Deep Neural Network Regression for Automated Retinal Layer Segmentation in Optical Coherence Tomography Images

Lua Ngo, Jaepyeong Cha, Jae Ho Han

Research output: Contribution to journalArticle

Abstract

Segmenting the retinal layers in optical coherence tomography (OCT) images helps to quantify the layer information in early diagnosis of retinal diseases, which are the main cause of permanent blindness. Thus, the segmentation process plays a critical role in preventing vision impairment. However, because there is a lack of practical automated techniques, expert ophthalmologists still have to manually segment the retinal layers. In this paper, we propose an automated segmentation method for OCT images based on a feature-learning regression network without human bias. The proposed deep neural network regression takes the intensity, gradient, and adaptive normalized intensity score (ANIS) of an image segment as features for learning, and then predicts the corresponding retinal boundary pixel. Reformulating the segmentation as a regression problem obviates the need for a huge dataset and reduces the complexity significantly, as shown in the analysis of computational complexity given here. In addition, assisted by ANIS, the method operates robustly on OCT images containing intensity variances, low-contrast regions, speckle noise, and blood vessels, yet remains accurate and time-efficient. In the evaluation of the method conducted using 114 images, the processing time was approximately 10.596 s per image for identifying eight boundaries, and the training phase for each boundary line took only 30 s. Further, the Dice similarity coefficient used for assessing accuracy gave a computed value of approximately 0.966. The absolute pixel distance of manual and automatic segmentation using the proposed scheme was 0.612, which is less than a one-pixel difference, on average.

Original languageEnglish
Article number8784409
Pages (from-to)303-312
Number of pages10
JournalIEEE Transactions on Image Processing
Volume29
DOIs
Publication statusPublished - 2020 Jan 1

Keywords

  • Artificial intelligence
  • biomedical optical imaging
  • image segmentation
  • neural network
  • optical coherence tomography

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Deep Neural Network Regression for Automated Retinal Layer Segmentation in Optical Coherence Tomography Images. / Ngo, Lua; Cha, Jaepyeong; Han, Jae Ho.

In: IEEE Transactions on Image Processing, Vol. 29, 8784409, 01.01.2020, p. 303-312.

Research output: Contribution to journalArticle

@article{7fb912cdf94a49058008cd41a773da0a,
title = "Deep Neural Network Regression for Automated Retinal Layer Segmentation in Optical Coherence Tomography Images",
abstract = "Segmenting the retinal layers in optical coherence tomography (OCT) images helps to quantify the layer information in early diagnosis of retinal diseases, which are the main cause of permanent blindness. Thus, the segmentation process plays a critical role in preventing vision impairment. However, because there is a lack of practical automated techniques, expert ophthalmologists still have to manually segment the retinal layers. In this paper, we propose an automated segmentation method for OCT images based on a feature-learning regression network without human bias. The proposed deep neural network regression takes the intensity, gradient, and adaptive normalized intensity score (ANIS) of an image segment as features for learning, and then predicts the corresponding retinal boundary pixel. Reformulating the segmentation as a regression problem obviates the need for a huge dataset and reduces the complexity significantly, as shown in the analysis of computational complexity given here. In addition, assisted by ANIS, the method operates robustly on OCT images containing intensity variances, low-contrast regions, speckle noise, and blood vessels, yet remains accurate and time-efficient. In the evaluation of the method conducted using 114 images, the processing time was approximately 10.596 s per image for identifying eight boundaries, and the training phase for each boundary line took only 30 s. Further, the Dice similarity coefficient used for assessing accuracy gave a computed value of approximately 0.966. The absolute pixel distance of manual and automatic segmentation using the proposed scheme was 0.612, which is less than a one-pixel difference, on average.",
keywords = "Artificial intelligence, biomedical optical imaging, image segmentation, neural network, optical coherence tomography",
author = "Lua Ngo and Jaepyeong Cha and Han, {Jae Ho}",
year = "2020",
month = "1",
day = "1",
doi = "10.1109/TIP.2019.2931461",
language = "English",
volume = "29",
pages = "303--312",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Deep Neural Network Regression for Automated Retinal Layer Segmentation in Optical Coherence Tomography Images

AU - Ngo, Lua

AU - Cha, Jaepyeong

AU - Han, Jae Ho

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Segmenting the retinal layers in optical coherence tomography (OCT) images helps to quantify the layer information in early diagnosis of retinal diseases, which are the main cause of permanent blindness. Thus, the segmentation process plays a critical role in preventing vision impairment. However, because there is a lack of practical automated techniques, expert ophthalmologists still have to manually segment the retinal layers. In this paper, we propose an automated segmentation method for OCT images based on a feature-learning regression network without human bias. The proposed deep neural network regression takes the intensity, gradient, and adaptive normalized intensity score (ANIS) of an image segment as features for learning, and then predicts the corresponding retinal boundary pixel. Reformulating the segmentation as a regression problem obviates the need for a huge dataset and reduces the complexity significantly, as shown in the analysis of computational complexity given here. In addition, assisted by ANIS, the method operates robustly on OCT images containing intensity variances, low-contrast regions, speckle noise, and blood vessels, yet remains accurate and time-efficient. In the evaluation of the method conducted using 114 images, the processing time was approximately 10.596 s per image for identifying eight boundaries, and the training phase for each boundary line took only 30 s. Further, the Dice similarity coefficient used for assessing accuracy gave a computed value of approximately 0.966. The absolute pixel distance of manual and automatic segmentation using the proposed scheme was 0.612, which is less than a one-pixel difference, on average.

AB - Segmenting the retinal layers in optical coherence tomography (OCT) images helps to quantify the layer information in early diagnosis of retinal diseases, which are the main cause of permanent blindness. Thus, the segmentation process plays a critical role in preventing vision impairment. However, because there is a lack of practical automated techniques, expert ophthalmologists still have to manually segment the retinal layers. In this paper, we propose an automated segmentation method for OCT images based on a feature-learning regression network without human bias. The proposed deep neural network regression takes the intensity, gradient, and adaptive normalized intensity score (ANIS) of an image segment as features for learning, and then predicts the corresponding retinal boundary pixel. Reformulating the segmentation as a regression problem obviates the need for a huge dataset and reduces the complexity significantly, as shown in the analysis of computational complexity given here. In addition, assisted by ANIS, the method operates robustly on OCT images containing intensity variances, low-contrast regions, speckle noise, and blood vessels, yet remains accurate and time-efficient. In the evaluation of the method conducted using 114 images, the processing time was approximately 10.596 s per image for identifying eight boundaries, and the training phase for each boundary line took only 30 s. Further, the Dice similarity coefficient used for assessing accuracy gave a computed value of approximately 0.966. The absolute pixel distance of manual and automatic segmentation using the proposed scheme was 0.612, which is less than a one-pixel difference, on average.

KW - Artificial intelligence

KW - biomedical optical imaging

KW - image segmentation

KW - neural network

KW - optical coherence tomography

UR - http://www.scopus.com/inward/record.url?scp=85072758442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072758442&partnerID=8YFLogxK

U2 - 10.1109/TIP.2019.2931461

DO - 10.1109/TIP.2019.2931461

M3 - Article

AN - SCOPUS:85072758442

VL - 29

SP - 303

EP - 312

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

M1 - 8784409

ER -