Automated Corneal Nerve Segmentation Using Weighted Local Phase Tensor

Kun Zhao; Hui Zhang; Yitian Zhao; Jianyang Xie; Yalin Zheng; David Borroni; Hong Qi; Jiang Liu

doi:10.1007/978-3-030-39343-4_39

Automated Corneal Nerve Segmentation Using Weighted Local Phase Tensor

Kun Zhao, Hui Zhang (Corresponding Author), Yitian Zhao (Corresponding Author), Jianyang Xie, Yalin Zheng, David Borroni, Hong Qi, Jiang Liu

Rīga Stradiņš University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

There has been increasing interest in the analysis of corneal nerve fibers to support examination and diagnosis of many diseases, and for this purpose, automated nerve fiber segmentation is a fundamental step. Existing methods of automated corneal nerve fiber detection continue to pose difficulties due to multiple factors, such as poor contrast and fragmented fibers caused by inaccurate focus. To address these problems, in this paper we propose a novel weighted local phase tensor-based curvilinear structure filtering method. This method not only takes into account local phase features using a quadrature filter to enhance edges and lines, but also utilizes the weighted geometric mean of the blurred and shifted responses to allow better tolerance of curvilinear structures with irregular appearances. To demonstrate its effectiveness, we apply this framework to 1578 corneal confocal microscopy images. The experimental results show that the proposed method outperforms existing state-of-the-art methods in applicability, effectiveness, and accuracy.

Original language	English
Title of host publication	Medical Image Understanding and Analysis - 23rd Conference, MIUA 2019, Proceedings
Editors	Yalin Zheng, Bryan M. Williams, Ke Chen
Publisher	Springer
Pages	459-469
Number of pages	11
ISBN (Print)	9783030393427
DOIs	https://doi.org/10.1007/978-3-030-39343-4_39
Publication status	Published - 2020
Event	23rd Conference on Medical Image Understanding and Analysis - Liverpool, United Kingdom Duration: 24 Jul 2019 → 26 Jul 2019 Conference number: 23

Publication series

Name	Communications in Computer and Information Science
Volume	1065 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	23rd Conference on Medical Image Understanding and Analysis
Abbreviated title	MIUA 2019
Country/Territory	United Kingdom
City	Liverpool
Period	24/07/19 → 26/07/19

Keywords*

Corneal nerve
Curvilinear structure
Local phase
Segmentation

Field of Science*

1.2 Computer and information sciences

Publication Type*

3.1. Articles or chapters in proceedings/scientific books indexed in Web of Science and/or Scopus database

Access to Document

10.1007/978-3-030-39343-4_39

Cite this

Zhao, K., Zhang, H., Zhao, Y., Xie, J., Zheng, Y., Borroni, D., Qi, H., & Liu, J. (2020). Automated Corneal Nerve Segmentation Using Weighted Local Phase Tensor. In Y. Zheng, B. M. Williams, & K. Chen (Eds.), Medical Image Understanding and Analysis - 23rd Conference, MIUA 2019, Proceedings (pp. 459-469). (Communications in Computer and Information Science; Vol. 1065 CCIS). Springer. https://doi.org/10.1007/978-3-030-39343-4_39

@inproceedings{09de348d43d249c4ad322d2ec7ab479d,

title = "Automated Corneal Nerve Segmentation Using Weighted Local Phase Tensor",

abstract = "There has been increasing interest in the analysis of corneal nerve fibers to support examination and diagnosis of many diseases, and for this purpose, automated nerve fiber segmentation is a fundamental step. Existing methods of automated corneal nerve fiber detection continue to pose difficulties due to multiple factors, such as poor contrast and fragmented fibers caused by inaccurate focus. To address these problems, in this paper we propose a novel weighted local phase tensor-based curvilinear structure filtering method. This method not only takes into account local phase features using a quadrature filter to enhance edges and lines, but also utilizes the weighted geometric mean of the blurred and shifted responses to allow better tolerance of curvilinear structures with irregular appearances. To demonstrate its effectiveness, we apply this framework to 1578 corneal confocal microscopy images. The experimental results show that the proposed method outperforms existing state-of-the-art methods in applicability, effectiveness, and accuracy.",

keywords = "Corneal nerve, Curvilinear structure, Local phase, Segmentation",

author = "Kun Zhao and Hui Zhang and Yitian Zhao and Jianyang Xie and Yalin Zheng and David Borroni and Hong Qi and Jiang Liu",

note = "Funding Information: Acknowledgment. This work was supported by National Natural Science Foundation of China (61601029, 61602322), Zhejiang Provincial and Ningbo Natural Science Foundation (LZ19F010001, 2018A610055). Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 23rd Conference on Medical Image Understanding and Analysis, MIUA 2019 ; Conference date: 24-07-2019 Through 26-07-2019",

year = "2020",

doi = "10.1007/978-3-030-39343-4_39",

language = "English",

isbn = "9783030393427",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "459--469",

editor = "Yalin Zheng and Williams, {Bryan M.} and Ke Chen",

booktitle = "Medical Image Understanding and Analysis - 23rd Conference, MIUA 2019, Proceedings",

address = "Germany",

}

Zhao, K, Zhang, H, Zhao, Y, Xie, J, Zheng, Y, Borroni, D, Qi, H & Liu, J 2020, Automated Corneal Nerve Segmentation Using Weighted Local Phase Tensor. in Y Zheng, BM Williams & K Chen (eds), Medical Image Understanding and Analysis - 23rd Conference, MIUA 2019, Proceedings. Communications in Computer and Information Science, vol. 1065 CCIS, Springer, pp. 459-469, 23rd Conference on Medical Image Understanding and Analysis, Liverpool, United Kingdom, 24/07/19. https://doi.org/10.1007/978-3-030-39343-4_39

Automated Corneal Nerve Segmentation Using Weighted Local Phase Tensor. / Zhao, Kun; Zhang, Hui (Corresponding Author); Zhao, Yitian (Corresponding Author) et al.
Medical Image Understanding and Analysis - 23rd Conference, MIUA 2019, Proceedings. ed. / Yalin Zheng; Bryan M. Williams; Ke Chen. Springer, 2020. p. 459-469 (Communications in Computer and Information Science; Vol. 1065 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automated Corneal Nerve Segmentation Using Weighted Local Phase Tensor

AU - Zhao, Kun

AU - Zhang, Hui

AU - Zhao, Yitian

AU - Xie, Jianyang

AU - Zheng, Yalin

AU - Borroni, David

AU - Qi, Hong

AU - Liu, Jiang

N1 - Conference code: 23

PY - 2020

Y1 - 2020

N2 - There has been increasing interest in the analysis of corneal nerve fibers to support examination and diagnosis of many diseases, and for this purpose, automated nerve fiber segmentation is a fundamental step. Existing methods of automated corneal nerve fiber detection continue to pose difficulties due to multiple factors, such as poor contrast and fragmented fibers caused by inaccurate focus. To address these problems, in this paper we propose a novel weighted local phase tensor-based curvilinear structure filtering method. This method not only takes into account local phase features using a quadrature filter to enhance edges and lines, but also utilizes the weighted geometric mean of the blurred and shifted responses to allow better tolerance of curvilinear structures with irregular appearances. To demonstrate its effectiveness, we apply this framework to 1578 corneal confocal microscopy images. The experimental results show that the proposed method outperforms existing state-of-the-art methods in applicability, effectiveness, and accuracy.

AB - There has been increasing interest in the analysis of corneal nerve fibers to support examination and diagnosis of many diseases, and for this purpose, automated nerve fiber segmentation is a fundamental step. Existing methods of automated corneal nerve fiber detection continue to pose difficulties due to multiple factors, such as poor contrast and fragmented fibers caused by inaccurate focus. To address these problems, in this paper we propose a novel weighted local phase tensor-based curvilinear structure filtering method. This method not only takes into account local phase features using a quadrature filter to enhance edges and lines, but also utilizes the weighted geometric mean of the blurred and shifted responses to allow better tolerance of curvilinear structures with irregular appearances. To demonstrate its effectiveness, we apply this framework to 1578 corneal confocal microscopy images. The experimental results show that the proposed method outperforms existing state-of-the-art methods in applicability, effectiveness, and accuracy.

KW - Corneal nerve

KW - Curvilinear structure

KW - Local phase

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85079089775&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-39343-4_39

DO - 10.1007/978-3-030-39343-4_39

M3 - Conference contribution

AN - SCOPUS:85079089775

SN - 9783030393427

T3 - Communications in Computer and Information Science

SP - 459

EP - 469

BT - Medical Image Understanding and Analysis - 23rd Conference, MIUA 2019, Proceedings

A2 - Zheng, Yalin

A2 - Williams, Bryan M.

A2 - Chen, Ke

PB - Springer

T2 - 23rd Conference on Medical Image Understanding and Analysis

Y2 - 24 July 2019 through 26 July 2019

ER -

Zhao K, Zhang H, Zhao Y, Xie J, Zheng Y, Borroni D et al. Automated Corneal Nerve Segmentation Using Weighted Local Phase Tensor. In Zheng Y, Williams BM, Chen K, editors, Medical Image Understanding and Analysis - 23rd Conference, MIUA 2019, Proceedings. Springer. 2020. p. 459-469. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-39343-4_39

Automated Corneal Nerve Segmentation Using Weighted Local Phase Tensor

Abstract

Publication series

Conference

Keywords*

Field of Science*

Publication Type*

Access to Document

Other files and links

Fingerprint

Cite this