Three-Dimensional Segmentation of the Ex-Vivo Anterior Lamina Cribrosa from Second-Harmonic Imaging Microscopy

Sundaresh Ram, Forest Danford, Stephen Howerton, Jeffrey J Rodriguez, Jonathan P Vande Geest

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The lamina cribrosa (LC) is a connective tissue in the posterior eye with a complex mesh-like trabecular microstructure, through which all the retinal ganglion cell axons and central retinal vessels pass. Recent studies have demonstrated that changes in the structure of the LC correlate with glaucomatous damage. Thus, accurate segmentation and reconstruction of the LC is of utmost importance. This paper presents a new automated method for segmenting the microstructure of the anterior LC in the images obtained via multiphoton microscopy using a combination of ideas. In order to reduce noise, we first smooth the input image using a 4-D collaborative filtering scheme. Next, we enhance the beam-like trabecular microstructure of the LC using wavelet multiresolution analysis. The enhanced LC microstructure is then automatically extracted using a combination of histogram thresholding and graph-cut binarization. Finally, we use morphological area opening as a postprocessing step to remove the small and unconnected 3-D regions in the binarized images. The performance of the proposed method is evaluated using mutual overlap accuracy, Tanimoto index, F-score, and Rand index. Quantitative and qualitative results show that the proposed algorithm provides improved segmentation accuracy and computational efficiency compared to the other recent algorithms.

Original languageEnglish (US)
Pages (from-to)1617-1629
Number of pages13
JournalIEEE Transactions on Biomedical Engineering
Volume65
Issue number7
DOIs
StatePublished - Jul 1 2018

Fingerprint

Microscopic examination
Imaging techniques
Microstructure
D region
Multiresolution analysis
Collaborative filtering
Computational efficiency
Tissue

Keywords

  • Graph cut segmentation
  • histogram thresholding
  • lamina cribrosa
  • volumetric data denoising
  • wavelet

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Three-Dimensional Segmentation of the Ex-Vivo Anterior Lamina Cribrosa from Second-Harmonic Imaging Microscopy. / Ram, Sundaresh; Danford, Forest; Howerton, Stephen; Rodriguez, Jeffrey J; Vande Geest, Jonathan P.

In: IEEE Transactions on Biomedical Engineering, Vol. 65, No. 7, 01.07.2018, p. 1617-1629.

Research output: Contribution to journalArticle

@article{c4e462e78cef4d82b53d24b5c441084b,
title = "Three-Dimensional Segmentation of the Ex-Vivo Anterior Lamina Cribrosa from Second-Harmonic Imaging Microscopy",
abstract = "The lamina cribrosa (LC) is a connective tissue in the posterior eye with a complex mesh-like trabecular microstructure, through which all the retinal ganglion cell axons and central retinal vessels pass. Recent studies have demonstrated that changes in the structure of the LC correlate with glaucomatous damage. Thus, accurate segmentation and reconstruction of the LC is of utmost importance. This paper presents a new automated method for segmenting the microstructure of the anterior LC in the images obtained via multiphoton microscopy using a combination of ideas. In order to reduce noise, we first smooth the input image using a 4-D collaborative filtering scheme. Next, we enhance the beam-like trabecular microstructure of the LC using wavelet multiresolution analysis. The enhanced LC microstructure is then automatically extracted using a combination of histogram thresholding and graph-cut binarization. Finally, we use morphological area opening as a postprocessing step to remove the small and unconnected 3-D regions in the binarized images. The performance of the proposed method is evaluated using mutual overlap accuracy, Tanimoto index, F-score, and Rand index. Quantitative and qualitative results show that the proposed algorithm provides improved segmentation accuracy and computational efficiency compared to the other recent algorithms.",
keywords = "Graph cut segmentation, histogram thresholding, lamina cribrosa, volumetric data denoising, wavelet",
author = "Sundaresh Ram and Forest Danford and Stephen Howerton and Rodriguez, {Jeffrey J} and {Vande Geest}, {Jonathan P}",
year = "2018",
month = "7",
day = "1",
doi = "10.1109/TBME.2017.2674521",
language = "English (US)",
volume = "65",
pages = "1617--1629",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "7",

}

TY - JOUR

T1 - Three-Dimensional Segmentation of the Ex-Vivo Anterior Lamina Cribrosa from Second-Harmonic Imaging Microscopy

AU - Ram, Sundaresh

AU - Danford, Forest

AU - Howerton, Stephen

AU - Rodriguez, Jeffrey J

AU - Vande Geest, Jonathan P

PY - 2018/7/1

Y1 - 2018/7/1

N2 - The lamina cribrosa (LC) is a connective tissue in the posterior eye with a complex mesh-like trabecular microstructure, through which all the retinal ganglion cell axons and central retinal vessels pass. Recent studies have demonstrated that changes in the structure of the LC correlate with glaucomatous damage. Thus, accurate segmentation and reconstruction of the LC is of utmost importance. This paper presents a new automated method for segmenting the microstructure of the anterior LC in the images obtained via multiphoton microscopy using a combination of ideas. In order to reduce noise, we first smooth the input image using a 4-D collaborative filtering scheme. Next, we enhance the beam-like trabecular microstructure of the LC using wavelet multiresolution analysis. The enhanced LC microstructure is then automatically extracted using a combination of histogram thresholding and graph-cut binarization. Finally, we use morphological area opening as a postprocessing step to remove the small and unconnected 3-D regions in the binarized images. The performance of the proposed method is evaluated using mutual overlap accuracy, Tanimoto index, F-score, and Rand index. Quantitative and qualitative results show that the proposed algorithm provides improved segmentation accuracy and computational efficiency compared to the other recent algorithms.

AB - The lamina cribrosa (LC) is a connective tissue in the posterior eye with a complex mesh-like trabecular microstructure, through which all the retinal ganglion cell axons and central retinal vessels pass. Recent studies have demonstrated that changes in the structure of the LC correlate with glaucomatous damage. Thus, accurate segmentation and reconstruction of the LC is of utmost importance. This paper presents a new automated method for segmenting the microstructure of the anterior LC in the images obtained via multiphoton microscopy using a combination of ideas. In order to reduce noise, we first smooth the input image using a 4-D collaborative filtering scheme. Next, we enhance the beam-like trabecular microstructure of the LC using wavelet multiresolution analysis. The enhanced LC microstructure is then automatically extracted using a combination of histogram thresholding and graph-cut binarization. Finally, we use morphological area opening as a postprocessing step to remove the small and unconnected 3-D regions in the binarized images. The performance of the proposed method is evaluated using mutual overlap accuracy, Tanimoto index, F-score, and Rand index. Quantitative and qualitative results show that the proposed algorithm provides improved segmentation accuracy and computational efficiency compared to the other recent algorithms.

KW - Graph cut segmentation

KW - histogram thresholding

KW - lamina cribrosa

KW - volumetric data denoising

KW - wavelet

UR - http://www.scopus.com/inward/record.url?scp=85049067798&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049067798&partnerID=8YFLogxK

U2 - 10.1109/TBME.2017.2674521

DO - 10.1109/TBME.2017.2674521

M3 - Article

VL - 65

SP - 1617

EP - 1629

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 7

ER -