Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Diposit Digital de l...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
Recolector de Ciencia Abierta, RECOLECTA
Bachelor thesis . 2025
License: CC BY NC ND
versions View all 2 versions
addClaim

Clasificación de densidad mamaria utilizando Aprendizaje Profundo

Authors: Cantero López, Alejandro;

Clasificación de densidad mamaria utilizando Aprendizaje Profundo

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.

Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2025, Director: Laura Igual Muñoz

Country
Spain
Related Organizations
Keywords

Programari, Breast cancer, Xarxes neuronals convolucionals, Deep learning (Machine learning), Bachelor's theses, Convolutional neural networks, Treballs de fi de grau, Computer software, Mamografia, Càncer de mama, Aprenentatge profund, Mammography

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green
Related to Research communities
Cancer Research