Show simple item record

dc.contributor.advisor Rao, Arvind
dc.contributor.advisor Veeraraghavan, Ashok
dc.creatorYang, Dalu
dc.date.accessioned 2017-08-01T16:43:46Z
dc.date.available 2017-08-01T16:43:46Z
dc.date.created 2016-12
dc.date.issued 2017-06-23
dc.date.submitted December 2016
dc.identifier.citation Yang, Dalu. "Identifying and Predicting Molecular Signatures in Glioblastoma Using Imaging-Derived Phenotypic Traits." (2017) Master’s Thesis, Rice University. https://hdl.handle.net/1911/96026.
dc.identifier.urihttps://hdl.handle.net/1911/96026
dc.description.abstract This thesis addresses the problem of linking molecular status of glioblastoma patients with imaging-derived phenotypic traits. Glioblastoma (GBM) is the most common and aggressive type of malignant brain tumor, with a median survival of only 12-15 months. Due to GBM’s complex heterogeneity in gene expression, the responses to current treatment strategy varies considerably among different patients. There is an urgent need for a deeper understanding of tumor biology and alternative personalized therapeutic intervention. Magnetic Resonance Imaging (MRI) and histologic images are routinely used for GBM diagnosis. A natural question to ask is that if the phenotypic tumor traits from these images can be linked to tumor molecular signatures. In this thesis, we explore the imaging-genomic relationship in GBM via three approaches. The first approach aims to find texture features extracted from the MRI images that best discriminate GBM molecular subtypes. The second approach aims to find gene networks that determines the radiologically-defined tumor sub-compartment volumes. The third approach aims to quantify GBM histologic hallmarks and correlate them with biological pathway activities. Our study shows that linking imaging traits with tumor molecular status can lead to discoveries that have potential clinical relevance and provide biological insight.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.subjectimaging-genomics
glioblastoma
molecular programs
computer vision
dc.title Identifying and Predicting Molecular Signatures in Glioblastoma Using Imaging-Derived Phenotypic Traits
dc.type Thesis
dc.date.updated 2017-08-01T16:43:46Z
dc.type.material Text
thesis.degree.department Electrical and Computer Engineering
thesis.degree.discipline Engineering
thesis.degree.grantor Rice University
thesis.degree.level Masters
thesis.degree.name Master of Science


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record