A Data-driven Representation Learning for Tumor Tissue Differentiation from Non-Small Cell Lung Cancer Histopathology Images

dc.contributor.advisorRomero Castro, Eduardo
dc.contributor.advisorCruz Roa, Angel Alfonso
dc.contributor.authorCano Ramirez, Fabian Alberto
dc.contributor.cvlacCano, Fabian [https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000183272]spa
dc.contributor.orcidCano, Fabian [0000-0003-3272-8701]spa
dc.contributor.researchgroupCim@Labspa
dc.date.accessioned2023-08-23T13:59:59Z
dc.date.available2023-08-23T13:59:59Z
dc.date.issued2022
dc.descriptionilustraciones, diagramasspa
dc.description.abstractLung cancer is the second most common type and the leading cause of cancer death in the world. It is divided into different types according to cellular and tissular features, and in turn, these types are distinguished by typical patterns that represent them. Each histological subtype of lung cancer is associated with the prognosis and treatment of patients, and is subjectively stratified mainly by its morphological features. However, due to the very nature of the disease, this stratification varies since there is no specialized grading system, and also because of the difficulty of characterizing cases that generally contain mixtures of histological patterns and unspecified tissues, which therefore, alters the diagnosis and prognosis of patients. This research work addresses a computational data-driven strategy to characterize histological patterns of lung cancer, in addition to determining its differentiation and aggressiveness, in order to support decision-making in clinical practice. Therefore, this work has been divided in two parts. The first part presents a supervised subtype differentiation learning of lung cancer features in a latent space constructed with a variational autoencoder. In such space, complicated patterns are quantified by estimating a differentiation grade of typical encoded features of lung cancer subtypes. Then, a logistic regression model assigns differentiation cancer subtype grade to the embedded tissue samples. This approach builds up a subtype differentiation grade of non-small cell lung cancer among complex structures which are fully interpretable and integrable with a pathology workflow. Finally, the second part presents an unsupervised computational approach based on an ensemble of tissue-specialized variational autoencoders, which were trained per histopathology subtype, to build an unsupervised embedded tissue-image representation. This representation was used to train a Random Forest classifier of three lung adenocarcinoma histology subtypes (lepidic, papillary and solid), and a 2D-visually interpretable projection from the learned embedded representation. (Texto tomado de la fuente)eng
dc.description.abstractEl cáncer de pulmón es el segundo tipo más común y la principal causa de muerte por cáncer en el mundo. Se divide en diferentes tipos según las características celulares y tisulares, y a su vez, estos tipos se distinguen por los patrones histológicos típicos que los representan. Cada subtipo histológico de cáncer de pulmón se asocia con el pronóstico y tratamiento de los pacientes, y se estratifica subjetivamente por parte de los patólogos principalmente por sus características morfológicas. Sin embargo, por la propia naturaleza de la enfermedad, esta estratificación varía ya que no existe un sistema de gradación especializado, y también por la dificultad de caracterizar los casos que generalmente contienen mezclas de patrones histológicos y tejidos no especificados, lo que puede afectar la precisión del diagnóstico y pronóstico de los pacientes. Este trabajo de investigación aborda una estrategia computacional basada en datos para caracterizar los patrones histológicos del cáncer de pulmón, además de determinar su diferenciación y agresividad, con el fin de apoyar la toma de decisiones en la práctica clínica. Por ello, este trabajo se ha dividido en dos partes. La primera parte presenta un aprendizaje supervisado de diferenciación de subtipos de características de cáncer de pulmón en un espacio latente construido con un autocodificador variacional. En dicho espacio, los patrones complejos se cuantifican mediante la estimación de un grado de diferenciación de las características codificadas típicas de los subtipos de cáncer de pulmón. Luego, un modelo de regresión logística asigna un grado de diferenciación del subtipo de cáncer a las muestras de tejido codificadas. Este enfoque construye un grado de diferenciación de subtipos de cáncer de pulmón de células no pequeñas entre estructuras complejas que son totalmente interpretables e integrables con un flujo de trabajo de patología. Finalmente, la segunda parte presenta un enfoque computacional no supervisado basado en un conjunto de codificadores automáticos variacionales especializados en tejidos, que fueron entrenados por subtipo de histopatología, para construir una representación de imagen de tejido codificada no supervisada. Esta representación se usó para entrenar un clasificador Random Forest para distinguir entre tres subtipos histológicos de adenocarcinoma de pulmón (lepídico, papilar y sólido) y una proyección visualmente interpretable en 2D a partir de la representación incrustada aprendida.spa
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ingeniería Biomédicaspa
dc.description.researchareaIngeniería Biomédicaspa
dc.format.extentxv, 46 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.repoRepositorio Institucional Universidad Nacional de Colombia
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/84587
dc.language.isoengspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotáspa
dc.publisher.facultyFacultad de Medicinaspa
dc.publisher.placeBogotá, Colombiaspa
dc.publisher.programBogotá - Medicina - Maestría en Ingeniería Biomédicaspa
dc.relation.referencesV. Moctezuma and Z. Patiño, “Cáncer de pulmón,” Anales de Radiología México, vol. 8, pp. 33–45, 2009.spa
dc.relation.referencesE. Bender, “Epidemiology: The dominant malignancy,” Nature, vol. 513, pp. 52–53, 2014.spa
dc.relation.referencesE. Kuhn, P. Morbini, and et. al., “Adenocarcinoma classification: patterns and prognosis,” Pathologica, vol. 110, pp. 5–11, 2018.spa
dc.relation.referencesC. Underwood, A. Musick, and C. Glass, “Adenocarcinoma overview.” https://www.pathologyoutlines.com/topic/lungtumoradenocarcinoma.html, 2019. Online; accessed Jun 2022.spa
dc.relation.referencesJ. Rocca, “Understanding variational autoencoders (vaes).” https://towardsdatascience.com/understanding-variational-autoencoders-vaes- f70510919f73, 2019. Online; accessed Nov 2022.spa
dc.relation.referencesA. Moreira, P. Ocampo, Y. Xia, and et. al., “A grading system for invasive pulmonary adenocarcinoma: A proposal from the international association for the study of lung cancer pathology committee,” J Thorac Oncol, vol. 15(10), pp. 1599–1610, 2020.spa
dc.relation.referencesM. Amin and et. al., AJCC Cancer Staging Manual. 8th ed. New York, NY.: Springer, 2017.spa
dc.relation.referencesH. Sung, J. Ferlay, R. L. Siegel, M. Laversanne, I. Soerjomataram, A. Jemal, and F. Bray, “Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries.,” CA: a cancer journal for clinicians, vol. 71(3), p. 209–249, 2021.spa
dc.relation.referencesM. Sˇuti ́c, A. Vuki ́c, J. Baranaˇsi ́c, A. Fo ̈rsti, F. Dˇzubur, M. Samarˇzija, and et al., “Diagnostic, predictive, and prognostic biomarkers in non-small cell lung cancer (nsclc) management,” J Pers Med., vol. 11, p. 1102, 2021.spa
dc.relation.referencesR. Wilson, A. Ryerson, K. Zhang, and D. X., “Relative survival analysis using the centers for disease control and prevention’s national program of cancer registries surveil- lance system data, 2000-2007,” Journal of registry management, vol. 41, p. 72, 2014.spa
dc.relation.referencesS. Blandin Knight, P. Crosbie, and et. al., “Progress and prospects of early detection in lung cancer,” Open biology, vol. 7, 2017.spa
dc.relation.referencesZ. Wang, M. Li, and et. al., “Clinical and radiological characteristics of central pulmonary adenocarcinoma: a comparison with central squamous cell carcinoma and small cell lung cancer and the impact on treatment response,” OncoTargets and therapy 2018, vol. 11, 2018.spa
dc.relation.referencesL. Osmani, F. Askin, E. Gabrielson, and Q. Li, “Current who guidelines and the critical role of immunohistochemical markers in the subclassification of non-small cell lung carcinoma (nsclc): Moving from targeted therapy to immunotherapy,” Semin Cancer Biol, vol. 52, p. 103–9, 2018.spa
dc.relation.referencesN. Coudray and et. al., “Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning,” Nature Medicine, vol. 24, pp. 1559– 1567, 2018.spa
dc.relation.referencesV. S. Viswanathan, P. Toro, and et. al., “The state of the art for artificial intelligence in lung digital pathology,” The Journal of pathology, vol. Advance online publication, 2022.spa
dc.relation.referencesC. Zappa and S. A. Mousa, “Non-small cell lung cancer: current treatment and future advances,” Translational lung cancer research, vol. 5, pp. 288–300, 2016.spa
dc.relation.referencesP. Bolaños and C. Chacón, “Escala patológica de gleason para el cáncer de prostata y sus modificaciones,” Medicina Legal de Costa Rica, vol. 34, pp. 237–243, 2017.spa
dc.relation.referencesW. Travis, E. Brambilla, and K. Geisinger, “Histological grading in lung cancer: one system for all or separate systems for each histological type?,” European Respiratory Journal, vol. 47, pp. 720–723, 2016.spa
dc.relation.referencesA. Gertych, Z. Swiderska-Chadaj, and et. al., “Convolutional neural networks can accurately distinguish four histologic growth patterns of lung adenocarcinoma in digital slides,” Sci Rep, vol. 9, p. 1483, 2019.spa
dc.relation.referencesJ. Wei, L. Tafe, and Y. e. a. Linnik, “Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks,” Sci Rep, vol. 9, p. 3358, 2019.spa
dc.relation.referencesM. Davidson, A. Gazdar, and B. Clarke, “The pivotal role of pathology in the management of lung cancer,” J Thorac Dis, vol. 5, 2013.spa
dc.relation.referencesP. Russell, Z. Wainer, G. Wright, M. Daniels, M. Conron, and R. Williams, “Does lung adenocarcinoma subtype predict patient survival?: A clinicopathologic study based on the new international association for the study of lung cancer/american thoracic society/european respiratory society international multidisciplinary lung adenocarcinoma classification,” J Thorac Oncol, vol. 6, pp. 1496–1504, 2011.spa
dc.relation.referencesS. Wang, A. Chen, L. Yang, and et. al., “Comprehensive analysis of lung cancer pathology images to discover tumor shape and boundary features that predict survival out- come,” Sci Rep, vol. 8, p. 10393, 2018.spa
dc.relation.referencesM. Van Bockstal, M. Berlière, F. Duhoux, and C. Galant, “Interobserver variability in ductal carcinoma in situ of the breast,” J Clin Pathol, vol. 154, pp. 596–609, 2020.spa
dc.relation.referencesS. Zachara-Szczakowski, T. Verdun, and A. Churg, “Accuracy of classifying poorly differentiated non–small cell lung carcinoma biopsies with commonly used lung carcinoma markers,” Hum Pathol, vol. 46, pp. 776–782, 2015.spa
dc.relation.referencesM. Connor, G. Canal, and C. Rozell, “Classification and pathology of lung cancer,” Surgical Oncology Clinics, vol. 25, pp. 447–468, 2016.spa
dc.relation.referencesE. Ruffini, O. Rena, and et. al., “Lung tumors with mixed histologic pattern. clinicopathologic characteristics and prognostic significance,” European Journal of Cardio- Thoracic Surgery, vol. 22, p. 701–707, 2002.spa
dc.relation.referencesJ. Qin and H. Lu, “Combined small-cell lung carcinoma,” OncoTargets and therapy, vol. 11, p. 3505–3511, 2018.spa
dc.relation.referencesW. D. Travis, E. Brambilla, M. Noguchi, A. G. Nicholson, K. R. Geisinger, Y. Yatabe, D. G. Beer, C. A. Powell, G. J. Riely, P. E. Van Schil, K. Garg, J. H. Austin, H. Asamura, V. W. Rusch, F. R. Hirsch, G. Scagliotti, T. Mitsudomi, R. M. Huber, Y. Ishikawa, J. Jett, and D. Yankelewitz, “International association for the study of lung cancer/american thoracic society/european respiratory society international multidisciplinary classification of lung adenocarcinoma,” Journal of thoracic oncology: of- ficial publication of the International Association for the Study of Lung Cancer, vol. 6, pp. 244–285, 2011.spa
dc.relation.referencesL. Gengpeng, L. Hui, K. Jianyi, T. Kejing, G. Yubiao, H. Anjia, and X. Canmao, “Acinar-predominant pattern correlates with poorer prognosis in invasive mucinous adenocarcinoma of the lung,” American Journal of Clinical Pathology, vol. 149, p. 373–378, 2018.spa
dc.relation.referencesK. Kadota, Y. C. Yeh, C. S. Sima, V. W. Rusch, A. L. Moreira, P. S. Adusumilli, and W. D. Travis, “The cribriform pattern identifies a subset of acinar predominant tumors with poor prognosis in patients with stage i lung adenocarcinoma: a conceptual proposal to classify cribriform predominant tumors as a distinct histologic subtype,” Modern pathology : an official journal of the United States and Canadian Academy of Pathology, vol. 27, p. 690–700, 2014.spa
dc.relation.referencesT. Kinno, K. Tsuta, K. Shiraishi, T. Mizukami, M. Suzuki, A. Yoshida, K. Suzuki, H. Asamura, K. Furuta, T. Kohno, and R. Kushima, “Clinicopathological features of nonsmall cell lung carcinomas with braf mutations,” Ann Oncol, vol. 25, p. 138–42, 2014.spa
dc.relation.referencesK. Bera, K. Schalper, and et. al., “Artificial intelligence in digital pathology — new tools for diagnosis and precision oncology,” Nat Rev Clin Oncol, vol. 16, pp. 703–715, 2019.spa
dc.relation.referencesM. Gurcan, L. Boucheron, A. Can, A. Madabhushi, N. Rajpoot, and B. Yener, “Histopathological image analysis: A review,” IEEE Rev Biomed Eng, vol. 2, pp. 147– 171, 2009.spa
dc.relation.referencesL. Pantanowitz, D. Hartman, Y. Qi, E. Cho, B. Suh, K. Paeng, R. Dhir, P. Michelow, S. Hazelhurst, S. Song, and S. Cho, “Accuracy and efficiency of an artificial intelligence tool when counting breast mitoses,” Diagn Pathol, vol. 15, p. 80, 2020.spa
dc.relation.referencesR. Ding, P. Prasanna, G. Corredor, and et al., “Image analysis reveals molecularly distinct patterns of tils in nsclc associated with treatment outcome,” npj Precis. Onc, vol. 6, p. 33, 2022.spa
dc.relation.referencesA. Ibrahim, P. Gamble, R. Jaroensri, M. Abdelsamea, C. Mermel, P.-H. Chen, and E. Rakha, “Artificial intelligence in digital breast pathology: Techniques and applications,” The Breast, vol. 49, pp. 267–273, 2020.spa
dc.relation.referencesM. Yousif, P. van Diest, A. Laurinavicius, D. Rimm, J. van der Laak, A. Madabhushi, S. Schnitt, and L. Pantanowitz, “Artificial intelligence applied to breast pathology,” Virchows Arch, 2021.spa
dc.relation.referencesD. Van Booven, M. Kuchakulla, R. Pai, F. Frech, R. Ramasahayam, P. Reddy, M. Parmar, R. Ramasamy, and H. Arora, “A systematic review of artificial intelligence in prostate cancer,” Res Rep Urol, vol. 13, pp. 31–39, 2021.spa
dc.relation.referencesO. Tataru, M. Vartolomei, J. Rassweiler, O. Virgil, G. Lucarelli, F. Porpiglia, D. Amparore, M. Manfredi, G. Carrieri, U. Falagario, D. Terracciano, O. de Cobelli, G. Busetto, F. Giudice, and M. Ferro, “Artificial intelligence and machine learning in prostate cancer patient management—current trends and future perspectives,” Res Rep Urol, vol. 11, p. 354, 2021.spa
dc.relation.referencesG. Litjens, C. Sanchez, N. Timofeeva, M. Hermsen, I. Nagtegaal, I. Kovacs, and et al, “Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis,” Scientific Reports, vol. 6, 2016.spa
dc.relation.referencesB. Veeling, J. Linmans, J. Winkens, T. Cohen, and M. Welling, “Rotation equivariant cnns for digital pathology,” Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, vol. 11071, 2018.spa
dc.relation.referencesS. Mukhopadhyay, M. Feldman, E. Abels, R. Ashfaq, S. Beltaifa, N. Cacciabeve, H. Cathro, L. Cheng, K. Cooper, G. Dickey, R. Gill, R. Heaton, R. Kerstens, G. Lind- berg, R. Malhotra, J. Mandell, E. Manlucu, A. Mills, S. Mills, C. Moskaluk, M. Nelis, D. Patil, C. Przybycin, J. Reynolds, B. Rubin, M. Saboorian, M. Salicru, M. Samols, C. Sturgis, K. Turner, M. Wick, J. Yoon, P. Zhao, and C. Taylor, “Whole slide imaging versus microscopy for primary diagnosis in surgical pathology: A multicenter blinded randomized noninferiority study of 1992 cases (pivotal study),” Am J Surg Pathol, vol. 42, pp. 39–52, 2018.spa
dc.relation.referencesZ. Ahmad, S. Rahim, M. Zubair, and J. Abdul-Ghafar, “Artificial intelligence (ai) in medicine, current applications and future role with special emphasis on its potential and promise in pathology: present and future impact, obstacles including costs and acceptance among pathologists, practical and philosophical considerations. a comprehensive review,” Diagn Pathol, vol. 16, p. 24, 2021.spa
dc.relation.referencesA. Le Page, E. Ballot, C. Truntzer, V. Derang`ere, A. Ilie, D. Rageot, F. Bibeau, and F. Ghiringhelli, “Using a convolutional neural network for classification of squamous and non-squamous non-small cell lung cancer based on diagnostic histopathology hes images,” Sci Rep, vol. 11, p. 23912, 2021.spa
dc.relation.referencesO. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, 2015.spa
dc.relation.referencesN. Punn and S. Agarwal, “Modality specific u-net variants for biomedical image segmentation: a survey,” Artif Intell Rev, 2022.spa
dc.relation.referencesH. Tizhoosh and L. Pantanowitz, “Artificial intelligence and digital pathology: Challenges and opportunities,” J Pathol Inform, vol. 9, p. 38, 2022.spa
dc.relation.referencesR. Baeza-Yates and Z. Liaghat, “Quality-efficiency trade-offs in machine learning for text processing,” IEEE International Conference on Big Data (Big Data), pp. 897–904, 2017.spa
dc.relation.referencesK. Huang, L. Yang, Y. Wang, L. Huang, X. Zhou, and W. Zhang, “Identification of non-small-cell lung cancer subtypes by unsupervised clustering of ct image features with distinct prognoses and gene pathway activities,” Biomedical Signal Processing and Control, vol. 76, 2022.spa
dc.relation.referencesC. Weis, K. Weihrauch, K. Kriegsmann, and M. Kriegsmann, “Unsupervised segmentation in nsclc: How to map the output of unsupervised segmentation to meaningful histological labels by linear combination?,” Appl. Sci., vol. 12, p. 3718, 2022.spa
dc.relation.referencesC. Lynch, V. van Berkel, and H. Frieboes, “Application of unsupervised analysis techniques to lung cancer patient data,” PloS one, vol. 12, p. 9, 2017.spa
dc.relation.referencesY. Gao, Y. Ding, W. Xiao, Z. Yao, X. Zhou, X. Sui, Y. Zhao, and Y. Zheng, “A semi-supervised learning framework for micropapillary adenocarcinoma detection,” International journal of computer assisted radiology and surgery, vol. 17, pp. 639–648, 2022.spa
dc.relation.referencesK. Shak, M. Al-Shabi, A. Liew, B. Lan, W. Leong, N. Kh, and M. Tan, “A new semi- supervised self-training method for lung cancer prediction,” arXiv:2012.09472, 2020.spa
dc.relation.referencesR. Chen, C. Chen, Y. Li, T. Chen, A. Trister, R. Krishnan, and F. Mahmood, “Scaling vision transformers to gigapixel images via hierarchical self-supervised learning,” arXiv:2206.02647, 2022.spa
dc.relation.referencesV. Thanh-Hung, L. Guee-Samg, Y. Hyung-Jeong, K. Sae-Ryung, O. In-Jae, , and K. Soo-Hyung, “Multi-task with variational autoencoder for lung cancer prognosis on clinical data,” In The 9th International Conference on Smart Media and Applications (SMA 2020), pp. 234–237, 2020.spa
dc.relation.referencesS. Wang, M. Zhou, Z. Liu, Z. Liu, D. Gu, Y. Zang, D. Dong, O. Gevaert, and J. Tian, “Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation,” Medical image analysis, vol. 40, pp. 172–183, 2017.spa
dc.relation.referencesK.-H. Yu, F. Wang, G. Berry, C. R ́e, R. Altman, M. Snyder, and I. Kohane, “Classifying non-small cell lung cancer types and transcriptomic subtypes using convolutional neural networks,” J Am Med Inform Assoc, vol. 27, pp. 757–769, 2020.spa
dc.relation.referencesC. Han and et. al., “Wsss4luad: Grand challenge on weakly-supervised tissue semantic segmentation for lung adenocarcinoma,” in arXiv, 2022.spa
dc.relation.referencesM. for Primary Industries, “University of louisville health adopts paige ai-enabled cancer detection software for enhanced cancer detection.” https://www.businesswire.com/news/home/20211215005218/en/University-of- Louisville-Health-Adopts-Paige-AI-enabled-Cancer-Detection-Software-for-Enhanced- Cancer-Detection, 2021. Online; accessed May 2022.spa
dc.relation.referencesJ. Amann, A. Blasimme, E. Vayena, D. Frey, and V. Madai, “Explainability for artificial intelligence in healthcare: a multidisciplinary perspective,” BMC Med Inform Decis Mak, vol. 20, p. 310, 2020.spa
dc.relation.referencesA. Madabhushi and G. Lee, “Image analysis and machine learning in digital pathology: Challenges and opportunities,” Medical image analysis, vol. 33, pp. 170–175, 2016.spa
dc.relation.referencesU. Michelucci, “An introduction to autoencoders,” 2022.spa
dc.relation.referencesA. Fuxjaeger and V. Belle, “Logical interpretations of autoencoders,” 2019.spa
dc.relation.referencesD. Kingma and M. Welling, “An introduction to variational autoencoders,” Foundations and Trends in Machine Learning, vol. 12, no. 4, pp. 307–392, 2019.spa
dc.relation.referencesI. Higgins, L. Matthey, and et. al., “beta-VAE: Learning basic visual concepts with a constrained variational framework,” in International Conference on Learning Represen- tations, 2017.spa
dc.relation.referencesD. Kingma and M. Welling, “Auto-encoding variational bayes,” 2013.spa
dc.relation.referencesF. Cano, C. Alvarez-Jimenez, D. Becerra, A. Siabatto, A. Cruz-Roa, and E. Romero, “A supervised subtype differentiation learning for building invariant features of non-small cell lung cancer in a latent space of a variational autoencoder,” in Proc. SPIE 12088, 17th International Symposium on Medical Information Processing and Analysis, 2021.spa
dc.relation.referencesF. Bray, J. Ferlay, I. Soerjomataram, and et. al., “Global cancer statistics 2018: Globo- can estimates of incidence and mortality worldwide for 36 cancers in 185 countries,” CA: a cancer journal for clinicians 2018, vol. 68, pp. 394–424, 2018.spa
dc.relation.referencesW. Wu, C. Parmar, P. Grossmann, J. Quackenbush, P. Lambin, J. Bussink, R. Mak, and H. Aerts, “Exploratory study to identify radiomics classifiers for lung cancer histology,” Front Oncol., vol. 6, p. 71, 2016.spa
dc.relation.referencesM. Connor, G. Canal, and C. Rozell, “Classification and pathology of lung cancer,” Surgical Oncology Clinics, vol. 25, pp. 447–468, 2016.spa
dc.relation.referencesS. Norouzi, D. Fleet, and M. Norouzi, “Exemplar vae: Linking generative models, near- est neighbor retrieval, and data augmentation,” 34th Conference on Neural Information Processing Systems (NeurIPS 2018), vol. -, 2020.spa
dc.relation.referencesJ. Yoo, H. Lee, and N. wak, “Density estimation and incremental learning of latent vector for generative autoencoders,” Mathematics, Computer Science, vol. -, 2019.spa
dc.relation.referencesL. Ternes, M. Dane, M. Labrie, G. Mills, J. Gray, L. Heiser, and Y. Chang, “Me-vae: Multi-encoder variational autoencoder for controlling multiple transformational features in single cell image analysis,” bioRxiv, vol. -, pp. –, 2021.spa
dc.relation.referencesN. Simidjievski, C. Bodnar, I. Tariq, P. Scherer, A. T., and et. al., “Variational autoencoders for cancer data integration: Design principles and computational practice,” Frontiers in Genetics, vol. 10, p. 1205, 2019.spa
dc.relation.referencesN. C. Institute, “The cancer genome atlas program,” 2022. Last accessed: 10 November 2022.spa
dc.relation.referencesJ. Klys, J. Snell, and R. Zemel, “Learning latent subspaces in variational autoencoders,” 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), vol. -, 2018.spa
dc.relation.referencesM. Connor, G. Canal, and C. Rozell, “Variational autoencoder with learned latent structure,” 24th International Conference on Artificial Intelligence and Statistics (AIS- TATS), vol. -, 2021.spa
dc.relation.referencesE. Parzen, “On estimation of a probability density function and mode,” Ann. Math. Statist, vol. 33, pp. 1065–1076, 1962.spa
dc.relation.referencesW. C. of Tumours, Thoracic Tumours, vol. 5. Lyon (France): International Agency for Research on Cancer: Editorial Board, 2021.spa
dc.relation.referencesD. L. Rimm, G. Han, and et. al., “A prospective, multi-institutional, pathologist-based assessment of 4 immunohistochemistry assays for pd-l1 expression in non-small cell lung cancer,” JAMA oncology, vol. 3(8), p. 1051–1058, 2017.spa
dc.relation.referencesL. McInnes and et. al., “Umap: Uniform manifold approximation and projection for dimension reduction,” 2018.spa
dc.relation.referencesD. Blei, A. Kucukelbir, and J. McAuliffe, “Variational inference: A review for statisticians.,” Journal of the American Statistical Association, vol. 112, no. 518, pp. 859–877, 2017.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseReconocimiento 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/spa
dc.subject.ddc610 - Medicina y saludspa
dc.subject.ddc000 - Ciencias de la computación, información y obras generalesspa
dc.subject.ddc620 - Ingeniería y operaciones afinesspa
dc.subject.decsPatología clínicaspa
dc.subject.decsPathology, Clinicaleng
dc.subject.decsTejidosspa
dc.subject.decsTissueseng
dc.subject.decsProcesamiento de imagen asistido por computadorspa
dc.subject.decsImage Processing, Computer-Assistedspa
dc.subject.proposalDigital Pathologyeng
dc.subject.proposalTissue Representationeng
dc.subject.proposalHistopathologyeng
dc.subject.proposalVariational Autoencodereng
dc.subject.proposalLung Adenocarcinomaeng
dc.subject.proposalLung Cancereng
dc.subject.proposalPatología Digitalspa
dc.subject.proposalRepresentación de tejidosspa
dc.subject.proposalHistopatologíaspa
dc.subject.proposalAutocodificador Variacionaspa
dc.subject.proposalAdenocarcinoma de pulmónspa
dc.subject.proposalCáncer de pulmónspa
dc.titleA Data-driven Representation Learning for Tumor Tissue Differentiation from Non-Small Cell Lung Cancer Histopathology Imageseng
dc.title.translatedUn aprendizaje de representación basado en datos para la diferenciación de tejido tumoral a partir de imágenes de histopatología de cáncer de pulmón de células no pequeñasspa
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentEstudiantesspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
1121932413.2022.pdf
Tamaño:
6.47 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería Biomédica

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción: