Content-based image retrieval (CBIR) systems allow for retrieval of images from a database that are similar in visual content to a query image. This is particularly useful in scenarios such as digital pathology, where text-based descriptors alone might be inadequate to accurately describe image content. By representing images via a set of quantitative image descriptors, the similarity between a query image with respect to archived, annotated images in a database can be computed and the most similar images retrieved. Recently, non-linear dimensionality reduction (NLDR) methods have become popular for embedding high dimensional data into a reduced dimensional space while preserving local object adjacencies, thereby allowing for object similarity to be determined more accurately in the reduced dimensional space. However, most dimensionality reduction (DR) methods implicitly assume, in computing the reduced dimensional representation, that all features are equally important. Erroneous or noisy features could potentially result in dissimilar images being mapped close to each other in the reduced embedding space. In this work we present Boosted Spectral Embedding (BoSE), a variant of the traditional Spectral Embedding (SE) NLDR method, which unlike SE utilizes a boosted distance metric (BDM) to selectively weight individual features to subsequently map the data into a reduced dimensional space. In this work BoSE is evaluated against SE (which employs equal feature weighting) in the context of CBIR of digitized prostate and breast cancer histopathology images. Across 154 hematoxylin and eosin (H&E) stained histopathology images corresponding to benign and malignant prostate cancer biopsy images, low and high grade ER+ breast cancer studies, and HER2+ breast cancer H&E images, BoSE outperformed SE both in terms of CBIR-based (area under the precision recall curve) and classifier-based (classification accuracy) performance measures. Consistent trends were observed when embedding the data into spaces with different dimensions. Our results suggest that BoSE could serve as an important tool for CBIR and classification of high dimensional biomedical data.
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.