Amb motiu del tancament d'estiu, la validació de documents es reprendrà a partir del 28 d'agost de 2026. Disculpeu les molèsties.
Con motivo del cierre de verano, la validación de documentos se reanudará a partir del 28 de agosto de 2026. Disculpad las molestias
Due to the summer closure, document validation will resume starting August 28, 2026. We apologize for any inconvenience.

Document type

Bachelor thesis

Publication date

Publication license

memòria: cc-nc-nd (c) Joan Ramiro Bolívar, 2022
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/187162

Predicció resposta al tractament de càncer de mama

Journal Title

Director/Tutor

Journal ISSN

Volume Title

Related resource

Abstract

[en] Breast cancer is the most widely diagnosed cancer, if it is detected in their early stages, it has a hight survival rate, 85 % if it is in the first stage. That’s why it is so important to act by early detection and choosing the best treatment to give to the patient. The aim of this study is to predict the complete pathological response of the patient, the prediction of their total care. To achieve it, a deep learning model will be developed, which by patient data and the magnetic ressonance image that is taken to him when the tumor is detected, will try to predict his pathological response. These data have been obtained thanks to the collaboration of the Hospital Parc Taulí in Sabadell, which provided it. The results obtained show potential although the model developed has not been as complex as it was intended from the beginning due to the lack of greater computing power. That’s why it would be a great idea to continue working in this field when having the necessary tools to be able to develop a model with greater complexity.

Description

Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2022, Director: Oliver Díaz

Citation

Citation

RAMIRO BOLÍVAR, Joan. Predicció resposta al tractament de càncer de mama. [consulted: 19 of August of 2026]. Available at: https://hdl.handle.net/2445/187162

Export metadata

JSON - METS

Share record