Predicting Liver Segmentation Model Failure with Feature-Based Out-of-Distribution Detection and Generative Adversarial Networks

Simple item page
dc.contributor.advisorPatel, Ankit Ben_US
dc.contributor.advisorJermaine, Christopher Men_US
dc.contributor.advisorBrock, Kristy Ken_US
dc.creatorWoodland, McKellen_US
dc.date.accessioned2024-08-30T18:33:19Zen_US
dc.date.available2024-08-30T18:33:19Zen_US
dc.date.created2024-08en_US
dc.date.issued2024-08-07en_US
dc.date.submittedAugust 2024en_US
dc.date.updated2024-08-30T18:33:19Zen_US
dc.description.abstractAdvanced liver cancer is often treated with radiotherapy, which requires precise liver segmentation. Deep learning models excel at segmentation but struggle on unseen data, a problem exacerbated by the difficulty of amassing large datasets in medical imaging. Clinicians manually correct these errors, but as models improve, the risk of clinicians overlooking mistakes due to automation bias increases. To ensure quality care for all patients, this thesis aims to offer automated, scalable, and interpretable solutions for detecting liver segmentation model failures. My first approach prioritized performance and scalability. It applied the Mahalanobis distance (MD) to the features of four Swin UNETR and nnU-net liver segmentation models. I proposed reducing the dimensionality of these features with either principal component analysis (PCA) or uniform manifold approximation and projection (UMAP), resulting in improved performance and efficiency. Additionally, I proposed a k-th nearest neighbors distance (KNN) as a non-parametric alternative to the MD for medical imaging. KNN drastically improved scalability and performance on raw and average-pooled bottleneck features. My second approach emphasized interpretability by introducing generative modeling for the localization of novel information that a model will fail on. It employed a StyleGAN2 network to model a distribution of 3,234 abdominal computed tomography exams (CTs). It then localized metal artifacts and abnormal fluid buildup, two prevalent causes of liver segmentation model failure, in 55 CTs by reconstructing the scans with backpropagation on the StyleGAN’s input space and focusing on the regions with the highest reconstruction errors. The computational cost, data requirements, and training complexity of generative adversarial networks, along with a lack of reliable evaluation measures, have impeded their application to medical imaging. Accordingly, a significant portion of this thesis is dedicated to evaluating the applications of StyleGAN2 and the Fréchet Inception Distance (FID), a common measure of synthetic image quality, to medical imaging. The principal contributions of this thesis are integrating PCA and UMAP with MD, utilizing KNN for out-of-distribution detection in medical imaging, leveraging generative modeling to localize novel information at inference, providing a comprehensive application study of StyleGAN2 to medical imaging, and challenging prevailing assumptions about the FID in medical imaging.en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationWoodland, McKell. Predicting Liver Segmentation Model Failure with Feature-Based Out-of-Distribution Detection and Generative Adversarial Networks. (2024). PhD diss., Rice University. https://hdl.handle.net/1911/117832en_US
dc.identifier.urihttps://hdl.handle.net/1911/117832en_US
dc.language.isoengen_US
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.subjectout-of-distribution detectionen_US
dc.subjectanomaly detectionen_US
dc.titlePredicting Liver Segmentation Model Failure with Feature-Based Out-of-Distribution Detection and Generative Adversarial Networksen_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentComputer Scienceen_US
thesis.degree.disciplineEngineeringen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelDoctoralen_US
thesis.degree.nameDoctor of Philosophyen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
WOODLAND-DOCUMENT-2024.pdf
Size:
10.74 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.98 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Theses and Dissertations