DeepSARS: Sistema de aprendizaje profundo automático para la identificación temprana y seguimiento de pacientes con riesgo de síndrome de distrés respiratorio agudo

Vista sencilla de ítem
dc.contributor.authorMartínez Carrillo, Fabio
dc.contributor.cvlacMartínez Carrillo, Fabio [0000738018]spa
dc.contributor.googlescholarMartínez Carrillo, Fabio [es&oi=ao]spa
dc.coverage.campusUNAB Campus Bucaramangaspa
dc.coverage.spatialBucaramanga (Santander, Colombia)spa
dc.date.accessioned2023-08-31T19:20:07Z
dc.date.available2023-08-31T19:20:07Z
dc.date.issued2020
dc.description.abstractEl sistema DeepSARS fue propuesto y desarrollado con el propósito de asistir la identificación temprana y seguimiento de pacientes con riesgo de síndrome de distrés respiratorio agudo producido por COVID-19. Principalmente, el sistema realiza el aprendizaje profundo de patrones visuales relevantes para identificar COVID-19 sobre estudios radiológicos de tórax, digitalizados en secuencias de Tomografía Computarizada (CT) y Rayos X (Rx). Durante el desarrollo del proyecto se lograron desarrollar con éxito un total de 9 modelos, con diferentes propósitos, y codificados para operar en los dos tipos de imágenes radiológicas. Estos modelos realizan las siguientes tareas: detectar si un estudio presenta COVID-19 teniendo en cuenta información 2D o 3D, extraer hallazgos o regiones relevantes donde está expresada la enfermedad, y clasificar si un estudio presenta síndrome respiratorio agudo. Adicionalmente, se desarrollaron dos modelos, uno multimodal que usa los síntomas y signos presentados por el paciente para mejorar la detección de casos con COVID-19, y el modelo restante que estratifica el grado de compromiso o evolución del COVID-19 sobre el estudio radiológico de un paciente.spa
dc.description.abstractenglishThe DeepSARS system was proposed and developed with the purpose of assisting the early identification and monitoring of patients at risk of acute respiratory distress syndrome caused by COVID-19. Mainly, the system performs deep learning of relevant visual patterns to identify COVID-19 on chest radiological studies, digitized in Computed Tomography (CT) and X-ray (Rx) sequences. During the development of the project, a total of 9 models were successfully developed, with different purposes, and coded to operate in the two types of radiological images. These models perform the following tasks: detect whether a study presents COVID-19 taking into account 2D or 3D information, extract relevant findings or regions where the disease is expressed, and classify whether a study presents acute respiratory syndrome. Additionally, two models were developed, a multimodal one that uses the symptoms and signs presented by the patient to improve the detection of cases with COVID-19, and the remaining model that stratifies the degree of compromise or evolution of COVID-19 on the radiological study. of a patient.spa
dc.description.learningmodalityModalidad Presencialspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameinstname:Universidad Autónoma de Bucaramanga - UNABspa
dc.identifier.reponamereponame:Repositorio Institucional UNABspa
dc.identifier.repourlrepourl:https://repository.unab.edu.cospa
dc.identifier.urihttp://hdl.handle.net/20.500.12749/21582
dc.language.isospaspa
dc.publisher.facultyFacultad Ciencias de la Saludspa
dc.publisher.grantorUniversidad Autónoma de Bucaramanga UNABspa
dc.relation.references1: Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (pp. 91-99)spa
dc.relation.references2: Salvador, A., Giró-i-Nieto, X., Marqués, F., & Satoh, S. I. (2016). Faster r-cnn features for instance search. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 9-16).spa
dc.relation.references3: Boyd, K., Eng, K. H., & Page, C. D. (2013, September). Area under the precision-recall curve: point estimates and confidence intervals. In Joint European conference on machine learning and knowledge discovery in databases (pp. 451-466). Springer, Berlin, Heidelberg.spa
dc.relation.references4: Wang, Z., Simoncelli, E. P., & Bovik, A. C. (2003, November). Multiscale structural similarity for image quality assessment. In The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 (Vol. 2, pp. 1398-1402). Ieee.spa
dc.relation.references5: Horadam, K. J., & Nyblom, M. A. (2014). Distances between sets based on set commonality. Discrete Applied Mathematics, 167, 310-314spa
dc.relation.references6: Kermack, William Ogilvy, A. G. McKendrick, and Gilbert Thomas Walker. “A Contribution to the Mathematical Theory of Epidemics.” Proceedings of the Royal Society of London. Series A, Containing Papers of a Mathematical and Physical Character 115, no. 772 (August 1, 1927): 700–721. https://doi.org/10.1098/rspa.1927.0118spa
dc.relation.references7: Li, Qun, Xuhua Guan, Peng Wu, Xiaoye Wang, Lei Zhou, Yeqing Tong, Ruiqi Ren, et al. “Early Transmission Dynamics in Wuhan, China, of Novel Coronavirus–Infected Pneumonia.” New England Journal of Medicine 382, no. 13 (March 26, 2020): 1199–1207. https://doi.org/10.1056/NEJMoa2001316spa
dc.relation.references8: Chen, Tian-Mu, Jia Rui, Qiu-Peng Wang, Ze-Yu Zhao, Jing-An Cui, and Ling Yin. “A Mathematical Model for Simulating the Phase-Based Transmissibility of a Novel Coronavirus.” Infectious Diseases of Poverty 9, no. 1 (February 28, 2020): 24. https://doi.org/10.1186/s40249-020-00640-3.spa
dc.relation.references9: Korolev, Ivan. “Identification and Estimation of the SEIRD Epidemic Model for COVID-19.” Journal of Econometrics, July 30, 2020. https://doi.org/10.1016/j.jeconom.2020.07.038.spa
dc.relation.references10: “Monitoring Italian COVID-19 Spread by a Forced SEIRD Model.” Accessed November 11, 2020. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7410324/spa
dc.relation.references11: “A Conceptual Model for the Coronavirus Disease 2019 (COVID-19) Outbreak in Wuhan, China with Individual Reaction and Governmental Action - International Journal of Infectious Diseases.” Accessed November 11, 2020. https://www.ijidonline.com/article/S1201-9712(20)30117-X/fulltextspa
dc.relation.references12: “Phase-Adjusted Estimation of the Number of Coronavirus Disease 2019 Cases in Wuhan, China | Cell Discovery.” Accessed November 11, 2020. https://www.nature.com/articles/s41421-020-0148-0.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.creativecommonsAtribución-NoComercial-SinDerivadas 2.5 Colombia*
dc.rights.localAbierto (Texto Completo)spa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.5/co/*
dc.subject.keywordsDeep learning modelsspa
dc.subject.keywordsChest imagingspa
dc.subject.keywordsAdult respiratory distress syndromespa
dc.subject.keywordsRespiratory insufficiencyspa
dc.subject.keywordsRespiratory diseasesspa
dc.subject.keywordsBreathing disordersspa
dc.subject.lembSíndrome de distrés respiratorio de adultosspa
dc.subject.lembInsuficiencia respiratoriaspa
dc.subject.lembEnfermedades respiratoriasspa
dc.subject.lembTrastornos de la respiraciónspa
dc.subject.proposalModelos de aprendizaje profundospa
dc.subject.proposalImágenes torácicasspa
dc.titleDeepSARS: Sistema de aprendizaje profundo automático para la identificación temprana y seguimiento de pacientes con riesgo de síndrome de distrés respiratorio agudospa
dc.title.translatedDeepSARS: Automatic deep learning system for early identification and tracking of patients at risk of acute respiratory distress syndromespa
dc.typeResearch reporteng
dc.type.coarhttp://purl.org/coar/resource_type/c_18ws
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.driverinfo:eu-repo/semantics/workingPaperspa
dc.type.hasversioninfo:eu-repo/semantics/acceptedVersionspa
dc.type.localInforme de investigaciónspa
dc.type.redcolhttp://purl.org/redcol/resource_type/IFIspa

Archivos

Bloque original

Mostrando 1 - 2 de 2
Miniatura
Nombre:
Informe.pdf
Tamaño:
934.84 KB
Formato:
Adobe Portable Document Format
Descripción:
Informe
Descargar
Miniatura
Nombre:
Licencia.pdf
Tamaño:
1.71 MB
Formato:
Adobe Portable Document Format
Descripción:
Licencia
Descargar

Bloque de licencias

Mostrando 1 - 1 de 1
Miniatura
Nombre:
license.txt
Tamaño:
829 B
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar

Colecciones

Informes de investigación