.referencesIntel & MobileODT, Cervical Cancer Screening, 2017, [Online]. Available: https://www.kaggle.com/c/intel-mobileodt-cervical-cancer-screening/dataspa
dc.relation.referencesSimonyan K., Zisserman A. Very Deep Convolutional Networks for Large Scale Image Recognition. Published as a conference paper at ICLR 2015. San Diego, California, Estados Unidos, abril, 2015.spa
dc.relation.referencesPark Chansung, Transfer Learning in Tensorflow (VGG19 on CIFAR-10): Part 1, 2018, 10 Octubre 2019, [Online]. Available: https://towardsdatascience.com/transfer-learning-in-tensorflow-9e4f7eae3bb4spa
dc.relation.referencesStanford University, Princeton University, ImageNet, 2016, 10 Octubre 2019, [Online]. Available: http://www.image-net.org/spa
dc.relation.referencesZhang XQ, Zhao S-G, Cervical image classification based on image segmentation preprocessing and a CapsNet network model, Wiley, páginas 19-28, 2019 , [Online]. Available: https://doi.org/10.1002/ima.22291spa
dc.relation.referencesFernandes K., Cardoso J., Fernandes J., Automated Methods for the Decision Support of Cervical Cancer Screening Using Digital Colposcopies, IEEE Xplore, Vol. 6, páginas 33910-33927, 2018, [Online]. Available: https://ieeexplore.ieee.org/document/8362613spa
dc.relation.referencesVasudha, Mittal A., Juneja M., Cervix Cancer Classification using Colposcopy Images by Deep Learning Method, IJETSR, Vol. 5, páginas 426-432, 2018, [Online]. Available: https://pdfs.semanticscholar.org/f099/0cd17037129f7a55fcdf279ea6e9d613e8fe.pdfspa
dc.relation.referencesCaraiman S., Vasile I., Histogram-based segmentation of quantum images, ELSEVIER, Vol. 529, páginas 46-60, 2014, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0304397513005835spa
dc.relation.referencesAdrian Rosebrock, pyimagesearch, Keras ImageDataGenerator and Data Augmentation(Julio 8, 2019), consultado por última vez el 10 de octubre del 2019 en: https://www.pyimagesearch.com/2019/07/08/keras-imagedatagenerator-and-data-augmentation/?utm_source=facebook&utm_medium=ad-08-07-2019&utm_campaign=8+July+2019+BP+-+Traffic&utm_content=Default+name+-+Traffic&fbid_campaign=6116019415846&fbid_adset=6116019416246&utm_adset=1+July+2019+BP+-+All+Visitors+90+Days+-+Worldwide+-+18%2B&fbid_ad=6116019417246spa
dc.relation.referencesMikolajczyk A. Grochowski M, Data augmentation for improving deep learning in image classification problem, IEEE Xplore, Poland, 2018, 21 Junio 2018, [Online]. Available: https://ieeexplore.ieee.org/document/8388338spa
dc.relation.referencesIntel & MobileODT, Cervical Cancer Screening, 2017, [Online]. Available: https://www.kaggle.com/c/intel-mobileodt-cervical-cancer-screeningspa
dc.relation.referencesTiago S. Nazar´e, Gabriel B. Paranhos da Costa, Welinton A. Contato, and Moacir Ponti, Deep Convolutional Neural Networks and Noisy Images, ResearchGate, paginas 416-424, 2018, [Online]. Available: https://www.researchgate.net/publication/322915518_Deep_Convolutional_Neural_Networks_and_Noisy_Imagesspa
dc.relation.referencesNawal M. Nour, Cervical Cancer: A Preventable Death, Obstet Gynecol, Vol. 2, páginas 240-244, 2009, [Online]. Available: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2812875/spa
dc.relation.referencesAyan E, H. Muray Ü, Data augmentation importance for classification of skin lesions via deep learning, IEEE Xplore, páginas 1-5, 2019, [Online]. Available: https://ieeexplore.ieee.org/document/8391469/citations?tabFilter=papers#citationsspa
dc.relation.referencesKeras Documentation, Keras, [Online]. Available: https://keras.io/why-use-keras/ [21]. TensorFlow Core r1.14, Tensorflow, [Online]. Available: https://www.tensorflow.org/versions/r1.14/api_docs/python/tfspa
dc.relation.referencesKrizhevsky A., Sutskever I., Hinton G.E. ImageNet Classification with Deep Convolutional Neural Networks. In NIPS, 2012.spa
dc.relation.referencesAbien Fred M. Agarap, Cornell University, Deep Learning using Rectified Linear Units (ReLU), 2019, 7 febrero 2019, [Online]. Available: https://arxiv.org/abs/1803.08375spa
dc.relation.referencesSridhar Narayan, The generalized sigmoid activation function: Competitive supervised learning, ScienceDirect, Vol. 99, páginas 69-82, 1997, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0020025596002009spa
dc.relation.referencesDaniel Godoy, Towards Data Science, Understanding binary cross-entropy / log loss: a visual explanation, 2018, 10 octubre 2019, [Online]. Available: https://towardsdatascience.com/understanding-binary-cross-entropy-log-loss-a-visual-explanation-a3ac6025181aspa
dc.relation.referencesZhang S., Choromanska A., and LeCun Y.. Deep learning with Elastic Averaging SGD. Neural Information Processing Systems Conference (NIPS 2015), Vol. 28, páginas 1–24, 2015, [Online]. Available: https://papers.nips.cc/paper/5761-deep-learning-with-elastic-averaging-sgdspa
dc.relation.referencesPiotr Skalski, Towards Data Science, Preventing Deep Neural Network from Overfitting, 2018, 10 Octubre 2019, [Online]. Available: https://towardsdatascience.com/preventing-deep-neural-network-from-overfitting-953458db800aspa
dc.relation.referencesSrivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R., Dropout: A Simple Way to Prevent Neural Networks from Overfitting, Journal of Machine Learning Research, Vol. 15, páginas. 1929-1958, 2014, [Online]. Available: http://jmlr.org/papers/v15/srivastava14a.htmlspa
dc.rightsRevista EIA - 2020spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.coarhttp://purl.org/coar/access_right/c_abf2spa
dc.rights.creativecommonsEsta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.spa
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0spa
dc.sourcehttps://revistas.eia.edu.co/index.php/reveia/article/view/1462spa
dc.subjectAumento de datosspa
dc.subjectCáncer cervicalspa
dc.subjectRedes neuronales convolucionalesspa
dc.subjectTransferencia de aprendizajespa
dc.subjectdata augmentationeng
dc.subjectcervical cancereng
dc.subjectconvolutional neural networkseng
dc.subjecttransfer learningeng
dc.titleClasificación de cáncer cervical usando redes neuronales convolucionales, transferencia de aprendizaje y aumento de datosspa
dc.title.translatedCervical cancer classification using convolutional neural networks, transfer learning and data augmentationeng
dc.typeArtículo de revistaspa
dc.typeJournal articleeng
dc.type.coarhttp://purl.org/coar/resource_type/c_6501spa
dc.type.coarhttp://purl.org/coar/resource_type/c_6501spa
dc.type.coarversionhttp://purl.org/coar/version/c_970fb48d4fbd8a85spa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/articlespa
dc.type.redcolhttp://purl.org/redcol/resource_type/ARTREFspa
dc.type.versioninfo:eu-repo/semantics/publishedVersionspa
dspace.entity.typePublication
Archivos
Colecciones
Revista EIA (Portal de Revistas)