A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology

Shumoos Al-Fahdawi, Rami Qahwaji, Alaa S. Al-Waisy, Stanley Ipson, Maryam Ferdousi, Rayaz Malik, Arun Brahma

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Background and Objective: Corneal endothelial cell abnormalities may be associated with a number of corneal and systemic diseases. Damage to the endothelial cells can significantly affect corneal transparency by altering hydration of the corneal stroma, which can lead to irreversible endothelial cell pathology requiring corneal transplantation. To date, quantitative analysis of endothelial cell abnormalities has been manually performed by ophthalmologists using time consuming and highly subjective semi-automatic tools, which require an operator interaction. We developed and applied a fully-automated and real-time system, termed the Corneal Endothelium Analysis System (CEAS) for the segmentation and computation of endothelial cells in images of the human cornea obtained by in vivo corneal confocal microscopy. Methods: First, a Fast Fourier Transform (FFT) Band-pass filter is applied to reduce noise and enhance the image quality to make the cells more visible. Secondly, endothelial cell boundaries are detected using watershed transformations and Voronoi tessellations to accurately quantify the morphological parameters of the human corneal endothelial cells. The performance of the automated segmentation system was tested against manually traced ground-truth images based on a database consisting of 40 corneal confocal endothelial cell images in terms of segmentation accuracy and obtained clinical features. In addition, the robustness and efficiency of the proposed CEAS system were compared with manually obtained cell densities using a separate database of 40 images from controls (n = 11), obese subjects (n = 16) and patients with diabetes (n = 13). Results: The Pearson correlation coefficient between automated and manual endothelial cell densities is 0.9 (p < 0.0001) and a Bland–Altman plot shows that 95% of the data are between the 2SD agreement lines. Conclusions: We demonstrate the effectiveness and robustness of the CEAS system, and the possibility of utilizing it in a real world clinical setting to enable rapid diagnosis and for patient follow-up, with an execution time of only 6 seconds per image.

Original languageEnglish
Pages (from-to)11-23
Number of pages13
JournalComputer Methods and Programs in Biomedicine
Volume160
DOIs
Publication statusPublished - 1 Jul 2018

Fingerprint

Endothelial cells
Endothelial Cells
Corneal Endothelium
Cell Count
Databases
Corneal Diseases
Corneal Stroma
Corneal Transplantation
Confocal microscopy
Computer Systems
Pathology
Fourier Analysis
Medical problems
Bandpass filters
Real time systems
Watersheds
Confocal Microscopy
Hydration
Fast Fourier transforms
Cornea

Keywords

  • Automatic cell segmentation
  • Corneal Confocal Microscopy
  • Corneal endothelial cells
  • Fast Fourier Transform
  • Voronoi Tessellation
  • Watershed transformation

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology. / Al-Fahdawi, Shumoos; Qahwaji, Rami; Al-Waisy, Alaa S.; Ipson, Stanley; Ferdousi, Maryam; Malik, Rayaz; Brahma, Arun.

In: Computer Methods and Programs in Biomedicine, Vol. 160, 01.07.2018, p. 11-23.

Research output: Contribution to journalArticle

Al-Fahdawi, Shumoos ; Qahwaji, Rami ; Al-Waisy, Alaa S. ; Ipson, Stanley ; Ferdousi, Maryam ; Malik, Rayaz ; Brahma, Arun. / A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology. In: Computer Methods and Programs in Biomedicine. 2018 ; Vol. 160. pp. 11-23.
@article{32a36a5f80c74a9fa5febf74cd8417b2,
title = "A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology",
abstract = "Background and Objective: Corneal endothelial cell abnormalities may be associated with a number of corneal and systemic diseases. Damage to the endothelial cells can significantly affect corneal transparency by altering hydration of the corneal stroma, which can lead to irreversible endothelial cell pathology requiring corneal transplantation. To date, quantitative analysis of endothelial cell abnormalities has been manually performed by ophthalmologists using time consuming and highly subjective semi-automatic tools, which require an operator interaction. We developed and applied a fully-automated and real-time system, termed the Corneal Endothelium Analysis System (CEAS) for the segmentation and computation of endothelial cells in images of the human cornea obtained by in vivo corneal confocal microscopy. Methods: First, a Fast Fourier Transform (FFT) Band-pass filter is applied to reduce noise and enhance the image quality to make the cells more visible. Secondly, endothelial cell boundaries are detected using watershed transformations and Voronoi tessellations to accurately quantify the morphological parameters of the human corneal endothelial cells. The performance of the automated segmentation system was tested against manually traced ground-truth images based on a database consisting of 40 corneal confocal endothelial cell images in terms of segmentation accuracy and obtained clinical features. In addition, the robustness and efficiency of the proposed CEAS system were compared with manually obtained cell densities using a separate database of 40 images from controls (n = 11), obese subjects (n = 16) and patients with diabetes (n = 13). Results: The Pearson correlation coefficient between automated and manual endothelial cell densities is 0.9 (p < 0.0001) and a Bland–Altman plot shows that 95{\%} of the data are between the 2SD agreement lines. Conclusions: We demonstrate the effectiveness and robustness of the CEAS system, and the possibility of utilizing it in a real world clinical setting to enable rapid diagnosis and for patient follow-up, with an execution time of only 6 seconds per image.",
keywords = "Automatic cell segmentation, Corneal Confocal Microscopy, Corneal endothelial cells, Fast Fourier Transform, Voronoi Tessellation, Watershed transformation",
author = "Shumoos Al-Fahdawi and Rami Qahwaji and Al-Waisy, {Alaa S.} and Stanley Ipson and Maryam Ferdousi and Rayaz Malik and Arun Brahma",
year = "2018",
month = "7",
day = "1",
doi = "10.1016/j.cmpb.2018.03.015",
language = "English",
volume = "160",
pages = "11--23",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology

AU - Al-Fahdawi, Shumoos

AU - Qahwaji, Rami

AU - Al-Waisy, Alaa S.

AU - Ipson, Stanley

AU - Ferdousi, Maryam

AU - Malik, Rayaz

AU - Brahma, Arun

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Background and Objective: Corneal endothelial cell abnormalities may be associated with a number of corneal and systemic diseases. Damage to the endothelial cells can significantly affect corneal transparency by altering hydration of the corneal stroma, which can lead to irreversible endothelial cell pathology requiring corneal transplantation. To date, quantitative analysis of endothelial cell abnormalities has been manually performed by ophthalmologists using time consuming and highly subjective semi-automatic tools, which require an operator interaction. We developed and applied a fully-automated and real-time system, termed the Corneal Endothelium Analysis System (CEAS) for the segmentation and computation of endothelial cells in images of the human cornea obtained by in vivo corneal confocal microscopy. Methods: First, a Fast Fourier Transform (FFT) Band-pass filter is applied to reduce noise and enhance the image quality to make the cells more visible. Secondly, endothelial cell boundaries are detected using watershed transformations and Voronoi tessellations to accurately quantify the morphological parameters of the human corneal endothelial cells. The performance of the automated segmentation system was tested against manually traced ground-truth images based on a database consisting of 40 corneal confocal endothelial cell images in terms of segmentation accuracy and obtained clinical features. In addition, the robustness and efficiency of the proposed CEAS system were compared with manually obtained cell densities using a separate database of 40 images from controls (n = 11), obese subjects (n = 16) and patients with diabetes (n = 13). Results: The Pearson correlation coefficient between automated and manual endothelial cell densities is 0.9 (p < 0.0001) and a Bland–Altman plot shows that 95% of the data are between the 2SD agreement lines. Conclusions: We demonstrate the effectiveness and robustness of the CEAS system, and the possibility of utilizing it in a real world clinical setting to enable rapid diagnosis and for patient follow-up, with an execution time of only 6 seconds per image.

AB - Background and Objective: Corneal endothelial cell abnormalities may be associated with a number of corneal and systemic diseases. Damage to the endothelial cells can significantly affect corneal transparency by altering hydration of the corneal stroma, which can lead to irreversible endothelial cell pathology requiring corneal transplantation. To date, quantitative analysis of endothelial cell abnormalities has been manually performed by ophthalmologists using time consuming and highly subjective semi-automatic tools, which require an operator interaction. We developed and applied a fully-automated and real-time system, termed the Corneal Endothelium Analysis System (CEAS) for the segmentation and computation of endothelial cells in images of the human cornea obtained by in vivo corneal confocal microscopy. Methods: First, a Fast Fourier Transform (FFT) Band-pass filter is applied to reduce noise and enhance the image quality to make the cells more visible. Secondly, endothelial cell boundaries are detected using watershed transformations and Voronoi tessellations to accurately quantify the morphological parameters of the human corneal endothelial cells. The performance of the automated segmentation system was tested against manually traced ground-truth images based on a database consisting of 40 corneal confocal endothelial cell images in terms of segmentation accuracy and obtained clinical features. In addition, the robustness and efficiency of the proposed CEAS system were compared with manually obtained cell densities using a separate database of 40 images from controls (n = 11), obese subjects (n = 16) and patients with diabetes (n = 13). Results: The Pearson correlation coefficient between automated and manual endothelial cell densities is 0.9 (p < 0.0001) and a Bland–Altman plot shows that 95% of the data are between the 2SD agreement lines. Conclusions: We demonstrate the effectiveness and robustness of the CEAS system, and the possibility of utilizing it in a real world clinical setting to enable rapid diagnosis and for patient follow-up, with an execution time of only 6 seconds per image.

KW - Automatic cell segmentation

KW - Corneal Confocal Microscopy

KW - Corneal endothelial cells

KW - Fast Fourier Transform

KW - Voronoi Tessellation

KW - Watershed transformation

UR - http://www.scopus.com/inward/record.url?scp=85044620697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044620697&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2018.03.015

DO - 10.1016/j.cmpb.2018.03.015

M3 - Article

C2 - 29728238

AN - SCOPUS:85044620697

VL - 160

SP - 11

EP - 23

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -