Document type

Bachelor thesis

Publication date

Publication license

cc-by-nc-nd (c) Matas, 2025
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/223121

Automation of breast cancer dosimetry with Vision Transformers

Journal Title

Journal ISSN

Volume Title

Related resource

Abstract

A hybrid model combining a Vision Transformers encoder with convolutional layers is proposed for breast cancer dosimetry. Its predictions were compared with a baseline U-Net trained under the same conditions. The results suggest improved performance in OAR metrics, while maintaining acceptable accuracy in PTV dose prediction. However, no statistically significant differences were found, so further research is still needed to explore the full potential of Transformers in radiotherapy

Description

Treballs Finals de Grau de Física, Facultat de Física, Universitat de Barcelona, Curs: 2025, Tutors: Bruno Juliá Diaz, Pedro Gallego Franco

Citation

Citation

MATAS LÓPEZ, Ana. Automation of breast cancer dosimetry with Vision Transformers. [consulted: 18 of June of 2026]. Available at: https://hdl.handle.net/2445/223121

Export metadata

JSON - METS

Share record