The problem of data integration involving imaging and non-imaging modalities is largely unexplored in the biomedical eld, mainly due to the challenges in quantitatively combining such heterogeneous modalities existing in diff erent dimensions and scales. Although several methods have been proposed in the literature involving quantitative integration of multi-protocol imaging, there has been a paucity of similar biomedical tools for quantitative integration of imaging and non-imaging data. In this work, we present novel data integration schemes to overcome the aforementioned challenges limiting the integration of imaging and non-imaging modalities, and hence improve disease characterization. Our novel data integration methods are applied to integration of multi-parametric Magnetic Resonance (MR) imaging (MP-MRI)-structural MR imaging with metabolic spectroscopic information (non-imaging) for improved prostate cancer (CaP) diagnosis, grading, and treatment evaluation post-radiation therapy (RT). To this end, we have developed novel data integration schemes such as, Multimodal Wavelet Embedding Representation for data Combination (MaWERiC), and Semi-Supervised Multi-Kernel (SeSMiK) Graph Embedding, which fi rst uniformly represent individual data modalities into a common framework using dimensionality reduction and kernel embedding techniques, followed by a seamless integration of imaging and non-imaging data in the common framework. The integrated quantitative signatures thus obtained are shown to be signifi cantly more diagnostically informative as compared to any single modality. Similar improvement in results was observed using integrated MP-MRI signatures for evaluating radiation therapy related changes in CaP patients, with an aim to identify (a) pre-RT disease extent along with extra capsule spread (if any) and (b) residual disease on post-RT MP-MRI.
Subject (authority = RUETD)
Topic
Biomedical Engineering
RelatedItem (type = host)
TitleInfo
Title
Rutgers University Electronic Theses and Dissertations
Rutgers University. Graduate School - New Brunswick
AssociatedObject
Type
License
Name
Author Agreement License
Detail
I hereby grant to the Rutgers University Libraries and to my school the non-exclusive right to archive, reproduce and distribute my thesis or dissertation, in whole or in part, and/or my abstract, in whole or in part, in and from an electronic format, subject to the release date subsequently stipulated in this submittal form and approved by my school. I represent and stipulate that the thesis or dissertation and its abstract are my original work, that they do not infringe or violate any rights of others, and that I make these grants as the sole owner of the rights to my thesis or dissertation and its abstract. I represent that I have obtained written permissions, when necessary, from the owner(s) of each third party copyrighted matter to be included in my thesis or dissertation and will supply copies of such upon request by my school. I acknowledge that RU ETD and my school will not distribute my thesis or dissertation or its abstract if, in their reasonable judgment, they believe all such rights have not been secured. I acknowledge that I retain ownership rights to the copyright of my work. I also retain the right to use all or part of this thesis or dissertation in future works, such as articles or books.