PhD defence
Automatic analysis of chest CT in systemic sclerosis using deep learning
- J. Jia
- Date
- Tuesday 10 September 2024
- Time
- Location
-
Academy Building
Rapenburg 73
2311 GJ Leiden
Supervisor(s)
- Prof.dr. M. Staring
- dr. B.C. Stoel
Summary
The aim of this thesis is to develop automatic methods focusing on quantifying disease severity of SSc disease based on CT images. We design two routes, direct and indirect, to achieve this aim. On the indirect route, we first obtain the segmentation of lungs, lobes and vessels by developing multi-task semi-supervised models. Then we estimate PFT based on the segmented vessels. On the direct route, we at first developed network for SSc-ILD scoring, which performed competitively with human experts and provides high-quality explanations. We also developed a 3D regression network which estimate PFTs directly from lung CT images. All the networks developed in this thesis have a runtime in the order of seconds, substantially improving over conventional methods. To summarize, deep learning has the powerful potential and a variety of applications on the automated analysis of chest CT in SSc.
PhD dissertations
Approximately one week after the defence, PhD dissertations by Leiden PhD students are available digitally through the Leiden Repository, that offers free access to these PhD dissertations. Please note that in some cases a dissertation may be under embargo temporarily and access to its full-text version will only be granted later.
Press enquiries (journalists only)
General information
Beadle's Office
pedel@bb.leidenuniv.nl
+31 71 527 7211