Automated brain tumor detection with artificial intelligence: a machine learning approach
This Final Master Project, "Automated Brain Tumor Detection with Artificial Intelligence: A Machine Learning Approach," focused on designing, implementing, and evaluating machine learning models for the automated detection and classification of brain tumours using MRI data. The cor...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Universitat Oberta de Catalunya (UOC) |
| Repositorio: | O2, repositorio institucional de la UOC |
| OAI Identifier: | oai:openaccess.uoc.edu:10609/153553 |
| Acceso en línea: | https://hdl.handle.net/10609/153553 |
| Access Level: | acceso abierto |
| Palabra clave: | machine learning image classification Machine learning -- TFM Aprenentatge automàtic -- TFM |
| Sumario: | This Final Master Project, "Automated Brain Tumor Detection with Artificial Intelligence: A Machine Learning Approach," focused on designing, implementing, and evaluating machine learning models for the automated detection and classification of brain tumours using MRI data. The core purpose was to enhance diagnostic accuracy, reduce human error, and improve patient outcomes. The implementation involved an iterative approach, starting with the development of several custom Convolutional Neural Networks (CNN1-4). These initial models progressively refined their architecture, introduced dynamic class weighting to address imbalance, and utilised data augmentation to establish a robust baseline. Building on these foundational efforts, the project transitioned to transfer learning models, beginning with ResNet50 and its enhanced variant (ResNet50 2), leveraging pre-trained weights for more sophisticated feature extraction. The project culminated in the Xception family of models (Xception 1-4), which demonstrated superior performance through successive advancements. |
|---|