Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Retinal layer segmentation in rodent OCT images: Local intensity profiles & fully convolutional neural networks

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@article{6473448d1fb84983be9a0fa3da2a2ad6,
title = "Retinal layer segmentation in rodent OCT images: Local intensity profiles & fully convolutional neural networks",
abstract = "BACKGROUND AND OBJECTIVE: Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented.METHODS: One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture.RESULTS: After a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons.CONCLUSIONS: Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images.",
author = "Sandra Morales and Adri{\'a}n Colomer and Mossi, {Jos{\'e} M} and {Del Amor}, Roc{\'i}o and David Woldbye and Kristian Klemp and Michael Larsen and Valery Naranjo",
note = "Copyright {\textcopyright} 2020. Published by Elsevier B.V.",
year = "2021",
month = jan,
doi = "10.1016/j.cmpb.2020.105788",
language = "English",
volume = "198",
pages = "105788",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

RIS

TY - JOUR

T1 - Retinal layer segmentation in rodent OCT images

T2 - Local intensity profiles & fully convolutional neural networks

AU - Morales, Sandra

AU - Colomer, Adrián

AU - Mossi, José M

AU - Del Amor, Rocío

AU - Woldbye, David

AU - Klemp, Kristian

AU - Larsen, Michael

AU - Naranjo, Valery

N1 - Copyright © 2020. Published by Elsevier B.V.

PY - 2021/1

Y1 - 2021/1

N2 - BACKGROUND AND OBJECTIVE: Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented.METHODS: One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture.RESULTS: After a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons.CONCLUSIONS: Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images.

AB - BACKGROUND AND OBJECTIVE: Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented.METHODS: One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture.RESULTS: After a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons.CONCLUSIONS: Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images.

U2 - 10.1016/j.cmpb.2020.105788

DO - 10.1016/j.cmpb.2020.105788

M3 - Journal article

C2 - 33130492

VL - 198

SP - 105788

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -

ID: 61963442