Stavropoulou, Kyriaki Alkisti;
(2025)
Image-Based Analysis of Radiation Induced Lung Damage.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Stavropoulou_10206475_Thesis.pdf Download (72MB) | Preview |
Abstract
This thesis addresses the underexplored and complex issue of Radiation-Induced Lung Damage (RILD) resulting from radiotherapy (RT) in the thorax. RT is a common treatment for many cancers in the thorax, such as lung cancers, breast cancers, oesophageal cancers, and more, but it can lead to severe negative side effects in the highly radiosensitive lung tissue. Motivated by the need for a deeper understanding of the long-term effects of RT on lung tissue, particularly the progression from acute pneumonitis to chronic fibrosis, the work seeks to fill gaps in current methodologies that often rely on small datasets and simplified dose-response relationships. The aim is to develop quantitative tools for analyzing the temporal evolution of RILD and its relationship with radiotherapy dose, across diverse patient cohorts. In this thesis, the focus has been placed on non-small cell lung cancer (NSCLC) patients, who are at high risk of developing RILD due to the proximity of the lung to the tumor site. The primary contributions include the creation of a novel, automated pipeline for the longitudinal analysis of lung CT images. This pipeline integrates image registration and segmentation techniques, enabling large-scale processing of complex datasets with minimal user intervention. A feature-based registration framework is presented, which aligns longitudinal scans even in the presence of significant anatomical changes. Additionally, the study explores the dose-tissue relationship in RILD, providing novel insights into its time-evolution, from acute to chronic stages. The pipeline was validated on two distinct datasets, offering a robust platform for future research on radiation-induced lung damage, with the potential to enhance RT planning and improve patient outcomes. This work represents a significant step forward in automated medical image analysis for RILD, offering new opportunities to improve clinical understanding and management of radiation-induced toxicity in lung cancer patients.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Image-Based Analysis of Radiation Induced Lung Damage |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2025. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10206475 |
Archive Staff Only
 |
View Item |
