Thesis Project Form
Title (tentative): Adding the temporal domain in [18F]F-DOPA PET radiomic features derived in paediatric gliomas| Thesis advisor(s): Trò Rossella | E-mail: |
| Address: | Phone: |
Description
Motivation and application domain
Radiomic features extracted from positron emission tomography (PET) scans are used to characterise tumour biology by quantifying radiotracer
intensity, lesion morphology and uptake heterogeneity. Traditionally, these features are derived from static images. However, incorporating the temporal dimension of tracer uptake could provide further insight into tumour behaviour and biology
intensity, lesion morphology and uptake heterogeneity. Traditionally, these features are derived from static images. However, incorporating the temporal dimension of tracer uptake could provide further insight into tumour behaviour and biology
General objectives and main activities
This study will analyse [18F]F DOPA PET/CT scans
of paediatric gliomas to calculate radiomic features in static images and textural information in dynamic images. This study aims to develop a tool for calculating textural matrices from dynamic [18F]F-DOPA PET scans and deriving features. The study will investigate the added value of dynamic radiomic features compared to those derived from static images
of paediatric gliomas to calculate radiomic features in static images and textural information in dynamic images. This study aims to develop a tool for calculating textural matrices from dynamic [18F]F-DOPA PET scans and deriving features. The study will investigate the added value of dynamic radiomic features compared to those derived from static images
Training Objectives (technical/analytical tools, experimental methodologies)
Gain expertise in the preprocessing of PET imaging and the extraction of data and radiomic features, specifically from static and dynamic [18F] F-DOPA PET. Conduct a study on the robustness of the extracted features. They will use Python for coding
Place(s) where the thesis work will be carried out: Neuroengineering Lab
Additional information
Pre-requisite abilities/skills: coding skills
Maximum number of students: 1