Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/151595
Title: Gathering AI solutions for building a meta-AI tool for chest X-Ray COVID- 19 diagnosis
Author: Abad Vazquez, Maider  
Director: Casas-Roma, Jordi  
Prados Carrasco, Ferran  
Abstract: Artificial intelligence (AI) is revolutionizing medical imaging by improving diagnostics, although it faces significant barriers to implementation. This thesis proposes overcoming these challenges through computer vision techniques that enhance data quality and model robustness. Experiments have been conducted focusing on domain adaptation, which is essential for models to operate effectively in different contexts. Additionally, Generative Adversarial Networks (GANs) are employed for data augmentation, and open-set models are utilized to ensure data quality. Ensemble methods have also been developed to combine decisions from multiple models, optimizing predictions based on entropy and dynamically adapting to the origin of the images. The models have been evaluated on public and private datasets, demonstrating substantial improvements in diagnostic accuracy compared to current methods. These innovations.
Keywords: artificial intelligence
computer vision
image preprocessing
medical imaging
domain adaptation
ensemble methods
Document type: info:eu-repo/semantics/doctoralThesis
Issue Date: 20-Dec-2024
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Tesis doctorals

Files in This Item:
File Description SizeFormat 
PhD_Maider_Abad_última versión.pdf
  Until 2025-12-21
Abad_Vazquez_dissertation19,97 MBAdobe PDFView/Open Request a copy
Share:
Export:
View statistics

This item is licensed under aCreative Commons License Creative Commons