Programa informático de apoyo para la evaluación del desarrollo de tumores mediante el método RECIST aplicando procesamiento digital de imágenes biomédicas a través de inteligencia artificial

dc.contributor.advisorGelvez Lizarazo, Oscar Mauricio
dc.contributor.advisorFranco Arias, Manuel Hernando
dc.contributor.authorBallesteros Rincón, Johan Steven
dc.contributor.authorGuzmán Trillos, Oskar Daliegt
dc.contributor.cvlacGelvez Lizarazo, Oscar Mauricio [0001342623]
dc.contributor.cvlacFranco Arias, Manuel Hernando [0001427755]
dc.contributor.orcidGelvez Lizarazo, Oscar Mauricio [0000-0001-6858-5293]
dc.contributor.researchgateGelvez Lizarazo, Oscar Mauricio [Oscar-Gelvez-Lizarazo]
dc.coverage.campusUNAB Campus Bucaramangaspa
dc.coverage.spatialBucaramanga (Santander, Colombia)spa
dc.date.accessioned2023-02-08T22:40:55Z
dc.date.available2023-02-08T22:40:55Z
dc.date.issued2022
dc.degree.nameIngeniero Biomédicospa
dc.description.abstractEl presente proyecto comprende el desarrollo de un programa informático de apoyo para la evaluación del desarrollo de tumores mediante el método RECIST aplicando procesamiento digital de imágenes biomédicas, a fin de secundar el diagnóstico del especialista en salud según los criterios del método ya mencionado. En cumplimiento del objetivo principal, se realizó el entrenamiento de una inteligencia artificial a través de redes neuronales convolucionales (CNN), la cual fue entrenada por medio de tomografías computacionales (CT) y máscaras de segmentación correspondientes al hígado, obtenidas de la base de datos del Decatlón de segmentación médica (MSD), así como el respectivo desarrollo de una interfaz gráfica de usuario (GUI) en la que se implementaron los criterios correspondientes a RECIST 1.1, todo realizado en el lenguaje de código abierto Python, con lo que se obtuvo una exactitud del 97,21%.spa
dc.description.abstractenglishThis project includes the development of a support computer program for the evaluation of tumor development through the RECIST method applying digital processing of biomedical images, in order to support the diagnosis of the health specialist according to the criteria of the aforementioned method. In compliance with the main objective, the training of an artificial intelligence was carried out through convolutional neural networks (CNN), which was trained by means of computed tomography (CT) and segmentation masks corresponding to the liver, obtained from the database of the Medical Segmentation Decathlon (MSD), as well as the respective development of a graphical user interface (GUI) in which the criteria corresponding to RECIST 1.1 were implemented, all carried out in the open source language Python, with which it was obtained an accuracy of 97.21%.spa
dc.description.degreelevelPregradospa
dc.description.learningmodalityModalidad Presencialspa
dc.description.tableofcontentsLista de contenido Resumen ......................................................................................................................................... 2 Abstract .......................................................................................................................................... 3 Agradecimientos ............................................................................................................................ 4 Lista de contenido ......................................................................................................................... 6 Lista de imágenes .......................................................................................................................... 9 Lista de tablas .............................................................................................................................. 11 Lista de ecuaciones ...................................................................................................................... 12 Lista de diagramas ...................................................................................................................... 13 Lista de gráficas .......................................................................................................................... 14 Capítulo 1 ..................................................................................................................................... 17 1.1. Planteamiento del problema .................................................................................................... 17 1.2. Justificación del problema ....................................................................................................... 18 1.3. Pregunta de investigación ........................................................................................................ 20 1.4. Objetivos ................................................................................................................................... 20 1.4.1. Objetivo general ..................................................................................................................... 20 1.4.2. Objetivos específicos .............................................................................................................. 20 Capítulo 2 ..................................................................................................................................... 21 2.1. Marco teórico ............................................................................................................................ 21 2.1.1. Evaluación en respuesta tumoral ........................................................................................... 21 2.1.1.1. RECIST .......................................................................................................................... 21 2.1.2. Imágenes médicas ................................................................................................................... 22 2.1.2.1. Técnicas de adquisición de imágenes médicas ............................................................... 22 2.1.2.1.1. Imágenes por resonancia magnética (MRI) ............................................................ 22 7 2.1.2.1.2. Tomografías computarizadas (CT) ......................................................................... 22 2.1.3. Inteligencia artificial – IA ...................................................................................................... 23 2.1.3.1. Machine Learning ........................................................................................................... 23 2.1.3.1.1. Deep Learning ........................................................................................................ 23 2.1.3.1.2. Redes Neuronales Convolucionales (CNN) ............................................................ 23 2.1.4. Procesamiento de imágenes ................................................................................................... 23 2.1.4.1. Segmentación .................................................................................................................. 24 2.2. Marco legal ............................................................................................................................... 24 2.3. Estado del arte .......................................................................................................................... 26 Capítulo 3 ..................................................................................................................................... 30 3.1. Etapa 1. Definición de requerimientos ................................................................................... 30 3.1.1. Criterios RECIST.................................................................................................................... 30 3.1.2. Obtención de la base de datos ................................................................................................ 33 3.2. Etapa 2. Diseño del software ................................................................................................... 38 3.2.1. Selección del lenguaje de programación ................................................................................ 38 3.2.2. Entrenamiento de la inteligencia artificial ............................................................................. 40 3.2.2.1. Redes neuronales convolucionales (CNN) ..................................................................... 40 3.2.2.2. Visualización máscaras de predicción ............................................................................ 46 3.2.2.3. Evaluación del modelo de segmentación. ....................................................................... 48 3.2.3. Diseño del aplicativo .............................................................................................................. 51 3.3. Etapa 3. Evaluación del software ............................................................................................ 55 Capítulo 4 ..................................................................................................................................... 63 4.1. Presentación de resultados ...................................................................................................... 63 4.1.1. Diseño del software ................................................................................................................ 63 4.1.2. Evaluación del software ......................................................................................................... 64 4.2. Análisis de resultados ............................................................................................................... 77 4.2.1. Diseño del software ................................................................................................................ 77 8 4.2.2. Evaluación del software ......................................................................................................... 79 Capítulo 5 ..................................................................................................................................... 81 5.1. Conclusiones ............................................................................................................................. 81 5.2. Recomendaciones ..................................................................................................................... 82 REFERENCIAS .......................................................................................................................... 84 ANEXOS ...................................................................................................................................... 90 a) Anexo 1. Carta de soporte del especialista…………………………………………………………..90 b) Anexo 2. Manual de Usuario………………………………………………………………………...91 c) Anexo 3. Guía de manejo rápido…………………………………………………………………….92spa
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/20.500.12749/18965
dc.language.isospaspa
dc.publisher.facultyFacultad Ingenieríaspa
dc.publisher.grantorUniversidad Autónoma de Bucaramanga UNABspa
dc.publisher.programPregrado Ingeniería Biomédicaspa
dc.relation.referencesAntonelli, M., Reinke, A., Bakas, S., Farahani, K., Kopp-Schneider, A., Landman, B. A., Litjens, G., Menze, B., Ronneberger, O., Summers, R. M., van Ginneken, B., Bilello, M., Bilic, P., Christ, P. F., Do, R. K. G., Gollub, M. J., Heckers, S. H., Huisman, H., Jarnagin, W. R., … Cardoso, M. J. (2022a). The Medical Segmentation Decathlon. Nature Communications 2022 13:1, 13(1), 1–13. https://doi.org/10.1038/s41467-022-30695-9spa
dc.relation.referencesAntonelli, M., Reinke, A., Bakas, S., Farahani, K., Kopp-Schneider, A., Landman, B. A., Litjens, G., Menze, B., Ronneberger, O., Summers, R. M., van Ginneken, B., Bilello, M., Bilic, P., Christ, P. F., Do, R. K. G., Gollub, M. J., Heckers, S. H., Huisman, H., Jarnagin, W. R., … Cardoso, M. J. (2022b). The Medical Segmentation Decathlon. Nature Communications, 13(1). https://doi.org/10.1038/S41467-022-30695-9spa
dc.relation.referencesBali, M. A., Pullini, S., Metens, T., Absil, J., Chao, S.-L., Marechal, R., Matos, C., Peerboccus, B. M., & van Laethem, J.-L. (2018). Assessment of response to chemotherapy in pancreatic ductal adenocarcinoma: Comparison between diffusion-weighted MR quantitative parameters and RECIST. European Journal of Radiology, 104, 49–57. https://doi.org/10.1016/j.ejrad.2018.04.024spa
dc.relation.referencesCancer Today. (n.d.). Retrieved April 4, 2022, from https://gco.iarc.fr/today/online-analysismap?v=2020&mode=population&mode_population=continents&population=900&populations=900&key=asr&sex=0&cancer=39&type=0&statistic=5&prevalence=0&population_group=0&ages_group%5B%5D=0&ages_group%5B%5D=17&nb_items=10&group_cancer=1&include_nmsc=0&include_nmsc_other=0&projection=naturalearth&color_palette=default&map_sca 85 le=quantile&map_nb_colors=5&continent=0&show_ranking=0&rotate=%255B10%252C0%25Dspa
dc.relation.referencesCarreño-Dueñas, J. A., Sánchez, J. O., Bermúdez-Silva, C. D., & Mesa, M. (2014). Errores en la formulación de quimioterapia. Revista Colombiana de Cancerología, 18(4), 179–185. https://doi.org/10.1016/j.rccan.2014.08.003spa
dc.relation.referencesCervera Deval, J. (2014a). RECIST y el radiólogo. Radiología, 56(3), 193–205. https://doi.org/10.1016/J.RX.2012.03.010spa
dc.relation.referencesCommon Cancer Types - NCI. (n.d.-a). Retrieved November 22, 2022, from https://www.cancer.gov/types/common-cancersspa
dc.relation.referencesCT-ORG: CT volumes with multiple organ segmentations - The Cancer Imaging Archive (TCIA) Public Access - Cancer Imaging Archive Wiki. (n.d.). Retrieved April 27, 2022, from https://wiki.cancerimagingarchive.net/display/Public/CTORG%3A+CT+volumes+with+multiple+organ+segmentationsspa
dc.relation.referencesDecreto 1360 de 1989 - Gestor Normativo - Función Pública. (n.d.). Retrieved April 27, 2022, from https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=10575spa
dc.relation.referencesDecreto 1474 de 2002 Nivel Nacional. (n.d.). Retrieved May 5, 2022, from https://www.alcaldiabogota.gov.co/sisjur/normas/Norma1.jsp?i=6076&dt=Sspa
dc.relation.referencesFenerty, K. E., Folio, L. R., Patronas, N. J., Marté, J. L., Gulley, J. L., & Heery, C. R. (2016). Predicting clinical outcomes in chordoma patients receiving immunotherapy: a 86 comparison between volumetric segmentation and RECIST. BMC Cancer, 16(1), 672. https://doi.org/10.1186/s12885-016-2699-xspa
dc.relation.referencesGambino, O., Vitabile, S., lo Re, G., la Tona, G., Librizzi, S., Pirrone, R., Ardizzone, E., & Midiri, M. (2010). Automatic Volumetric Liver Segmentation Using Texture Based Region Growing. 2010 International Conference on Complex, Intelligent and Software Intensive Systems, 146–152. https://doi.org/10.1109/CISIS.2010.118spa
dc.relation.referencesHistory and License — Python 3.10.4 documentation. (n.d.). Retrieved April 27, 2022, from https://docs.python.org/3/license.htmlspa
dc.relation.referencesIntroduction to Magnetic Resonance Imaging (MRI). (n.d.). Retrieved April 4, 2022, from https://www.maximintegrated.com/en/design/technical-documents/tutorials/4/4681.htmlspa
dc.relation.referencesLey 23 de 1982 - Gestor Normativo - Función Pública. (n.d.). Retrieved April 27, 2022, from https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=3431spa
dc.relation.referencesLey 44 de 1993 Nivel Nacional. (n.d.). Retrieved May 5, 2022, from https://www.alcaldiabogota.gov.co/sisjur/normas/Norma1.jsp?i=3429spa
dc.relation.referencesMedical Image Segmentation. (n.d.). Retrieved April 4, 2022, from https://www5.cs.fau.de/research/groups/medical-image-segmentation/index.htmlspa
dc.relation.referencesMedical Imaging | FDA. (n.d.). Retrieved April 4, 2022, from https://www.fda.gov/radiation-emittingproducts/radiation-emitting-products-and-procedures/medical-imagingspa
dc.relation.referencesMoltz, J. hendrik, Bornemann, L., Dicken, V., & Peitgen, H.-O. (2008). Segmentation of Liver Metastases in CT Scans by Adaptive Thresholding and Morphological Processing. The MIDAS Journal. https://doi.org/10.54294/msg94uspa
dc.relation.references¿Qué es inteligencia artificial? | IBM. (n.d.). Retrieved April 4, 2022, from https://www.ibm.com/coes/analytics/journey-to-aispa
dc.relation.referencesRECIST. (n.d.). Retrieved April 4, 2022, from https://recist.eortc.org/spa
dc.relation.referencesRECIST 1.1 - Calyx Informatics. (n.d.). Retrieved April 4, 2022, from https://www.recist.com/recist/recist-inpractice/01.phpspa
dc.relation.referencesSegmentación de imágenes - MATLAB & Simulink - MathWorks América Latina. (n.d.). Retrieved May 5, 2022, from https://la.mathworks.com/help/images/image-segmentation.htmlspa
dc.relation.referencesSeo, H., Huang, C., Bassenne, M., Xiao, R., & Xing, L. (2020). Modified U-Net (mU-Net) With Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images. IEEE Transactions on Medical Imaging, 39(5), 1316–1325. https://doi.org/10.1109/TMI.2019.2948320spa
dc.relation.referencesShanbhogue, A. K. P., Karnad, A. B., & Prasad, S. R. (2010). Tumor Response Evaluation in Oncology. Journal of Computer Assisted Tomography, 34(4), 479–484. https://doi.org/10.1097/RCT.0b013e3181db2670
dc.relation.referencesSICE - Comunidad Andina - Decisión 351. (n.d.). Retrieved April 27, 2022, from http://www.sice.oas.org/trade/junac/decisiones/dec351s.asp
dc.relation.referencesTan, M., Li, Z., Qiu, Y., McMeekin, S. D., Thai, T. C., Ding, K., Moore, K. N., Liu, H., & Zheng, B. (2015). A New Approach to Evaluate Drug Treatment Response of Ovarian Cancer Patients Based on Deformable Image Registration. IEEE Transactions on Medical Imaging, 35(1), 316–325. https://doi.org/10.1109/TMI.2015.2473823
dc.relation.referencesTaner, A., Öztekin, Y. B., & Duran, H. (2021). Performance analysis of deep learning cnn models for variety classification in Hazelnut. Sustainability (Switzerland), 13(12). https://doi.org/10.3390/SU13126527
dc.relation.referencesTang, Y., Tang, Y., Zhu, Y., Xiao, J., & Summers, R. M. (2020). E$^2$Net: An Edge Enhanced Network for Accurate Liver and Tumor Segmentation on CT Scans. http://arxiv.org/abs/2007.09791
dc.relation.referencesTorchIO. (n.d.). Retrieved November 22, 2022, from https://torchio.readthedocs.io/index.html
dc.relation.referencesWhat is Deep Learning? | IBM. (n.d.). Retrieved April 4, 2022, from https://www.ibm.com/cloud/learn/deeplearning
dc.relation.referencesWhat Is Diagnostic Imaging? - Health Images. (n.d.). Retrieved April 4, 2022, from https://www.healthimages.com/what-is-diagnostic-imaging/
dc.relation.referencesWhat is Machine Learning? | IBM. (n.d.). Retrieved April 4, 2022, from https://www.ibm.com/cloud/learn/machine-learning
dc.relation.referencesZhang, X., Tian, J., Deng, K., Wu, Y., & Li, X. (2010). Automatic Liver Segmentation Using a Statistical Shape Model With Optimal Surface Detection. IEEE Transactions on Biomedical Engineering, 57(10), 2622–2626. https://doi.org/10.1109/TBME.2010.2056369
dc.relation.referencesZhang, Y., Peng, C., Peng, L., Xu, Y., Lin, L., Tong, R., Peng, Z., Mao, X., Hu, H., Chen, Y.-W., & Li, J. (2021). DeepRecS: From RECIST Diameters to Precise Liver Tumor Segmentation. IEEE Journal of Biomedical and Health Informatics, 26(2), 614–625. https://doi.org/10.1109/JBHI.2021.3091900
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.keywordsBiomedical engineeringspa
dc.subject.keywordsEngineeringspa
dc.subject.keywordsMedical electronicsspa
dc.subject.keywordsBiological physicsspa
dc.subject.keywordsBioengineeringspa
dc.subject.keywordsMedical instruments and apparatusspa
dc.subject.keywordsMedicinespa
dc.subject.keywordsBiomedicalspa
dc.subject.keywordsClinical engineeringspa
dc.subject.keywordsCancer treatmentsspa
dc.subject.keywordsLiver tumorsspa
dc.subject.keywordsBiomedical imagingspa
dc.subject.lembIngeniería biomédicaspa
dc.subject.lembIngenieríaspa
dc.subject.lembBiofísicaspa
dc.subject.lembBioingenieríaspa
dc.subject.lembMedicinaspa
dc.subject.lembBiomédicaspa
dc.subject.proposalIngeniería clínicaspa
dc.subject.proposalElectrónica médicaspa
dc.subject.proposalInstrumentos y aparatos médicosspa
dc.subject.proposalTratamientos oncológicosspa
dc.subject.proposalTumores hepáticosspa
dc.subject.proposalImágenes biomédicasspa
dc.titlePrograma informático de apoyo para la evaluación del desarrollo de tumores mediante el método RECIST aplicando procesamiento digital de imágenes biomédicas a través de inteligencia artificialspa
dc.title.translatedSupport computer program for the evaluation of tumor development through the RECIST method applying digital processing of biomedical images through artificial intelligencespa
dc.type.coarhttp://purl.org/coar/resource_type/c_7a1f
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.driverinfo:eu-repo/semantics/bachelorThesis
dc.type.hasversioninfo:eu-repo/semantics/acceptedVersion
dc.type.localTrabajo de Gradospa
dc.type.redcolhttp://purl.org/redcol/resource_type/TP

Archivos

Bloque original

Mostrando 1 - 5 de 5
Cargando...
Miniatura
Nombre:
2022_Tesis_Johan_Steven_Ballesteros_Rincón - Oskar_Daliegt_Guzmán_Trillos.pdf
Tamaño:
1.86 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis
Cargando...
Miniatura
Nombre:
2022_Licencia_Johan_Steven_Ballesteros_Rincón.pdf
Tamaño:
126.63 KB
Formato:
Adobe Portable Document Format
Descripción:
Licencia
Cargando...
Miniatura
Nombre:
2022_Licencia_Oskar_Daliegt_Guzmán_Trillos.pdf
Tamaño:
125.63 KB
Formato:
Adobe Portable Document Format
Descripción:
Licencia
Cargando...
Miniatura
Nombre:
2022_Guia_Johan_Steven_Ballesteros_Rincón - Oskar_Daliegt_Guzmán_Trillos.pdf
Tamaño:
135.08 KB
Formato:
Adobe Portable Document Format
Descripción:
Guia
Cargando...
Miniatura
Nombre:
2022_Manual_Johan_Steven_Ballesteros_Rincón - Oskar_Daliegt_Guzmán_Trillos.pdf
Tamaño:
568.41 KB
Formato:
Adobe Portable Document Format
Descripción:
Manual

Bloque de licencias

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