Geometric Deep Learning for Healthcare Applications

Simple item page
dc.contributor.authorKarwande, Gaurang Ajiten
dc.contributor.committeechairJones, Creed F. IIIen
dc.contributor.committeechairLourentzou, Isminien
dc.contributor.committeememberAbbott, Amos L.en
dc.contributor.departmentElectrical and Computer Engineeringen
dc.date.accessioned2023-06-07T08:01:02Zen
dc.date.available2023-06-07T08:01:02Zen
dc.date.issued2023-06-06en
dc.description.abstractThis thesis explores the application of Graph Neural Networks (GNNs), a subset of Geometric Deep Learning methods, for medical image analysis and causal structure learning. Tracking the progression of pathologies in chest radiography poses several challenges in anatomical motion estimation and image registration as this task requires spatially aligning the sequential X-rays and modelling temporal dynamics in change detection. The first part of this thesis proposes a novel approach for change detection in sequential Chest X-ray (CXR) scans using GNNs. The proposed model CheXRelNet utilizes local and global information in CXRs by incorporating intra-image and inter-image anatomical information and showcases an increased downstream performance for predicting the change direction for a pair of CXRs. The second part of the thesis focuses on using GNNs for causal structure learning. The proposed method introduces the concept of intervention on graphs and attempts to relate belief propagation in Bayesian Networks (BN) to message passing in GNNs. Specifically, the proposed method leverages the downstream prediction accuracy of a GNN-based model to infer the correctness of Directed Acyclic Graph (DAG) structures given observational data. Our experimental results do not reveal any correlation between the downstream prediction accuracy of GNNs and structural correctness and hence indicate the harms of directly relating message passing in GNNs to belief propagation in BNs. Overall, this thesis demonstrates the potential of GNNs in medical image analysis and highlights the challenges and limitations of applying GNNs to causal structure learning.en
dc.description.abstractgeneralGraphs are a powerful way to represent different real-world data such as interactions between patient observations, co-morbidities, treatments, and relationships between different parts of the human anatomy. They are also a simple and intuitive way of representing causeand- effect relationships between related entities. Graph Neural Networks (GNNs) are neural networks that model such graph-structured data. In this thesis, we explore the applicability of GNNs in analyzing chest radiography and in learning causal relationships. In the first part of this thesis, we propose a method for monitoring disease progression over time in sequential chest X-rays (CXRs). This proposed model CheXRelNet focuses on the interactions within different regions of a CXR and temporal interactions between the same region compared in two CXRs taken at different times for a given patient and accurately predicts the disease progression trend. In the second part of the thesis, we explore if GNNs can be used for identifying causal relationships between covariates. We design a method that uses GNNs for ranking different graph structures based on how well the structures explain the observed data.en
dc.description.degreeMaster of Scienceen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:37300en
dc.identifier.urihttp://hdl.handle.net/10919/115361en
dc.language.isoenen
dc.publisherVirginia Techen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectGraph Neural Networksen
dc.subjectMedical Imagingen
dc.subjectCausal Structure Learningen
dc.subjectBayesian Networksen
dc.titleGeometric Deep Learning for Healthcare Applicationsen
dc.typeThesisen
thesis.degree.disciplineComputer Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Karwande_GA_T_2023.pdf
Size:
2.61 MB
Format:
Adobe Portable Document Format
Download

Collections

Masters Theses