University of Twente Student Theses
Representing Ultra Low Dose CT scans as Chest X-Rays : how far can and do we need to go?
Paalvast, Olivier (2022) Representing Ultra Low Dose CT scans as Chest X-Rays : how far can and do we need to go?
|
PDF
71MB |
| Abstract: | This thesis focuses on the idea of replacing conventional chest radiography with Ultra Low-Dose Computed Tomography (ULDCT) imaging. For chest imaging specifically, the clinical value of ULDCT over the traditional Chest Radiograph (CXR) has been shown in multiple clinical areas. The primary objector to the use of ULDCT is the clinical interpretation time, which is on average ten times as long as the CXR interpretation time. This difference makes the widespread adoption of ULDCT imaging unfeasible at this point. Resolving this issue entirely goes beyond the scope of this thesis project. To direct my efforts, I have chosen to focus a number of promising methods related to the interpretation of ULDCT data. The goal of this thesis is therefore to investigate and develop methods which may aid in the interpretation of ULDCT imaging. One promising approach is to use Digitally Reconstructed Radiograph (DRR)s to provide a synthetic CXR of ULDCT data. The intuition here is that CXRs are faster to read, so therefore a DRR might be too. There has, however, been very limited research into the diagnostic value of DRRs. In this thesis I have investigated the manner in which DRRs can be used to create representative visualisations of ULDCT data. The goal in this has always been to approach the quality of the original CXR, not to match or surpass it. The DRR could be an ideal vessel to display summary information of an ULDCT scan in a format that is highly familiar to radiologists. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science MSc (60300) |
| Link to this item: | https://purl.utwente.nl/essays/93557 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page