Texture analysis of corpora lutea in ultrasonographic ovarian images using genetic programming and rotation invariant local binary patterns
| dc.contributor.advisor | Eramian, Mark G. | en_US |
| dc.contributor.committeeMember | Pierson, Roger A. | en_US |
| dc.contributor.committeeMember | Sarty, Gordon E. | en_US |
| dc.contributor.committeeMember | Ludwig, Simone | en_US |
| dc.creator | Dong, Meng | en_US |
| dc.date.accessioned | 2011-08-10T15:34:50Z | en_US |
| dc.date.accessioned | 2013-01-04T04:52:24Z | |
| dc.date.available | 2012-08-16T08:00:00Z | en_US |
| dc.date.available | 2013-01-04T04:52:24Z | |
| dc.date.created | 2011-07 | en_US |
| dc.date.issued | 2011-07 | en_US |
| dc.date.submitted | July 2011 | en_US |
| dc.description.abstract | Ultrasonography is widely used in medical diagnosis with the advantages of being low cost, non-invasive and capable of real time imaging. When interpreting ultrasonographic images of mammalian ovaries, the structures of interest are follicles, corpora lutea (CL) and stroma. This thesis presents an approach to perform CL texture analysis, including detection and segmentation, based on the classifiers trained by genetic programming (GP). The objective of CL detection is to determine whether there is a CL in the ovarian images, while the goal of segmentation is to localize the CL within the image. Genetic programming (GP) offers a solution through the evolution of computer programs by methods inspired by the mechanisms of natural selection. Herein, we use rotationally invariant local binary patterns (LBP) to encode the local texture features. These are used by the programs which are manipulated by GP to obtain highly fit CL classifiers. Grayscale standardization was performed on all images in our data set based on the reference grayscale in each image. CL classification programs were evolved by genetic programming and tested on ultrasonographic images of ovaries. On the bovine dataset, our CL detection algorithm is reliable and robust. The detection algorithm correctly determined the presence or absence of a CL in 93:3% of 60 test images. The segmentation algorithm achieved a mean (± standard deviation) sensitivity and specificity of 0:87 ± 0:14 and 0:91 ± 0:05, respectively, over the 30 CL images. Our CL segmentation algorithm is an improvement over the only previously published algorithm, since our method is fully automatic and does not require the placement of an initial contour. The success of these algorithms demonstrates that similar algorithms designed for analysis of in vivo human ovaries are likely viable. | en_US |
| dc.identifier.uri | http://hdl.handle.net/10388/etd-08102011-153450 | en_US |
| dc.language.iso | en_US | en_US |
| dc.subject | Texture Analysis | en_US |
| dc.subject | Ultrasonography | en_US |
| dc.subject | Corpora lutea | en_US |
| dc.subject | Local Binary Patterns | en_US |
| dc.subject | Genetic Programming | en_US |
| dc.title | Texture analysis of corpora lutea in ultrasonographic ovarian images using genetic programming and rotation invariant local binary patterns | en_US |
| dc.type.genre | Thesis | en_US |
| dc.type.material | text | en_US |
| thesis.degree.department | Computer Science | en_US |
| thesis.degree.discipline | Computer Science | en_US |
| thesis.degree.grantor | University of Saskatchewan | en_US |
| thesis.degree.level | Masters | en_US |
| thesis.degree.name | Master of Science (M.Sc.) | en_US |