Theses and Dissertations from UMD

Permanent URI for this communityhttp://hdl.handle.net/1903/2

New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a give thesis/dissertation in DRUM

More information is available at Theses and Dissertations at University of Maryland Libraries.

Browse

Filters

2012 - 20172

Settings

Subject: search.filters.subject.Image segmentation

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Multimodal Biomedical Data Visualization: Enhancing Network, Clinical, and Image Data Depiction
    (2017) Cheng, Hsueh-Chien; Varshney, Amitabh; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    In this dissertation, we present visual analytics tools for several biomedical applications. Our research spans three types of biomedical data: reaction networks, longitudinal multidimensional clinical data, and biomedical images. For each data type, we present intuitive visual representations and efficient data exploration methods to facilitate visual knowledge discovery. Rule-based simulation has been used for studying complex protein interactions. In a rule-based model, the relationships of interacting proteins can be represented as a network. Nevertheless, understanding and validating the intended behaviors in large network models are ineffective and error prone. We have developed a tool that first shows a network overview with concise visual representations and then shows relevant rule-specific details on demand. This strategy significantly improves visualization comprehensibility and disentangles the complex protein-protein relationships by showing them selectively alongside the global context of the network. Next, we present a tool for analyzing longitudinal multidimensional clinical datasets, that we developed for understanding Parkinson's disease progression. Detecting patterns involving multiple time-varying variables is especially challenging for clinical data. Conventional computational techniques, such as cluster analysis and dimension reduction, do not always generate interpretable, actionable results. Using our tool, users can select and compare patient subgroups by filtering patients with multiple symptoms simultaneously and interactively. Unlike conventional visualizations that use local features, many targets in biomedical images are characterized by high-level features. We present our research characterizing such high-level features through multiscale texture segmentation and deep-learning strategies. First, we present an efficient hierarchical texture segmentation approach that scales up well to gigapixel images to colorize electron microscopy (EM) images. This enhances visual comprehensibility of gigapixel EM images across a wide range of scales. Second, we use convolutional neural networks (CNNs) to automatically derive high-level features that distinguish cell states in live-cell imagery and voxel types in 3D EM volumes. In addition, we present a CNN-based 3D segmentation method for biomedical volume datasets with limited training samples. We use factorized convolutions and feature-level augmentations to improve model generalization and avoid overfitting.
  • Thumbnail Image
    Item
    THE IMAGE TORQUE OPERATOR FOR MID-LEVEL VISION: THEORY AND EXPERIMENT
    (2012) Nishigaki, Morimichi; Aloimonos, Yiannis; Fermuller, Cornelia; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    A problem central to visual scene understanding and computer vision is to extract semantically meaningful parts of images. A visual scene consists of objects, and the objects and parts of objects are delineated from their surrounding by closed contours. In this thesis a new bottom-up visual operator, called the Torque operator, which captures the concept of closed contours is introduced. Its computation is inspired by the mechanical definition of torque or moment of force, and applied to image edges. It takes as input edges and computes over regions of different size a measure of how well the edges are aligned to form a closed, convex contour. The torque operator is by definition scale independent, and can be seen as an operator of mid-level vision that captures the organizational concept of 'closure' and grouping mechanism of edges. In this thesis, fundamental properties of the torque measure are studied, and experiments are performed to demonstrate and verify that it can be made a useful tool for a variety of applications, including visual attention, segmentation, and boundary edge detection.