Show simple item record

Graph Theory and Dynamic Programming Framework for Automated Segmentation of Ophthalmic Imaging Biomarkers

dc.contributor.advisor Farsiu, Sina
dc.contributor.author Chiu, Stephanie Ja-Yi
dc.date.accessioned 2014-05-14T19:17:17Z
dc.date.available 2015-05-09T04:30:05Z
dc.date.issued 2014
dc.identifier.uri https://hdl.handle.net/10161/8688
dc.description.abstract <p>Accurate quantification of anatomical and pathological structures in the eye is crucial for the study and diagnosis of potentially blinding diseases. Earlier and faster detection of ophthalmic imaging biomarkers also leads to optimal treatment and improved vision recovery. While modern optical imaging technologies such as optical coherence tomography (OCT) and adaptive optics (AO) have facilitated in vivo visualization of the eye at the cellular scale, the massive influx of data generated by these systems is often too large to be fully analyzed by ophthalmic experts without extensive time or resources. Furthermore, manual evaluation of images is inherently subjective and prone to human error.</p><p>This dissertation describes the development and validation of a framework called graph theory and dynamic programming (GTDP) to automatically detect and quantify ophthalmic imaging biomarkers. The GTDP framework was validated as an accurate technique for segmenting retinal layers on OCT images. The framework was then extended through the development of the quasi-polar transform to segment closed-contour structures including photoreceptors on AO scanning laser ophthalmoscopy images and retinal pigment epithelial cells on confocal microscopy images. </p><p>The GTDP framework was next applied in a clinical setting with pathologic images that are often lower in quality. Algorithms were developed to delineate morphological structures on OCT indicative of diseases such as age-related macular degeneration (AMD) and diabetic macular edema (DME). The AMD algorithm was shown to be robust to poor image quality and was capable of segmenting both drusen and geographic atrophy. To account for the complex manifestations of DME, a novel kernel regression-based classification framework was developed to identify retinal layers and fluid-filled regions as a guide for GTDP segmentation.</p><p>The development of fast and accurate segmentation algorithms based on the GTDP framework has significantly reduced the time and resources necessary to conduct large-scale, multi-center clinical trials. This is one step closer towards the long-term goal of improving vision outcomes for ocular disease patients through personalized therapy.</p>
dc.subject Biomedical engineering
dc.subject Computer science
dc.subject Ophthalmology
dc.subject graph theory and dynamic programming
dc.subject GTDP
dc.subject kernel regression-based classification
dc.subject optical coherence tomography
dc.subject quasi-polar transform
dc.subject segmentation
dc.title Graph Theory and Dynamic Programming Framework for Automated Segmentation of Ophthalmic Imaging Biomarkers
dc.type Dissertation
dc.department Biomedical Engineering
duke.embargo.months 12


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record