Retinal Fluids Segmentation Using Volumetric Deep Neural Networks on Optical Coherence Tomography Scans

Retinal diseases are among the significant reasons for vision loss worldwide. Age-related macular degeneration (AMD) influences older people, and 170 million individuals are diagnosed with AMD on the global level. This number is expected to increase to 288 million people by 2040. Optical coherence t...

Full description

Main Authors: Alsaih, K., Yusoff, M.Z., Tang, T.B., Faye, I., Meriaudeau, F.
Format: Conference or Workshop Item
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.30118 /
Published: Institute of Electrical and Electronics Engineers Inc. 2020
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093868884&doi=10.1109%2fICCSCE50387.2020.9204951&partnerID=40&md5=69a6cc273dcc3d0be6f65ca79485ba91
http://eprints.utp.edu.my/30118/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.30118
recordtype eprints
spelling utp-eprints.301182022-03-25T06:34:54Z Retinal Fluids Segmentation Using Volumetric Deep Neural Networks on Optical Coherence Tomography Scans Alsaih, K. Yusoff, M.Z. Tang, T.B. Faye, I. Meriaudeau, F. Retinal diseases are among the significant reasons for vision loss worldwide. Age-related macular degeneration (AMD) influences older people, and 170 million individuals are diagnosed with AMD on the global level. This number is expected to increase to 288 million people by 2040. Optical coherence tomography (OCT) is the most effective and noninvasive modality to view the retinal layers. The frequent visit of patients affected with retinal diseases raised the need for developing automatic algorithms to localize and quantity the morphological changes occurring in the retina. Deep learning networks show excellent performance in classifying 2D scans at the image level and pixel level. Medical data is usually obtained with depth information, and using only 2D information could lead to lower accuracy in localizing the fluid volume size. Mimicking human performance in manually locating the diseases over medical images is the main target of automatic methods to exceed. In this study, we have used the RETOUCH challenge dataset to segment various retinal fluids. Human performance reported in the challenge scored 0.71 in the dice similarity coefficient (DSC) metric. Encoder-decoder network is demonstrated in a 3D manner for the retinal disease segmentation, and the average performance score is 0.73 in the dice metric from the Cirrus scanner data. The dataset released three different fluids, and intraretinal fluid (IRF) is more identified with 0.79 in the DSC metric. © 2020 IEEE. Institute of Electrical and Electronics Engineers Inc. 2020 Conference or Workshop Item NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093868884&doi=10.1109%2fICCSCE50387.2020.9204951&partnerID=40&md5=69a6cc273dcc3d0be6f65ca79485ba91 Alsaih, K. and Yusoff, M.Z. and Tang, T.B. and Faye, I. and Meriaudeau, F. (2020) Retinal Fluids Segmentation Using Volumetric Deep Neural Networks on Optical Coherence Tomography Scans. In: UNSPECIFIED. http://eprints.utp.edu.my/30118/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description Retinal diseases are among the significant reasons for vision loss worldwide. Age-related macular degeneration (AMD) influences older people, and 170 million individuals are diagnosed with AMD on the global level. This number is expected to increase to 288 million people by 2040. Optical coherence tomography (OCT) is the most effective and noninvasive modality to view the retinal layers. The frequent visit of patients affected with retinal diseases raised the need for developing automatic algorithms to localize and quantity the morphological changes occurring in the retina. Deep learning networks show excellent performance in classifying 2D scans at the image level and pixel level. Medical data is usually obtained with depth information, and using only 2D information could lead to lower accuracy in localizing the fluid volume size. Mimicking human performance in manually locating the diseases over medical images is the main target of automatic methods to exceed. In this study, we have used the RETOUCH challenge dataset to segment various retinal fluids. Human performance reported in the challenge scored 0.71 in the dice similarity coefficient (DSC) metric. Encoder-decoder network is demonstrated in a 3D manner for the retinal disease segmentation, and the average performance score is 0.73 in the dice metric from the Cirrus scanner data. The dataset released three different fluids, and intraretinal fluid (IRF) is more identified with 0.79 in the DSC metric. © 2020 IEEE.
format Conference or Workshop Item
author Alsaih, K.
Yusoff, M.Z.
Tang, T.B.
Faye, I.
Meriaudeau, F.
spellingShingle Alsaih, K.
Yusoff, M.Z.
Tang, T.B.
Faye, I.
Meriaudeau, F.
Retinal Fluids Segmentation Using Volumetric Deep Neural Networks on Optical Coherence Tomography Scans
author_sort Alsaih, K.
title Retinal Fluids Segmentation Using Volumetric Deep Neural Networks on Optical Coherence Tomography Scans
title_short Retinal Fluids Segmentation Using Volumetric Deep Neural Networks on Optical Coherence Tomography Scans
title_full Retinal Fluids Segmentation Using Volumetric Deep Neural Networks on Optical Coherence Tomography Scans
title_fullStr Retinal Fluids Segmentation Using Volumetric Deep Neural Networks on Optical Coherence Tomography Scans
title_full_unstemmed Retinal Fluids Segmentation Using Volumetric Deep Neural Networks on Optical Coherence Tomography Scans
title_sort retinal fluids segmentation using volumetric deep neural networks on optical coherence tomography scans
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2020
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093868884&doi=10.1109%2fICCSCE50387.2020.9204951&partnerID=40&md5=69a6cc273dcc3d0be6f65ca79485ba91
http://eprints.utp.edu.my/30118/
_version_ 1741197352782266368
score 11.62408

Similar Items