You are here

UCF Digital Collections ยป ETD Collection

A Decision Support Tool for Video Retinal Angiography

Download pdf | Full Screen View

Date Issued:
2018
Abstract/Description:
Fluorescein angiogram (FA) is a medical procedure that helps the ophthalmologists to monitor the status of the retinal blood vessels and to diagnose proper treatment. This research is motivated by the necessity of blood vessel segmentation of the retina. Retinal vessel segmentation has been a major challenge and has long drawn the attention of researchers for decades due to the presence of complex blood vessels with varying size, shape, angles and branching pattern of vessels, and non-uniform illumination and huge anatomical variability between subjects. In this thesis, we introduce a new computational tool that combines deep learning based machine learning algorithm and a signal processing based video magnification method to support physicians in analyzing and diagnosing retinal angiogram videos for the first time in the literature.The proposed approach has a pipeline-based architecture containing three phases - image registration for large motion removal from video angiogram, retinal vessel segmentation and video magnification based on the segmented vessels. In image registration phase, we align distorted frames in the FA video using rigid registration approaches. In the next phase, we use baseline capsule based neural networks for retinal vessel segmentation in comparison with the state-of-the-art methods. We move away from traditional convolutional network approaches to capsule networks in this work. This is because, despite being widely used in different computer vision applications, convolutional neural networks suffer from learning ability to understand the object-part relationships, have high computational times due to additive nature of neurons and, loose information in the pooling layer. Although having these drawbacks, we use deep learning methods like U-Net and Tiramisu to measure the performance and accuracy of SegCaps. Lastly, we apply Eulerian video magnification to magnify the subtle changes in the retinal video. In this phase, magnification is applied to segmented videos to visualize the flow of blood in the retinal vessels.
Title: A Decision Support Tool for Video Retinal Angiography.
32 views
19 downloads
Name(s): Laha, Sumit, Author
Bagci, Ulas, Committee Chair
Foroosh, Hassan, Committee Member
Song, Sam, Committee Member
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2018
Publisher: University of Central Florida
Language(s): English
Abstract/Description: Fluorescein angiogram (FA) is a medical procedure that helps the ophthalmologists to monitor the status of the retinal blood vessels and to diagnose proper treatment. This research is motivated by the necessity of blood vessel segmentation of the retina. Retinal vessel segmentation has been a major challenge and has long drawn the attention of researchers for decades due to the presence of complex blood vessels with varying size, shape, angles and branching pattern of vessels, and non-uniform illumination and huge anatomical variability between subjects. In this thesis, we introduce a new computational tool that combines deep learning based machine learning algorithm and a signal processing based video magnification method to support physicians in analyzing and diagnosing retinal angiogram videos for the first time in the literature.The proposed approach has a pipeline-based architecture containing three phases - image registration for large motion removal from video angiogram, retinal vessel segmentation and video magnification based on the segmented vessels. In image registration phase, we align distorted frames in the FA video using rigid registration approaches. In the next phase, we use baseline capsule based neural networks for retinal vessel segmentation in comparison with the state-of-the-art methods. We move away from traditional convolutional network approaches to capsule networks in this work. This is because, despite being widely used in different computer vision applications, convolutional neural networks suffer from learning ability to understand the object-part relationships, have high computational times due to additive nature of neurons and, loose information in the pooling layer. Although having these drawbacks, we use deep learning methods like U-Net and Tiramisu to measure the performance and accuracy of SegCaps. Lastly, we apply Eulerian video magnification to magnify the subtle changes in the retinal video. In this phase, magnification is applied to segmented videos to visualize the flow of blood in the retinal vessels.
Identifier: CFE0007342 (IID), ucf:52125 (fedora)
Note(s): 2018-12-01
M.S.
Engineering and Computer Science, Computer Science
Masters
This record was generated from author submitted information.
Subject(s): Fluorescein angiogram -- Rigid image registration -- Retinal vessel segmentation -- Deep learning -- Capsule networks -- SegCaps -- Eulerian video magnification
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0007342
Restrictions on Access: public 2018-12-15
Host Institution: UCF

In Collections