國立虎尾科技大學 |

GAN-Based Super-Resolution and Segmentation of Retinal Layers in Optical Coherence Tomography Scans.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	GAN-Based Super-Resolution and Segmentation of Retinal Layers in Optical Coherence Tomography Scans./
Author:	Jeihouni, Paria.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
Description:	48 p.
Notes:	Source: Dissertations Abstracts International, Volume: 84-05, Section: B.
Contained By:	Dissertations Abstracts International84-05B.
Subject:	Tomography. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29731053
ISBN:	9798352979280

GAN-Based Super-Resolution and Segmentation of Retinal Layers in Optical Coherence Tomography Scans.
Jeihouni, Paria.

GAN-Based Super-Resolution and Segmentation of Retinal Layers in Optical Coherence Tomography Scans. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 48 p.

Source: Dissertations Abstracts International, Volume: 84-05, Section: B.

Thesis (M.Sc.)--West Virginia University, 2022.

This item must not be sold to any third party vendors.

Optical Coherence Tomography (OCT) has been identified as a noninvasive and cost-effective imaging modality for identifying potential biomarkers for Alzheimer's diagnosis and progress detection. Current hypotheses indicate that retinal layer thickness, which can be assessed via OCT scans, is an efficient biomarker for identifying Alzheimer's disease. Due to factors such as speckle noise, a small target region, and unfavorable imaging conditions manual segmentation of retina layers is a challenging task. Therefore, as a reasonable first step, this study focuses on automatically segmenting retinal layers to separate them for subsequent investigations. Another important challenge commonly faced is the lack of clarity of the layer boundaries in retina OCT scans, which compels the research of super-resolving the images for improved clarity. Deep learning pipelines have stimulated substantial progress for the segmentation tasks. Generative adversarial networks (GANs) are a prominent field of deep learning which achieved astonishing performance in semantic segmentation. Conditional adversarial networks as a general-purpose solution to image-to-image translation problems not only learn the mapping from the input image to the output image but also learn a loss function to train this mapping. We propose a GAN-based segmentation model and evaluate incorporating popular networks, namely, U-Net and ResNet, in the GAN architecture with additional blocks of transposed convolution and sub-pixel convolution for the task of upscaling OCT images from low to high resolution by a factor of four. We also incorporate the Dice loss as an additional reconstruction loss term to improve the performance of this joint optimization task. Our best model configuration empirically achieved the Dice coefficient of 0.867 and mIOU of 0.765.

ISBN: 9798352979280Subjects--Topical Terms:

528407
Tomography.

GAN-Based Super-Resolution and Segmentation of Retinal Layers in Optical Coherence Tomography Scans.
LDR:03097nam a2200409 4500 001 1104677
005 20230619080117.5
006 m o d
007 cr#unu||||||||
008 230907s2022 ||||||||||||||||| ||eng d
020 $a 9798352979280
035 $a (MiAaPQ)AAI29731053
035 $a (MiAaPQ)WVirginia12310
035 $a AAI29731053
040 $a MiAaPQ $c MiAaPQ
100 1 $a Jeihouni, Paria. $3 1413646
245 1 0 $a GAN-Based Super-Resolution and Segmentation of Retinal Layers in Optical Coherence Tomography Scans.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 48 p.
500 $a Source: Dissertations Abstracts International, Volume: 84-05, Section: B.
500 $a Advisor: Nasrabadi, Nasser M. ;Dawson, Jeremy;Dehzangi, Omid.
502 $a Thesis (M.Sc.)--West Virginia University, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Optical Coherence Tomography (OCT) has been identified as a noninvasive and cost-effective imaging modality for identifying potential biomarkers for Alzheimer's diagnosis and progress detection. Current hypotheses indicate that retinal layer thickness, which can be assessed via OCT scans, is an efficient biomarker for identifying Alzheimer's disease. Due to factors such as speckle noise, a small target region, and unfavorable imaging conditions manual segmentation of retina layers is a challenging task. Therefore, as a reasonable first step, this study focuses on automatically segmenting retinal layers to separate them for subsequent investigations. Another important challenge commonly faced is the lack of clarity of the layer boundaries in retina OCT scans, which compels the research of super-resolving the images for improved clarity. Deep learning pipelines have stimulated substantial progress for the segmentation tasks. Generative adversarial networks (GANs) are a prominent field of deep learning which achieved astonishing performance in semantic segmentation. Conditional adversarial networks as a general-purpose solution to image-to-image translation problems not only learn the mapping from the input image to the output image but also learn a loss function to train this mapping. We propose a GAN-based segmentation model and evaluate incorporating popular networks, namely, U-Net and ResNet, in the GAN architecture with additional blocks of transposed convolution and sub-pixel convolution for the task of upscaling OCT images from low to high resolution by a factor of four. We also incorporate the Dice loss as an additional reconstruction loss term to improve the performance of this joint optimization task. Our best model configuration empirically achieved the Dice coefficient of 0.867 and mIOU of 0.765.
590 $a School code: 0256.
650 4 $a Tomography. $3 528407
650 4 $a Deep learning. $3 1127428
650 4 $a Retina. $3 795433
650 4 $a Dementia. $3 678297
650 4 $a Neural networks. $3 1011215
650 4 $a Medical research. $2 bicssc $3 809476
650 4 $a Maps. $3 889832
650 4 $a Biomarkers. $3 1155103
650 4 $a Design. $3 595500
650 4 $a Art. $3 807354
650 4 $a Algorithms. $3 527865
650 4 $a Older people. $3 554842
650 4 $a Radiation. $3 673044
650 4 $a Markov analysis. $3 1413647
650 4 $a Semantics. $3 555362
650 4 $a Alzheimers disease. $3 1413648
650 4 $a Computer science. $3 573171
650 4 $a Gerontology. $3 559846
650 4 $a Logic. $3 558909
650 4 $a Medical imaging. $3 1180167
650 4 $a Neurosciences. $3 593561
690 $a 0389
690 $a 0800
690 $a 0984
690 $a 0351
690 $a 0395
690 $a 0574
690 $a 0317
690 $a 0796
710 2 $a West Virginia University. $3 1187945
773 0 $t Dissertations Abstracts International $g 84-05B.
790 $a 0256
791 $a M.Sc.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29731053