Document type
Bachelor thesisPublication date
Publication license
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/223697
Clasificación de densidad mamaria utilizando Aprendizaje Profundo
Journal Title
Authors
Director/Tutor
Journal ISSN
Volume Title
Related resource
Abstract
La densidad mamaria es un factor clínico relevante en la detección del cáncer de mama, ya que influye tanto en la dificultad de identificar lesiones en las mamografías como en el riesgo asociado al desarrollo de esta enfermedad. Una mayor densidad implica un aumento tanto en la complejidad del diagnóstico por imagen como en la probabilidad de padecer cáncer mamario.
En los últimos años, el avance tecnológico ha permitido integrar herramientas de inteligencia artificial en el ámbito médico, con el objetivo de mejorar la precisión diagnóstica y apoyar la labor de los profesionales de la salud. En este contexto, el aprendizaje automático, y en particular las redes neuronales convolucionales, han demostrado ser especialmente eficaces en tareas de análisis de imágenes médicas.
Este trabajo tiene como objetivo desarrollar un modelo de aprendizaje automático capaz de clasificar mamografías según su densidad mamaria.
Para ello, se ha implementado una red neuronal convolucional basada en la arquitectura DenseNet-121, utilizando el lenguaje de programación Python. El modelo ha sido entrenado y evaluado empleando dos bases de
datos públicas de mamografías, con el fin de analizar el comportamiento en una tarea de clasificación multiclase que presenta variabilidades técnicas y subjetividad clínica.
Breast density is a clinically relevant factor in the detection of breast cancer, as it influences both the difficulty of identifying lesions in mammograms and the risk associated with the development of the disease. Higher breast density increases not only the complexity of image-based diagnosis but also the likelihood of developing breast cancer. In recent years, technological advances have enabled the integration of artificial intelligence tools into the medical field, aiming to improve diagnostic accuracy and support the work of healthcare professionals. In this con- text, machine learning —particularly convolutional neural networks— has proven especially effective in medical image analysis tasks. This project aims to develop a machine learning model capable of classifying mammograms according to breast density. To achieve this, a convolutional neural network based on the DenseNet-121 architecture has been implemented using the Python programming language. The model has been trained and evaluated using two public mammography datasets, in order to analyze its performance in a multiclass classification task characterized by technical variability and clinical subjectivity.
Breast density is a clinically relevant factor in the detection of breast cancer, as it influences both the difficulty of identifying lesions in mammograms and the risk associated with the development of the disease. Higher breast density increases not only the complexity of image-based diagnosis but also the likelihood of developing breast cancer. In recent years, technological advances have enabled the integration of artificial intelligence tools into the medical field, aiming to improve diagnostic accuracy and support the work of healthcare professionals. In this con- text, machine learning —particularly convolutional neural networks— has proven especially effective in medical image analysis tasks. This project aims to develop a machine learning model capable of classifying mammograms according to breast density. To achieve this, a convolutional neural network based on the DenseNet-121 architecture has been implemented using the Python programming language. The model has been trained and evaluated using two public mammography datasets, in order to analyze its performance in a multiclass classification task characterized by technical variability and clinical subjectivity.
Description
Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2025, Director: Laura Igual Muñoz
Citation
Citation
CANTERO LÓPEZ, Alejandro. Clasificación de densidad mamaria utilizando Aprendizaje Profundo. [consulted: 16 of June of 2026]. Available at: https://hdl.handle.net/2445/223697