Dijous 11 de juny, el Dipòsit Digital no estarà operatiu de 15:00 a 17:00 h per tasques de manteniment. Disculpeu les molèsties.
El jueves 11 de Junio, el Dipòsit Digital no estará operativo de 15:00 a 17:00 h debido a tareas de mantenimiento. Disculpen las molestias.
Thursday, Jun 11th, the Digital Repository will be unavailable due to a system update.

Document type

Bachelor thesis

Publication date

Publication license

cc-by-nc-nd (c) Guo, 2024
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/222247

Advances in Diagnostic Imaging: Integrating Explainable AI to Optimize Convolutional Networks

Journal Title

Journal ISSN

Volume Title

Related resource

Abstract

Convolutional neural networks (CNNs) are fundamental in deep learning, especially in computer vision tasks.They stand out for their ability to extract spatial features from data. However,their complexity has generated the need for explainability in artificial intelligence (XAI), which seeks to interpret and understand their predictions.This work is carried out with the purpose of knowing the applicability of convolutional networks in the classification of Medical images,specifically, endoscopi images already previously collected, and through fine-tunning we will explore architectures that present better performance. Afterwards, we implement the AI explainability techniques,together with the Language model we will assess the process of automating the creation of the medical report through the graphic representations created.

Description

Treballs Finals de Grau en Estadística UB-UPC, Facultat d'Economia i Empresa (UB) i Facultat de Matemàtiques i Estadística (UPC), Curs: 2023-2024, Tutor: Esteban Vegas Lozano

Citation

Citation

GUO, Xiuchao. Advances in Diagnostic Imaging: Integrating Explainable AI to Optimize Convolutional Networks. [consulted: 10 of June of 2026]. Available at: https://hdl.handle.net/2445/222247

Export metadata

JSON - METS

Share record