Spelling suggestions: "subject:"image analysis"" "subject:"lmage analysis""
91 |
Image analysis techniques for classification of pulmonary disease in cattleMiller, C. Denise 13 September 2007 (has links)
Histologic analysis of tissue samples is often a critical step in the diagnosis of disease. However, this type of assessment is inherently subjective, and consequently a high degree of variability may occur between results produced by different pathologists. Histologic analysis is also a very time-consuming task for pathologists. Computer-based quantitative analysis of tissue samples shows promise for both reducing the subjectivity of traditional manual tissue assessments, as well as potentially reducing the time required to analyze each sample. <p>The objective of this thesis project was to investigate image processing techniques and to develop software which could be used as a diagnostic aid in pathology assessments of cattle lung tissue samples. The software examines digital images of tissue samples, identifying and highlighting the presence of a set of features that indicate disease, and that can be used to distinguish various pulmonary diseases from one another. The output of the software is a series of segmented images with relevant disease indicators highlighted, and measurements quantifying the occurrence of these features within the tissue samples. Results of the software analysis of a set of 50 cattle lung tissue samples were compared to the detailed manual analysis of these samples by a pathology expert.<p>The combination of image analysis techniques implemented in the thesis software shows potential. Detection of each of the disease indicators is successful to some extent, and in some cases the analysis results are extremely good. There is a large difference in accuracy rates for identification of the set of disease indicators, however, with sensitivity values ranging from a high of 94.8% to a low of 22.6%. This wide variation in result scores is partially due to limitations of the methodology used to determine accuracy.
|
92 |
Computer-Assisted Image Analysis of Human Ovarian Follicles: Imaging Physiologic SelectionRezaeisarlak, Elham 06 August 2009 (has links)
Antral ovarian folliculogenesis involves recruitment of a cohort of small follicles, physiological selection of a dominant follicle, and ovulation. The mechanism of selection has not been precisely determined. Identification of the timing of preovulatory selection is a key component in understanding natural and peri-menopausal ovarian function, ovarian suppression for contraception, and improvement of ovarian stimulation protocols. Morphologic characteristics obtained by ultrasonography cannot be precisely quantitated by the human eye. Computer-assisted image analysis overcomes subjective human evaluation of ultrasonographic images.<p>
The objectives of this research were to assess ultrasound image attributes of human dominant (DF) and 1st subordinate (SF1) ovarian follicles during natural menstrual cycles and following discontinuation of conventional and continuous oral contraceptives (OC). We utilized sophisticated computer algorithms to elucidate an association between image attributes and physiologic status of follicles. Transvaginal ultrasonographic images obtained in 2 previous studies were used to quantify changes that occur in ovarian follicles.<p>
We detected quantitative differences between the dominant and largest subordinate follicles of ovulatory and major anovulatory follicular waves, as well as during the first wave following OC discontinuation. Differences in ultrasonographic image attributes were associated with the physiological status of follicles. Evidence of follicular dominance in follicles which develop during major ovulatory waves or following OC discontinuation can be detected prior to the time of selection manifest by differences in dominant and subordinate follicle diameters. In addition, differences in quantitative image attributes were detected between ovulatory and anovulatory DF. Follicles that develop following conventional and continuous OC administration schemes exhibit the same image characteristics.<p>
Further research is necessary to elucidate the exact correlation of follicle image attributes during all stages of development with histological characteristics, prediction of the timing of DF selection and the effects of different OC formulations on follicle development during and following OC cessation. Computer-assisted image analysis of ultrasound images has the potential to develop into a diagnostic, prognostic, and research tool for the in vivo evaluation of ovarian physiology and pathology and elucidate biologically important times such as physiologic selection, ovulation of DF and characterization of abnormal follicles (i.e., follicular cysts, luteinized unovulated follicles).
|
93 |
Pose Recognition for Tracker Initialization Using 3D ModelsBerg, Martin January 2008 (has links)
<p>In this thesis it is examined whether the pose of an object can be determined by a system trained with a synthetic 3D model of said object. A number of variations of methods using P-channel representation are examined. Reference images are rendered from the 3D model, features, such as gradient orientation and color information are extracted and encoded into P-channels. The P-channel representation is then used to estimate an overlapping channel representation, using B<sub>1</sub>-spline functions, to estimate a density function for the feature set. Experiments were conducted with this representation as well as the raw P-channel representation in conjunction with a number of distance measures and estimation methods.</p><p>It is shown that, with correct preprocessing and choice of parameters, the pose can be detected with some accuracy and, if not in real-time, fast enough to be useful in a tracker initialization scenario. It is also concluded that the success rate of the estimation depends heavily on the nature of the object.</p>
|
94 |
Firefly web-based interactive tool for the visualization and validation of image processing algorithms /Beard, Daniel, Palaniappan, K. January 2009 (has links)
The entire thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file; a non-technical public abstract appears in the public.pdf file. Title from PDF of title page (University of Missouri--Columbia, viewed on December 21, 2009. Thesis advisor: Dr. Kannappan Palaniappan. Includes bibliographical references.
|
95 |
Automated image analysis for petrographic image assessments /Zhao, Xianghong, January 2000 (has links)
Thesis (M.Eng.)--Memorial University of Newfoundland, 2001. / Bibliography: leaves 112-115.
|
96 |
Feature-based motion estimation and motion segmentation /Cheng, Xin, January 1999 (has links)
Thesis (M.Eng.)--Memorial University of Newfoundland, 2000. / Bibliography: leaves 95-97.
|
97 |
Image segmentation for coding /Chowdhury, Md. Mahbubul Islam, January 2000 (has links)
Thesis (M.Eng.)--Memorial University of Newfoundland, 2000. / Bibliography: leaves 102-107.
|
98 |
Laser monitoring system for the ALICE ITSRizzo, Benjamin. January 2008 (has links)
Thesis (M.S.)--Creighton University, 2008. / Abstract. Title from title screen (viewed Mar. 8, 2010). Bluebrary (DSpace). Includes bibliographical references (leaves 111-113).
|
99 |
Mutual information based non-rigid image registration using adaptive grid generation GPU implementation and application to breast MRI /Chu, Mei Yi. January 2008 (has links)
Thesis (Ph.D.) -- University of Texas at Arlington, 2008.
|
100 |
A methodology for trajectory based learning and prediction of human motions in visual surveillanceChen, Zhuo, 陈卓 January 2011 (has links)
published_or_final_version / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy
|
Page generated in 0.0436 seconds