Rangelov, Bojidar Alexandrov;
(2025)
Discovering Imaging Biomarkers of Chronic Obstructive Pulmonary Disease.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Bojidar_Rangelov_Thesis.pdf - Accepted Version Download (54MB) | Preview |
Abstract
Chronic obstructive pulmonary disease (COPD) is a progressive disease that affects nearly 400 million people and is the third leading cause of death worldwide. Development of novel drugs for COPD is lagging while diagnosis and staging is still driven by unspecific spirometry measurements. Medical imaging, in the form of high-resolution computed tomography (HRCT), is rarely included in the workup of COPD but can provide a rich array of imaging biomarkers (IBs) which could aid disease staging and management, as well as define exacerbations of COPD (acute episodes of disease worsening) directly from imaging. This thesis delivers novel medical image analysis and machine learning techniques to model the progression of stable COPD and attempt to define an imaging signature of exacerbations of COPD. First, a disease progression model, SuStaIn, was used in a large cohort of patients with stable COPD to discover two clinically important phenotypes (AirwayTissue and TissueAirway) that had distinct progression patterns. SuStaIn was then adapted to model infection of COVID-19 on a cohort of patients from the NCCID study: three COVID-19 phenotypes were discovered, which had different in-hospital outcomes. A systematic review was then conducted to identify candidates for the imaging biomarkers of exacerbations of COPD – this produced a list of anatomical structures within the thorax, which could exhibit changes during exacerbation. A novel automatic pipeline of segmentation and quantification techniques was developed to extract the potential imaging signature of exacerbation of COPD. The segmentation techniques produced state-of-the-art results in two segmentation competitions. Finally, the pipeline was used on a small dataset of patients scanned during exacerbation to quantify changes in their biomarkers upon recovery from exacerbation. The results for the majority of IBs were not significant, but still represent an important clinical finding and motivate additional investigation into the imaging definition of exacerbations of COPD.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Discovering Imaging Biomarkers of Chronic Obstructive Pulmonary Disease |
| 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 UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Chemical Engineering |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10203523 |
Loading...
Loading...Loading...| 1. |  United Kingdom | 6 |
| 2. |  China | 1 |
| 3. |  Israel | 1 |
Archive Staff Only
 |
View Item |
