Medical image segmentation in a multiple labelers context : application to the study of histopathology
| dc.contributor.advisor | Álvarez Meza, Andrés Marino | |
| dc.contributor.advisor | Castellanos Domínguez, Germán | |
| dc.contributor.author | Lotero Londoño, Brandon | |
| dc.contributor.cvlac | Lotero Londoño, Brandon [0001836907] | |
| dc.contributor.googlescholar | Lotero Londono, Brandon [H2E8Kd8AAAAJ] | |
| dc.contributor.orcid | Lotero Londoño, Brandon [0009000844326383] | |
| dc.contributor.researchgate | Lotero Londoño, Brandon [Brandon-Lotero] | |
| dc.contributor.researchgroup | Grupo de Control y Procesamiento Digital de Señales | |
| dc.date.accessioned | 2026-02-25T20:52:27Z | |
| dc.date.available | 2026-02-25T20:52:27Z | |
| dc.date.issued | 2025 | |
| dc.description | graficas, tablas | spa |
| dc.description.abstract | Breast cancer remains one of the deadliest diseases affecting women worldwide, making accurate diagnosis and treatment planning crucial for improving patient outcomes. Semantic segmentation of histopathology images plays a vital role in this process, as it enables precise identification and analysis of tissue structures. However, the current approaches face significant challenges in real-world scenarios where multiple annotators with varying expertise and reliability contribute to the labeling process. This crowdsourcing paradigm, while cost-effective, introduces inconsistencies that can compromise the quality of the segmentation results. This thesis addresses two fundamental challenges in medical image segmentation: the inherent uncertainty in multiple annotator scenarios and the need for robustsegmentation models that can handle varying image quality and annotator expertise. These challenges arise from the complex nature of histopathology images, where tissue structures can be ambiguous, and the varying levels of expertise among annotators lead to inconsistent labeling patterns. Additionally, the high cost and time requirements for expert annotations create a need for efficient solutions that can work with crowdsourced data. To address these challenges, this thesis proposes a comprehensive approach that combines novel loss functions with robust deep learning architectures to handle multiple annotator scenarios effectively. The first objective introduces a novel loss function that implicitly infers optimal segmentation while assessing labeler reliability without requiring explicit performance inputs. This approach differs from conventional methods by eliminating the need for direct supervision of labeler performance, instead using an intermediate reliability map that enables the model to prioritize information from reliable labelers while disregarding noisy labels. The mathematical foundation of this approach lies in the probabilistic modeling of annotator reliability across the input space. The second objective focuses on the development of a robust segmentation architecture that combines the strengths of U-shaped deep learning models with the proposed reliability-aware loss function. This combination enables the model to learn both the segmentation task and the reliability patterns simultaneously, leading to more accurate and consistent results. The architecture’s key innovation lies in its ability to adapt to varying image quality and annotator expertise levels without requiring explicit performance metrics. The third objective involves validating the proposed approach through extensive experimentation on both synthetic datasets and real-world histopathology images. The evaluation demonstrates superior performance compared to state-of-the-art approaches in terms of segmentation accuracy and uncertainty quantification. The results show that the proposed method can effectively handle inconsistent annotations while maintaining high segmentation accuracy, making it particularly valuable for clinical applications. The research makes significant contributions to the field by providing a robust solution for handling inconsistent annotations in medical image segmentation, particularly valuable in histopathology where expert annotations are expensive and time-consuming to obtain. The proposed approach shows promising results in reducing annotation costs while maintaining high segmentation accuracy, making it particularly relevant for clinical applications where precise segmentation of tissue structures is crucial for diagnosis and treatment planning. This work opens new research directions in the areas of crowdsourced medical image analysis, uncertainty quantification in deep learning, and the development of more efficient annotation protocols for medical imaging (Texto tomado de la fuente). | eng |
| dc.description.abstract | El cáncer de mama sigue siendo una de las enfermedades más mortales en la población femenina en todo el mundo, lo que hace que el diagnóstico preciso y la planificación del tratamiento sean cruciales para mejorar las condiciones de los pacientes. La segmentación semántica de imágenes histopatológicas juega un papel vital en este proceso, ya que permite la identificación y análisis preciso de estructuras tisulares. Sin embargo, los enfoques actuales enfrentan desafíos significativos en escenarios del mundo real donde múltiples anotadores con diferentes niveles de experiencia y confiabilidad contribuyen al proceso de etiquetado. Este paradigma de crowdsourcing, aunque rentable, introduce inconsistencias que pueden comprometer la calidad de los resultados de segmentación. Esta tesis aborda dos desafíos fundamentales en la segmentación de imágenes médicas: la incertidumbre inherente en escenarios de múltiples anotadores y la necesidad de modelos de segmentación robustos que puedan manejar la calidad variable de las imágenes y la experiencia de los anotadores. Estos desafíos surgen de la naturaleza compleja de las imágenes histopatológicas, donde las estructuras tisulares pueden ser ambiguas, y los diferentes niveles de experiencia entre los anotadores conducen a patrones de etiquetado inconsistentes. Además, el alto costo y los requisitos de tiempo para las anotaciones de expertos crean la necesidad de soluciones eficientes que puedan trabajar con datos crowdsourced. El primer objetivo introduce una función de pérdida novedosa que infiere implícitamente la segmentación óptima mientras evalúa la confiabilidad de los etiquetadores sin requerir entradas explícitas sobre su rendimiento. Este enfoque difiere de los métodos convencionales al eliminar la necesidad de supervisión directa del rendimiento de los etiquetadores, utilizando en su lugar un mapa de confiabilidad intermedio que permite al modelo priorizar la información de etiquetadores confiables mientras descarta etiquetas ruidosas. La base matemática de este enfoque radica en el modelado probabilístico de la confiabilidad de los anotadores a través del espacio de entrada. El segundo objetivo se centra en el desarrollo de una arquitectura de segmentación robusta que combina las fortalezas de los modelos de aprendizaje profundo en forma de U con la función de pérdida propuesta que tiene en cuenta la confiabilidad. Esta combinación permite que el modelo aprenda tanto la tarea de segmentación como los patrones de confiabilidad simultáneamente, lo que lleva a resultados más precisos y consistentes. La innovación clave de la arquitectura radica en su capacidad para adaptarse a diferentes niveles de calidad de imagen y experiencia de los anotadores sin requerir métricas de rendimiento explícitas. El tercer objetivo valida el enfoque propuesto a través de experimentación exhaustiva tanto en conjuntos de datos sintéticos como en imágenes histopatológicas del mundo real. La evaluación demuestra un rendimiento superior en comparación con los enfoques más avanzados en términos de precisión de segmentación y cuantificación de incertidumbre. Los resultados muestran que el método propuesto puede manejar efectivamente anotaciones inconsistentes mientras mantiene una alta precisión de segmentación, lo que lo hace particularmente valioso para aplicaciones clínicas. La investigación hace contribuciones significativas al campo al proporcionar una solución robusta para manejar anotaciones inconsistentes en la segmentación de imágenes médicas, particularmente valiosa en histopatología donde las anotaciones de expertos son costosas y requieren mucho tiempo para obtenerlas. El enfoque propuesto muestra resultados prometedores en la reducción de costos de anotación mientras mantiene una alta precisión de segmentación, lo que lo hace particularmente relevante para aplicaciones clínicas donde la segmentación precisa de estructuras tisulares es crucial para el diagnóstico y la planificación del tratamiento. Este trabajo abre nuevas direcciones de investigación en las áreas de análisis de imágenes médicas crowdsourced, cuantificación de incertidumbre en aprendizaje profundo y el desarrollo de protocolos de anotación más eficientes para imágenes médicas. | spa |
| dc.description.curriculararea | Eléctrica, Electrónica, Automatización Y Telecomunicaciones.Sede Manizales | |
| dc.description.degreelevel | Maestría | |
| dc.description.degreename | Magíster en Ingeniería - Automatización Industrial | |
| dc.description.researcharea | Computer Vision | |
| dc.description.sponsorship | Hospital Universitario de Caldas - SES HUC | |
| dc.format.extent | xxxii, 128 páginas | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.instname | Universidad Nacional de Colombia | spa |
| dc.identifier.reponame | Repositorio Institucional Universidad Nacional de Colombia | spa |
| dc.identifier.repourl | https://repositorio.unal.edu.co/ | spa |
| dc.identifier.uri | https://repositorio.unal.edu.co/handle/unal/89684 | |
| dc.language.iso | eng | |
| dc.publisher | Universidad Nacional de Colombia | |
| dc.publisher.branch | Universidad Nacional de Colombia - Sede Manizales | |
| dc.publisher.faculty | Facultad de Ingeniería y Arquitectura | |
| dc.publisher.place | Manizales, Colombia | |
| dc.publisher.program | Manizales - Ingeniería y Arquitectura - Maestría en Ingeniería - Automatización Industrial | |
| dc.relation.indexed | Agrosavia | |
| dc.relation.indexed | Bireme | |
| dc.relation.indexed | RedCol | |
| dc.relation.indexed | LaReferencia | |
| dc.relation.indexed | Agrovoc | |
| dc.relation.references | [Abadi et al., 2016] Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner, B., Tucker, P. A., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., and Zhang, X. (2016). Tensorflow: A system for large-scale machine learning. CoRR, abs/1605.08695. | |
| dc.relation.references | [Akiba et al., 2019] Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework | |
| dc.relation.references | [Alloghani et al., 2020] Alloghani, M., Al-Jumeily, D., Mustafina, J., Hussain, A., and Aljaaf, A. J. (2020). A Systematic Review on Supervised and Unsupervised Machine Learning Algorithms for Data Science, pages 3–21. Springer International Publishing, Cham | |
| dc.relation.references | [Amgad et al., 2019] Amgad, M., Elfandy, H., Hussein, H., Atteya, L. A., Elsebaie, M. A. T., Abo Elnasr, L. S., Sakr, R. A., Salem, H. S. E., Ismail, A. F., Saad, A. M., Ahmed, J., Elsebaie, M. A. T., Rahman, M., Ruhban, I. A., Elgazar, N. M., Alagha, Y., Osman, M. H., Alhusseiny, A. M., Khalaf, M. M., Younes, A.-A. F., Abdulkarim, A., Younes, D. M., Gadallah, A. M., Elkashash, A. M., Fala, S. Y., Zaki, B. M., Beezley, J., Chittajallu, D. R., Manthey, D., Gutman, D. A., and Cooper, L. A. D. (2019). Structured crowdsourcing enables convolutional segmentation of histology images. Bioinformatics, 35(18):3461–3467. | |
| dc.relation.references | [Avanzo et al., 2024] Avanzo, M., Stancanello, J., Pirrone, G., Drigo, A., and Retico, A. (2024). The evolution of artificial intelligence in medical imaging: From computer science to machine and deep learning. Cancers (Basel), 16(21):3702. Author Joseph Stancanello is employed by Elekta SA. The remaining authors declare no commercial or financial conflicts of interest. | |
| dc.relation.references | [Azad et al., 2024] Azad, R., Aghdam, E. K., Rauland, A., Jia, Y., Avval, A. H., Bozorgpour, A., Karimijafarbigloo, S., Cohen, J. P., Adeli, E., and Merhof, D. (2024). Medical image segmentation review: The success of u-net. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):10076–10095 | |
| dc.relation.references | [Banerjee et al., 2025] Banerjee, A., Shan, H., and Feng, R. (2025). Editorial: Artificial intelligence applications for cancer diagnosis in radiology. Frontiers in Radiology, 5. | |
| dc.relation.references | [Bhalgat et al., 2018] Bhalgat, Y., Shah, M. P., and Awate, S. P. (2018). Annotation- cost minimization for medical image segmentation using suggestive mixed supervision fully convolutional networks. CoRR, abs/1812.11302. | |
| dc.relation.references | [Brito-Pacheco et al., 2025] Brito-Pacheco, D., Giannopoulos, P., and Reyes- Aldasoro, C. C. (2025). Persistent homology in medical image processing: A literature review. | |
| dc.relation.references | [Carmo et al., 2025] Carmo, D. S., Pezzulo, A. A., Villacreses, R. A., Eisenbeisz, M. L., Anderson, R. L., Van Dorin, S. E., Rittner, L., Lotufo, R. A., Gerard, S. E., Reinhardt, J. M., and Comellas, A. P. (2025). Manual segmentation of opacities and consolidations on ct of long covid patients from multiple annotators. Scientific Data, 12(1):402 | |
| dc.relation.references | [de G. Matthews et al., 2016] de G. Matthews, A. G., van der Wilk, M., Nickson, T., Fujii, K., Boukouvalas, A., León-Villagrá, P., Ghahramani, Z., and Hensman, J. (2016). Gpflow: A gaussian process library using tensorflow. | |
| dc.relation.references | [Duarte and Baraniuk, 2012] Duarte, M. F. and Baraniuk, R. G. (2012). Kronecker compressive sensing. IEEE Transactions on Image Processing, 21(2):494–504. | |
| dc.relation.references | [Dutordoir et al., 2021] Dutordoir, V., Salimbeni, H., Hambro, E., McLeod, J., Leibfried, F., Artemev, A., van der Wilk, M., Hensman, J., Deisenroth, M. P., and John, S. (2021). Gpflux: A library for deep gaussian processes. | |
| dc.relation.references | [Elhaminia et al., 2025] Elhaminia, B., Alsalemi, A., Nasir, E., Jahanifar, M., Awan, R., Young, L. S., Rajpoot, N. M., Minhas, F., and Raza, S. E. A. (2025). From traditional to deep learning approaches in whole slide image registration: A methodological review. | |
| dc.relation.references | [Elnakib et al., 2020] Elnakib, A., Elmenabawy, N., and S Moustafa, H. (2020). Automated deep system for joint liver and tumor segmentation using majority voting. MEJ-Mansoura Engineering Journal, 45(4):30–36. | |
| dc.relation.references | [Farahani et al., 2015] Farahani, N., Parwani, A. V., and Pantanowitz, L. (2015). Whole slide imaging in pathology: advantages, limitations, and emerging perspectives. Pathology and Laboratory Medicine International, 7:23–33. | |
| dc.relation.references | [Ghezloo et al., 2025] Ghezloo, F., Chang, O. H., Knezevich, S. R., Shaw, K. C., Thigpen, K. G., Reisch, L. M., Shapiro, L. G., and Elmore, J. G. (2025). Robust roi detection in whole slide images guided by pathologists’ viewing patterns. Journal of Imaging Informatics in Medicine, 38(1):439–454. | |
| dc.relation.references | [Gil-Gonzalez et al., 2018] Gil-Gonzalez, J., Alvarez-Meza, A., and Orozco-Gutierrez, A. (2018). Learning from multiple annotators using kernel alignment. Pattern Recognition Letters, 116:150–156. | |
| dc.relation.references | [Gil-Gonzalez et al., 2023] Gil-Gonzalez, J., Giraldo, J. J., Alvarez-Meza, A. M., Orozco-Gutierrez, A., and Alvarez, M. A. (2023). Correlated chained gaussian processes for datasets with multiple annotators. IEEE Transactions on Neural Networks and Learning Systems, 34(8):4514–4528. | |
| dc.relation.references | [Gil-Gonzalez et al., 2021a] Gil-Gonzalez, J., Orozco-Gutierrez, A., and Alvarez- Meza, A. (2021a). Learning from multiple inconsistent and dependent annotators to support classification tasks. Neurocomputing, 423:236–247. | |
| dc.relation.references | [Gil-Gonzalez et al., 2021b] Gil-Gonzalez, J., Valencia-Duque, A., Alvarez-Meza, A., Orozco-Gutierrez, A., and Garcia-Moreno, A. (2021b). Regularized chained deep neural network classifier for multiple annotators. Applied Sciences, 11(12). | |
| dc.relation.references | [Gil-González and Álvarez Meza, 2023] Gil-González, J. and Álvarez Meza, A. M. (2023). A supervised learning framework in the context of multiple annotators. | |
| dc.relation.references | [Giraldo et al., 2022] Giraldo, J.-J., Zhang, J., and Álvarez, M. A. (2022). Correlated chained gaussian processes for modelling citizens mobility using a zero- inflated poisson likelihood. IEEE Transactions on Intelligent Transportation Systems, 23(11):20337–20351 | |
| dc.relation.references | [Giri and Bhatia, 2024] Giri, K. and Bhatia, S. (2024). Artificial intelligence in nephrology- its applications from bench to bedside. International Journal of Advances in Nephrology Research, 7(1):90–97. | |
| dc.relation.references | [Grefve et al., 2024] Grefve, J., Söderkvist, K., Gunnlaugsson, A., Sandgren, K., Jonsson, J., Keeratijarut Lindberg, A., Nilsson, E., Axelsson, J., Bergh, A., Zackrisson, B., Moreau, M., Thellenberg Karlsson, C., Olsson, L., Widmark, A., Riklund, K., Blomqvist, L., Berg Loegager, V., Strandberg, S. N., and Nyholm, T. (2024). Histopathology-validated gross tumor volume delineations of intraprostatic lesions using psma-positron emission tomography/multiparametric magnetic resonance imaging. Physics and Imaging in Radiation Oncology, 31:100633. | |
| dc.relation.references | [Habis, 2024] Habis, A. A. (2024). Developing interactive artificial intelligence tools to assist pathologists with histology annotation. Theses, Institut Polytechnique de Paris. | |
| dc.relation.references | [He et al., 2015] He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep residual learning for image recognition. | |
| dc.relation.references | [Hossain et al., 2023] Hossain, M. S., Shahriar, G. M., Syeed, M. M. M., Uddin, M. F., Hasan, M., Shivam, S., and Advani, S. (2023). Region of interest (roi) selection using vision transformer for automatic analysis using whole slide images. Scientific Reports, 13(1):11314. | |
| dc.relation.references | [Hu et al., 2025] Hu, D., Jiang, Z., Shi, J., Xie, F., Wu, K., Tang, K., Cao, M., Huai, J., and Zheng, Y. (2025). Pathology report generation from whole slide images with knowledge retrieval and multi-level regional feature selection. Computer Methods and Programs in Biomedicine, 263:108677. | |
| dc.relation.references | [Jia et al., 2014] Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R. B., Guadarrama, S., and Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. CoRR, abs/1408.5093. | |
| dc.relation.references | [Karthikeyan et al., 2023] Karthikeyan, R., McDonald, A., and Mehta, R. (2023). What’s in a label? annotation differences in forecasting mental fatigue using ecg data and seq2seq architectures. | |
| dc.relation.references | [Kendall and Gal, 2017] Kendall, A. and Gal, Y. (2017). What uncertainties do we need in bayesian deep learning for computer vision? In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R., editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. | |
| dc.relation.references | [Kim et al., 2024] Kim, Y., Lee, E., Lee, Y., and Oh, U. (2024). Understanding novice’s annotation process for 3d semantic segmentation task with human- in-the-loop. In Proceedings of the 29th International Conference on Intelligent User Interfaces, IUI ’24, page 444–454, New York, NY, USA. Association for Computing Machinery. | |
| dc.relation.references | [Lam and Suen, 1997] Lam, L. and Suen, S. (1997). Application of majority voting to pattern recognition: an analysis of its behavior and performance. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 27(5):553–568. | |
| dc.relation.references | [Li et al., 2024] Li, H. B., Navarro, F., Ezhov, I., Bayat, A., Das, D., Kofler, F., Shit, S., Waldmannstetter, D., Paetzold, J. C., Hu, X., Wiestler, B., Zimmer, L., Amiranashvili, T., Prabhakar, C., Berger, C., Weidner, J., Alonso-Basant, M., Rashid, A., Baid, U., Adel, W., Ali, D., Baheti, B., Bai, Y., Bhatt, I., Cetindag, S. C., Chen, W., Cheng, L., Dutand, P., Dular, L., Elattar, M. A., Feng, M., Gao, S., Huisman, H., Hu, W., Innani, S., Jiat, W., Karimi, D., Kuijf, H. J., Kwak, J. T., Le, H. L., Lia, X., Lin, H., Liu, T., Ma, J., Ma, K., Ma, T., Oksuz, I., Holland, R., Oliveira, A. L., Pal, J. B., Pei, X., Qiao, M., Saha, A., Selvan, R., Shen, L., Silva, J. L., Spiclin, Z., Talbar, S., Wang, D., Wang, W., Wang, X., Wang, Y., Xia, R., Xu, K., Yan, Y., Yergin, M., Yu, S., Zeng, L., Zhang, Y., Zhao, J., Zheng, Y., Zukovec, M., Do, R., Becker, A., Simpson, A., Konukoglu, E., Jakab, A., Bakas, S., Joskowicz, L., and Menze, B. (2024). Qubiq: Uncertainty quantification for biomedical image segmentation challenge. | |
| dc.relation.references | [Lin et al., 2024] Lin, Y., Lian, A., Liao, M., and Yuan, S. (2024). Bcdnet: A fast residual neural network for invasive ductal carcinoma detection. | |
| dc.relation.references | [Liu et al., 2020] Liu, H., Ong, Y.-S., Shen, X., and Cai, J. (2020). When gaussian process meets big data: A review of scalable gps. IEEE Transactions on Neural Networks and Learning Systems, 31(11):4405–4423. | |
| dc.relation.references | [López-Pérez et al., 2023] López-Pérez, M., Morales-Álvarez, P., Cooper, L. A. D., Molina, R., and Katsaggelos, A. K. (2023). Crowdsourcing segmentation of histopathological images using annotations provided by medical students. In Juarez, J. M., Marcos, M., Stiglic, G., and Tucker, A., editors, Artificial Intelligence in Medicine, pages 245–249, Cham. Springer Nature Switzerland. | |
| dc.relation.references | [Lu et al., 2023] Lu, X., Ratcliffe, D., Kao, T.-T., Tikhonov, A., Litchfield, L., Rodger, C., and Wang, K. (2023). Rethinking quality assurance for crowdsourced multi- roi image segmentation. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 11(1):103–114. | |
| dc.relation.references | [López-Pérez et al., 2024] López-Pérez, M., Morales-Álvarez, P., Cooper, L. A., Felicelli, C., Goldstein, J., Vadasz, B., Molina, R., and Katsaggelos, A. K. (2024). Learning from crowds for automated histopathological image segmentation. Computerized Medical Imaging and Graphics, 112:102327. | |
| dc.relation.references | [Ma et al., 2023] Ma, F., Yuan, M., and Kozak, I. (2023). Multispectral imaging: Review of current applications. Survey of Ophthalmology, 68(5):889–904. (page 27) | |
| dc.relation.references | [Mazzarini et al., 2021] Mazzarini, M., Falchi, M., Bani, D., and Migliaccio, A. R. (2021). Evolution and new frontiers of histology in bio-medical research. Microscopy Research and Technique, 84(2):217–237. | |
| dc.relation.references | [Pan et al., 2021] Pan, X., Lu, Y., Lan, R., Liu, Z., Qin, Z., Wang, H., and Liu, Z. (2021). Mitosis detection techniques in h&e stained breast cancer pathological images: A comprehensive review. Computers & Electrical Engineering, 91:107038. | |
| dc.relation.references | [Panayides et al., 2020] Panayides, A. S., Amini, A., Filipovic, N. D., Sharma, A., Tsaftaris, S. A., Young, A., Foran, D., Do, N., Golemati, S., Kurc, T., Huang, K., Nikita, K. S., Veasey, B. P., Zervakis, M., Saltz, J. H., and Pattichis, C. S. (2020). Ai in medical imaging informatics: Current challenges and future directions. IEEE Journal of Biomedical and Health Informatics, 24(7):1837–1857. | |
| dc.relation.references | [Parkhi et al., 2012] Parkhi, O. M., Vedaldi, A., Zisserman, A., and Jawahar, C. V. (2012). Cats and dogs. In IEEE Conference on Computer Vision and Pattern Recognition. | |
| dc.relation.references | [Paszke et al., 2019] Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Köpf, A., Yang, E. Z., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., and Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library. CoRR, abs/1912.01703. | |
| dc.relation.references | [Plasilova et al., 2016] Plasilova, M. L., Hayse, B., Killelea, B. K., Horowitz, N. R., Chagpar, A. B., and Lannin, D. R. (2016). Features of triple-negative breast cancer: Analysis of 38,813 cases from the national cancer database. Medicine (Baltimore), 95(35):e4614. | |
| dc.relation.references | [Qiu et al., 2022] Qiu, Y., Hu, Y., Kong, P., Xie, H., Zhang, X., Cao, J., Wang, T., and Lei, B. (2022). Automatic prostate gleason grading using pyramid semantic parsing network in digital histopathology. Frontiers in Oncology, 12. | |
| dc.relation.references | [Rashmi et al., 2021] Rashmi, R., Prasad, K., and Udupa, C. B. K. (2021). Breast histopathological image analysis using image processing techniques for diagnostic purposes: A methodological review. Journal of Medical Systems, 46(1):7. | |
| dc.relation.references | [Rasmussen and Williams, 2006a] Rasmussen, C. E. and Williams, C. K. I. (2006a). Gaussian Processes for Machine Learning. MIT Press, Cambridge, MA, USA. | |
| dc.relation.references | [Rasmussen and Williams, 2006b] Rasmussen, C. E. and Williams, C. K. I. (2006b). Gaussian Processes for Machine Learning. MIT Press, Cambridge, MA, USA. | |
| dc.relation.references | [Roelofs et al., 2019] Roelofs, R., Shankar, V., Recht, B., Fridovich-Keil, S., Hardt, M., Miller, J., and Schmidt, L. (2019). A meta-analysis of overfitting in machine learning. In Wallach, H., Larochelle, H., Beygelzimer, A., d'Alché-Buc, F., Fox, E., and Garnett, R., editors, Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc. | |
| dc.relation.references | [Ronneberger et al., 2015] Ronneberger, O., Fischer, P., and Brox, T. (2015). U- net: Convolutional networks for biomedical image segmentation. In Navab, N., Hornegger, J., Wells, W. M., and Frangi, A. F., editors, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241, Cham. Springer International Publishing. | |
| dc.relation.references | [Ryou et al., 2025] Ryou, H., Thomas, E., Wojciechowska, M., Harding, L., Tam, K. H., Wang, R., Hu, X., Rittscher, J., Cooper, R., and Royston, D. (2025). Reticulin- free quantitation of bone marrow fibrosis in mpns: Utility and applications. eJHaem, 6(2):e70005. | |
| dc.relation.references | [Sarvamangala and Kulkarni, 2022] Sarvamangala, D. R. and Kulkarni, R. V. (2022). Convolutional neural networks in medical image understanding: a survey. Evolutionary Intelligence, 15(1):1–22. | |
| dc.relation.references | [Saul et al., 2016] Saul, A. D., Hensman, J., Vehtari, A., and Lawrence, N. D. (2016). Chained gaussian processes. | |
| dc.relation.references | [Shah et al., 2018] Shah, M. P., Merchant, S. N., and Awate, S. P. (2018). Ms-net: Mixed-supervision fully-convolutional networks for full-resolution segmentation. In Frangi, A. F., Schnabel, J. A., Davatzikos, C., Alberola- López, C., and Fichtinger, G., editors, Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, pages 379–387, Cham. Springer International Publishing. | |
| dc.relation.references | [Shalf, 2020] Shalf, J. (2020). The future of computing beyond moore’s law. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 378(2166):20190061. | |
| dc.relation.references | [Singh et al., 2020] Singh, S. P., Wang, L., Gupta, S., Goli, H., Padmanabhan, P., and Gulyás, B. (2020). 3d deep learning on medical images: A review. Sensors, 20(18). | |
| dc.relation.references | [Soydaner, 2020] Soydaner, D. (2020). A comparison of optimization algorithms for deep learning. International Journal of Pattern Recognition and Artificial Intelligence, 34(13):2052013. | |
| dc.relation.references | [Taye, 2023] Taye, M. M. (2023). Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation, 11(3). | |
| dc.relation.references | [TIAN and Zhu, 2015] TIAN, T. and Zhu, J. (2015). Max-margin majority voting for learning from crowds. In Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., and Garnett, R., editors, Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc. | |
| dc.relation.references | [Triana-Martinez et al., 2023] Triana-Martinez, J. C., Gil-González, J., Fernandez- Gallego, J. A., Álvarez Meza, A. M., and Castellanos-Dominguez, C. G. (2023). Chained deep learning using generalized cross-entropy for multiple annotators classification. Sensors, 23(7). | |
| dc.relation.references | [Warfield et al., 2004] Warfield, S., Zou, K., and Wells, W. (2004). Simultaneous truth and performance level estimation (staple): an algorithm for the validation of image segmentation. IEEE Transactions on Medical Imaging, 23(7):903–921. | |
| dc.relation.references | [Weitz et al., 2023] Weitz, P., Valkonen, M., Solorzano, L., Carr, C., Kartasalo, K., Boissin, C., Koivukoski, S., Kuusela, A., Rasic, D., Feng, Y., Sinius Pouplier, S., Sharma, A., Ledesma Eriksson, K., Latonen, L., Laenkholm, A.-V., Hartman, J., Ruusuvuori, P., and Rantalainen, M. (2023). A multi-stain breast cancer histological whole-slide-image data set from routine diagnostics. Scientific Data, 10(1):562. | |
| dc.relation.references | [Werbos, 1990] Werbos, P. (1990). Backpropagation through time: what it does and how to do it. Proceedings of the IEEE, 78(10):1550–1560. | |
| dc.relation.references | [Wilson et al., 2016] Wilson, A. G., Hu, Z., Salakhutdinov, R., and Xing, E. P. (2016). Deep kernel learning. In Gretton, A. and Robert, C. C., editors, Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, volume 51 of Proceedings of Machine Learning Research, pages 370–378, Cadiz, Spain. PMLR. | |
| dc.relation.references | [Xie and Richmond, 2018] Xie, Y. and Richmond, D. (2018). Pre-training on grayscale imagenet improves medical image classification. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. | |
| dc.relation.references | [Xu et al., 2024] Xu, Y., Quan, R., Xu, W., Huang, Y., Chen, X., and Liu, F. (2024). Advances in medical image segmentation: A comprehensive review of traditional, deep learning and hybrid approaches. Bioengineering, 11(10). | |
| dc.relation.references | [Yan et al., 2014] Yan, Y., Rosales, R., Fung, G., Subramanian, R., and Dy, J. (2014). Learning from multiple annotators with varying expertise. Machine Learning, 95(3):291–327. | |
| dc.relation.references | [Yu et al., 2025] Yu, J., Li, B., Pan, X., Shi, Z., Wang, H., Lan, R., and Luo, X. (2025). Semi-supervised gland segmentation via feature-enhanced contrastive learning and dual-consistency strategy. IEEE Journal of Biomedical and Health Informatics, pages 1–11. | |
| dc.relation.references | [Zhang, 2022] Zhang, J. (2022). Knowledge learning with crowdsourcing: A brief review and systematic perspective. IEEE/CAA Journal of Automatica Sinica, 9(5):749–762. | |
| dc.relation.references | [Zhang et al., 2020] Zhang, L., Tanno, R., Xu, M.-C., Jin, C., Jacob, J., Cicarrelli, O., Barkhof, F., and Alexander, D. (2020). Disentangling human error from ground truth in segmentation of medical images. In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H., editors, Advances in Neural Information Processing Systems, volume 33, pages 15750–15762. Curran Associates, Inc. | |
| dc.relation.references | [Zhang and Sabuncu, 2018] Zhang, Z. and Sabuncu, M. R. (2018). Generalized cross entropy loss for training deep neural networks with noisy labels. | |
| dc.relation.references | [Zhao et al., 2020] Zhao, R., Qian, B., Zhang, X., Li, Y., Wei, R., Liu, Y., and Pan, Y. (2020). Rethinking dice loss for medical image segmentation. In 2020 IEEE International Conference on Data Mining (ICDM), pages 851–860. | |
| dc.relation.references | [Zhou et al., 2021] Zhou, S. K., Greenspan, H., Davatzikos, C., Duncan, J. S., Van Ginneken, B., Madabhushi, A., Prince, J. L., Rueckert, D., and Summers, R. M. (2021). A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises. Proceedings of the IEEE, 109(5):820–838. | |
| dc.relation.references | [Zhou et al., 2024] Zhou, Z., Gong, H., Hsieh, S., McCollough, C. H., and Yu, L. (2024). Image quality evaluation in deep-learning-based ct noise reduction using virtual imaging trial methods: Contrast-dependent spatial resolution. Medical Physics, 51(8):5399–5413. | |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | |
| dc.rights.license | Reconocimiento 4.0 Internacional | |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
| dc.subject.ddc | 000 - Ciencias de la computación, información y obras generales | |
| dc.subject.proposal | Crowdsourcing | eng |
| dc.subject.proposal | Multiple annotators | eng |
| dc.subject.proposal | Histopathology | eng |
| dc.subject.proposal | Breast cancer | eng |
| dc.subject.proposal | Semantic image segmentation | eng |
| dc.subject.proposal | Gaussian process | eng |
| dc.subject.proposal | Deep learning | eng |
| dc.subject.proposal | Medical image analysis | eng |
| dc.subject.proposal | Múltiples anotadores | spa |
| dc.subject.proposal | Histopatología | spa |
| dc.subject.proposal | Cáncer de mama | spa |
| dc.subject.proposal | Segmentación semántica de imágenes | spa |
| dc.subject.proposal | Procesos Gaussianos | spa |
| dc.subject.proposal | Aprendizaje profundo | spa |
| dc.subject.proposal | Análisis de imágenes médicas | spa |
| dc.subject.unesco | Inteligencia artificial | |
| dc.subject.unesco | Artificial intelligence | |
| dc.subject.unesco | Análisis de datos | |
| dc.subject.unesco | Data analysis | |
| dc.title | Medical image segmentation in a multiple labelers context : application to the study of histopathology | eng |
| dc.title.translated | Segmentación de imágenes médicas en un contexto de múltiples anotadores : aplicación al estudio de histopatologías | spa |
| dc.type | Trabajo de grado - Maestría | |
| dc.type.coar | http://purl.org/coar/resource_type/c_bdcc | |
| dc.type.coarversion | http://purl.org/coar/version/c_ab4af688f83e57aa | |
| dc.type.content | Text | |
| dc.type.driver | info:eu-repo/semantics/masterThesis | |
| dc.type.version | info:eu-repo/semantics/acceptedVersion | |
| dcterms.audience.professionaldevelopment | Investigadores | |
| dcterms.audience.professionaldevelopment | Especializada | |
| oaire.accessrights | http://purl.org/coar/access_right/c_abf2 | |
| oaire.awardtitle | Sistema de visión artificial para el monitoreo y seguimiento de efectos analgésicos y anestésicos administrados vía neuroaxial epidural en población obstétrica durante labores de parto para el fortalecimiento de servicios de salud materna del Hospital Universitario de Caldas - SES HUC-Hermes-57661 | |
| oaire.fundername | Universidad Nacional de Colombia |
Archivos
Bloque original
1 - 1 de 1
Cargando...
- Nombre:
- Tesis de Maestría en Ingeniería - Automatización Industrial.pdf
- Tamaño:
- 15.73 MB
- Formato:
- Adobe Portable Document Format
- Descripción:
- Tesis de Maestría en Ingeniería - Automatización Industrial
Bloque de licencias
1 - 1 de 1
Cargando...
- Nombre:
- license.txt
- Tamaño:
- 5.74 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción:

