DOI
https://doi.org/10.25772/E34K-F967
Defense Date
2010
Document Type
Dissertation
Degree Name
Doctor of Philosophy
Department
Computer Science
First Advisor
Kayvan Najarian
Abstract
In the past decades, technical advances have allowed for the collection and storage of more types and larger quantities of medical data. The increase in the volume of existing medical data has increased the need for processing and analyzing such data. Medical data holds information that is invaluable for diagnostic as well as treatment planning purposes. Presently, a large portion of the data is not optimally used towards medical decisions because information contained in the data is inaccessible through simple human inspection, or traditional computational methods. In the field of trauma medicine, where caregivers are frequently confronted with situations where they need to make rapid decisions based on large amounts of information, the need for reliable, fast and automated computational methods for decision support systems is stringent. Such methods could process and analyze, in a timely fashion, all available medical data and provide caretakers with recommendations/predictions for both patient diagnostic and treatment planning. Presently however, even extracting features that are known to be useful for diagnosis, like presence and location of hemorrhage and fracture, is not easily achievable in automatic manner. Trauma is the main cause of death among Americans age 40 and younger; hence, it has become a national priority. A computer-aided decision making system capable of rapidly analyzing all data available for a patient and forming reliable recommendations for physicians can greatly impact the quality of care provided to patients. Such a system would also reduce the overall costs involved in patient care as it helps in optimizing the decisions, avoiding unnecessary procedures, and customizing treatments for individual patients. Among different types of trauma with a high impact on the lives of Americans, traumatic pelvic injuries, which often occur in motor vehicle accidents and in falls, have had a tremendous toll on both human lives and healthcare costs in the United States. The present project has developed automated computational methods and algorithms to analyze pelvic CT images and extract significant features describing the severity of injuries. Such a step is of great importance as every CT scan consists of tens of slices that need to be closely examined. This method can automatically extract information hidden in CT images and therefore reduce the time of the examination. The method identifies and signals areas of potential abnormality and allows the user to decide upon the action to be taken (e.g. further examination of the image and/or area and neighboring images in the scan). The project also initiates the design of a system that combines the features extracted from biomedical signals and images with information such as injury scores, injury mechanism and demographic information in order to detect the presence and the severity of Traumatic Pelvic Injuries and to provide recommendations for diagnosis and treatment. The recommendations are provided in form of grammatical rules, allowing physicians to explore the reasoning behind these assessments.
Rights
© The Author
Is Part Of
VCU University Archives
Is Part Of
VCU Theses and Dissertations
Date of Submission
May 2010