A fully automatic nerve segmentation and morphometric parameter quantification system for early diagnosis of diabetic neuropathy in corneal images

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

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Diabetic Peripheral Neuropathy (DPN) is one of the most common types of diabetes that can affect the cornea. An accurate analysis of the nerve structures can assist the early diagnosis of this disease. This paper proposes a robust, fast and fully automatic nerve segmentation and morphometric parameter quantification system for corneal confocal microscope images. The segmentation part consists of three main steps. First, a preprocessing step is applied to enhance the visibility of the nerves and remove noise using anisotropic diffusion filtering, specifically a Coherence filter followed by Gaussian filtering. Second, morphological operations are applied to remove unwanted objects in the input image such as epithelial cells and small nerve segments. Finally, an edge detection step is applied to detect all the nerves in the input image. In this step, an efficient algorithm for connecting discontinuous nerves is proposed. In the morphometric parameters quantification part, a number of features are extracted, including thickness, tortuosity and length of nerve, which may be used for the early diagnosis of diabetic polyneuropathy and when planning Laser-Assisted in situ Keratomileusis (LASIK) or Photorefractive keratectomy (PRK). The performance of the proposed segmentation system is evaluated against manually traced ground-truth images based on a database consisting of 498 corneal sub-basal nerve images (238 are normal and 260 are abnormal). In addition, the robustness and efficiency of the proposed system in extracting morphometric features with clinical utility was evaluated in 919 images taken from healthy subjects and diabetic patients with and without neuropathy. We demonstrate rapid (13 seconds/image), robust and effective automated corneal nerve quantification. The proposed system will be deployed as a useful clinical tool to support the expertise of ophthalmologists and save the clinician time in a busy clinical setting.

Original languageEnglish
Pages (from-to)151-166
Number of pages16
JournalComputer Methods and Programs in Biomedicine
Volume135
DOIs
Publication statusPublished - 1 Oct 2016

Fingerprint

Diabetic Neuropathies
Early Diagnosis
Photorefractive Keratectomy
Laser In Situ Keratomileusis
Edge detection
Peripheral Nervous System Diseases
Medical problems
Visibility
Cornea
Noise
Healthy Volunteers
Microscopes
Epithelial Cells
Databases
Planning
Lasers
Ophthalmologists

Keywords

  • Anisotropic diffusion filtering
  • Automatic nerve segmentation
  • Corneal confocal microscopy
  • Corneal subbasal epithelium
  • Diabetes
  • Diabetic peripheral neuropathy

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

A fully automatic nerve segmentation and morphometric parameter quantification system for early diagnosis of diabetic neuropathy in corneal images. / Al-Fahdawi, Shumoos; Qahwaji, Rami; Al-Waisy, Alaa S.; Ipson, Stanley; Malik, Rayaz; Brahma, Arun; Chen, Xin.

In: Computer Methods and Programs in Biomedicine, Vol. 135, 01.10.2016, p. 151-166.

Research output: Contribution to journalArticle

Al-Fahdawi, Shumoos ; Qahwaji, Rami ; Al-Waisy, Alaa S. ; Ipson, Stanley ; Malik, Rayaz ; Brahma, Arun ; Chen, Xin. / A fully automatic nerve segmentation and morphometric parameter quantification system for early diagnosis of diabetic neuropathy in corneal images. In: Computer Methods and Programs in Biomedicine. 2016 ; Vol. 135. pp. 151-166.
@article{f8014a439c464f8ba37b1b5e70b08e60,
title = "A fully automatic nerve segmentation and morphometric parameter quantification system for early diagnosis of diabetic neuropathy in corneal images",
abstract = "Diabetic Peripheral Neuropathy (DPN) is one of the most common types of diabetes that can affect the cornea. An accurate analysis of the nerve structures can assist the early diagnosis of this disease. This paper proposes a robust, fast and fully automatic nerve segmentation and morphometric parameter quantification system for corneal confocal microscope images. The segmentation part consists of three main steps. First, a preprocessing step is applied to enhance the visibility of the nerves and remove noise using anisotropic diffusion filtering, specifically a Coherence filter followed by Gaussian filtering. Second, morphological operations are applied to remove unwanted objects in the input image such as epithelial cells and small nerve segments. Finally, an edge detection step is applied to detect all the nerves in the input image. In this step, an efficient algorithm for connecting discontinuous nerves is proposed. In the morphometric parameters quantification part, a number of features are extracted, including thickness, tortuosity and length of nerve, which may be used for the early diagnosis of diabetic polyneuropathy and when planning Laser-Assisted in situ Keratomileusis (LASIK) or Photorefractive keratectomy (PRK). The performance of the proposed segmentation system is evaluated against manually traced ground-truth images based on a database consisting of 498 corneal sub-basal nerve images (238 are normal and 260 are abnormal). In addition, the robustness and efficiency of the proposed system in extracting morphometric features with clinical utility was evaluated in 919 images taken from healthy subjects and diabetic patients with and without neuropathy. We demonstrate rapid (13 seconds/image), robust and effective automated corneal nerve quantification. The proposed system will be deployed as a useful clinical tool to support the expertise of ophthalmologists and save the clinician time in a busy clinical setting.",
keywords = "Anisotropic diffusion filtering, Automatic nerve segmentation, Corneal confocal microscopy, Corneal subbasal epithelium, Diabetes, Diabetic peripheral neuropathy",
author = "Shumoos Al-Fahdawi and Rami Qahwaji and Al-Waisy, {Alaa S.} and Stanley Ipson and Rayaz Malik and Arun Brahma and Xin Chen",
year = "2016",
month = "10",
day = "1",
doi = "10.1016/j.cmpb.2016.07.032",
language = "English",
volume = "135",
pages = "151--166",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - A fully automatic nerve segmentation and morphometric parameter quantification system for early diagnosis of diabetic neuropathy in corneal images

AU - Al-Fahdawi, Shumoos

AU - Qahwaji, Rami

AU - Al-Waisy, Alaa S.

AU - Ipson, Stanley

AU - Malik, Rayaz

AU - Brahma, Arun

AU - Chen, Xin

PY - 2016/10/1

Y1 - 2016/10/1

N2 - Diabetic Peripheral Neuropathy (DPN) is one of the most common types of diabetes that can affect the cornea. An accurate analysis of the nerve structures can assist the early diagnosis of this disease. This paper proposes a robust, fast and fully automatic nerve segmentation and morphometric parameter quantification system for corneal confocal microscope images. The segmentation part consists of three main steps. First, a preprocessing step is applied to enhance the visibility of the nerves and remove noise using anisotropic diffusion filtering, specifically a Coherence filter followed by Gaussian filtering. Second, morphological operations are applied to remove unwanted objects in the input image such as epithelial cells and small nerve segments. Finally, an edge detection step is applied to detect all the nerves in the input image. In this step, an efficient algorithm for connecting discontinuous nerves is proposed. In the morphometric parameters quantification part, a number of features are extracted, including thickness, tortuosity and length of nerve, which may be used for the early diagnosis of diabetic polyneuropathy and when planning Laser-Assisted in situ Keratomileusis (LASIK) or Photorefractive keratectomy (PRK). The performance of the proposed segmentation system is evaluated against manually traced ground-truth images based on a database consisting of 498 corneal sub-basal nerve images (238 are normal and 260 are abnormal). In addition, the robustness and efficiency of the proposed system in extracting morphometric features with clinical utility was evaluated in 919 images taken from healthy subjects and diabetic patients with and without neuropathy. We demonstrate rapid (13 seconds/image), robust and effective automated corneal nerve quantification. The proposed system will be deployed as a useful clinical tool to support the expertise of ophthalmologists and save the clinician time in a busy clinical setting.

AB - Diabetic Peripheral Neuropathy (DPN) is one of the most common types of diabetes that can affect the cornea. An accurate analysis of the nerve structures can assist the early diagnosis of this disease. This paper proposes a robust, fast and fully automatic nerve segmentation and morphometric parameter quantification system for corneal confocal microscope images. The segmentation part consists of three main steps. First, a preprocessing step is applied to enhance the visibility of the nerves and remove noise using anisotropic diffusion filtering, specifically a Coherence filter followed by Gaussian filtering. Second, morphological operations are applied to remove unwanted objects in the input image such as epithelial cells and small nerve segments. Finally, an edge detection step is applied to detect all the nerves in the input image. In this step, an efficient algorithm for connecting discontinuous nerves is proposed. In the morphometric parameters quantification part, a number of features are extracted, including thickness, tortuosity and length of nerve, which may be used for the early diagnosis of diabetic polyneuropathy and when planning Laser-Assisted in situ Keratomileusis (LASIK) or Photorefractive keratectomy (PRK). The performance of the proposed segmentation system is evaluated against manually traced ground-truth images based on a database consisting of 498 corneal sub-basal nerve images (238 are normal and 260 are abnormal). In addition, the robustness and efficiency of the proposed system in extracting morphometric features with clinical utility was evaluated in 919 images taken from healthy subjects and diabetic patients with and without neuropathy. We demonstrate rapid (13 seconds/image), robust and effective automated corneal nerve quantification. The proposed system will be deployed as a useful clinical tool to support the expertise of ophthalmologists and save the clinician time in a busy clinical setting.

KW - Anisotropic diffusion filtering

KW - Automatic nerve segmentation

KW - Corneal confocal microscopy

KW - Corneal subbasal epithelium

KW - Diabetes

KW - Diabetic peripheral neuropathy

UR - http://www.scopus.com/inward/record.url?scp=84982683748&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84982683748&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2016.07.032

DO - 10.1016/j.cmpb.2016.07.032

M3 - Article

VL - 135

SP - 151

EP - 166

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -