Sfoglia per Autore  

Opzioni
Mostrati risultati da 1 a 1 di 1
Tipologia Anno Titolo Titolo inglese Autore File
Lauree magistrali 2024 AI Development on Rectal Cancer by using Medical Imaging. The growing incidence of rectal cancer has emphasized the need for advanced diagnostic and prognostic methodologies to enhance patient outcomes. This thesis shows the development of an artificial intelligence (AI) system that is designed to analyze rectal cancer through medical imaging. The process begins with using of 3D Slicer software for the precise identification and segmentation of tumor regions in medical images, including MRI and CT scans. This segmentation provides detailed anatomical information necessary for subsequent analytical stages. Following segmentation, a deep learning model is provided to predict various tumor characteristics such as stage, aggressiveness, and potential therapeutic response. The deep learning framework is based on convolutional neural networks (CNNs), selected for their superior performance in image analysis tasks. The model is trained and validated using a comprehensive dataset of annotated medical images, ensuring its robustness and generalizability across different patient populations. The synergy between 3D Slicer for accurate tumor identification and deep learning for predictive analytics aims to improve diagnostic precision and provide insightful prognostic information. This AI-driven approach aspires to assist clinicians in devising informed treatment strategies, thereby contributing to the advancement of personalized medicine in rectal cancer care. This research aims to demonstrate the potential of integrating advanced medical imaging techniques with AI to achieve more precise and efficient cancer management. The findings of this thesis offer a significant contribution to the field of oncology, particularly in rectal cancer, and highlight the importance of interdisciplinary collaboration in fostering medical innovation. FARMAN, AMIR MOHAMMAD
Mostrati risultati da 1 a 1 di 1
Legenda icone

  •  file ad accesso aperto
  •  file ad accesso riservato
  •  file sotto embargo
  •  nessun file disponibile