Pterygium-Net: a deep learning approach to pterygium detection and localization

Mohd Asyraf Zulkifley, Siti Raihanah Abdani, Nuraisyah Hani Zulkifley

Research output: Contribution to journalArticle

Abstract

Automatic pterygium detection is an essential screening tool for health community service groups. It allows non-expert to perform screening process without the needs of big and expensive equipment, especially for the application in rural areas. Thence, patients who have been screened as positive pterygium will be referred to the certified medical personnel for further diagnosis and treatment. Current state-of-the-art algorithms for pterygium detection rely on basic machine learning approach such as artificial neural network and support vector machine, which have not yet achieved high detection sensitivity and specificity as required in standard medical practice. Hence, a deep learning approach based on fully convolutional neural networks is proposed to detect and localize the pterygium infected tissues automatically. The input image requirement for the developed system is low as any commercial mobile phone camera is sufficient. Moreover, the developed algorithm, which we refer as Pterygium-Net works well even if the eye image is captured under low lighting condition with pupil position is not at the center location. Pterygium-Net utilizes three layers of convolutional neural networks (CNN) and three layers of fully connected networks. Two steps are implemented to overcome lacks of training data by generating synthetic images and pre-training the CNN weights and biases in a different public dataset. As for pterygium localization, an additional step of box proposal based on edges information is used to generate possible regions of the pterygium infected tissues. Hanning window is also applied to the generated regions to give more weightage to the center area. Experimental results show that Pterygium-Net produces high average detection sensitivity and specificity of 0.95 and 0.983, respectively. As for pterygium tissues localization, the algorithm achieves 0.811 accuracy with a very low failure rate of 0.053. In the future, deeper networks can be implemented to further improve pterygium localization.

Original languageEnglish
JournalMultimedia Tools and Applications
DOIs
Publication statusAccepted/In press - 1 Jan 2019

Fingerprint

Neural networks
Tissue
Screening
Mobile phones
Support vector machines
Learning systems
Lighting
Cameras
Health
Personnel
Deep learning

Keywords

  • Machine learning
  • Pterygium detection
  • Pterygium localization

ASJC Scopus subject areas

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Pterygium-Net : a deep learning approach to pterygium detection and localization. / Zulkifley, Mohd Asyraf; Abdani, Siti Raihanah; Zulkifley, Nuraisyah Hani.

In: Multimedia Tools and Applications, 01.01.2019.

Research output: Contribution to journalArticle

@article{f34ffa33e51d4922aa5a170b2152a062,
title = "Pterygium-Net: a deep learning approach to pterygium detection and localization",
abstract = "Automatic pterygium detection is an essential screening tool for health community service groups. It allows non-expert to perform screening process without the needs of big and expensive equipment, especially for the application in rural areas. Thence, patients who have been screened as positive pterygium will be referred to the certified medical personnel for further diagnosis and treatment. Current state-of-the-art algorithms for pterygium detection rely on basic machine learning approach such as artificial neural network and support vector machine, which have not yet achieved high detection sensitivity and specificity as required in standard medical practice. Hence, a deep learning approach based on fully convolutional neural networks is proposed to detect and localize the pterygium infected tissues automatically. The input image requirement for the developed system is low as any commercial mobile phone camera is sufficient. Moreover, the developed algorithm, which we refer as Pterygium-Net works well even if the eye image is captured under low lighting condition with pupil position is not at the center location. Pterygium-Net utilizes three layers of convolutional neural networks (CNN) and three layers of fully connected networks. Two steps are implemented to overcome lacks of training data by generating synthetic images and pre-training the CNN weights and biases in a different public dataset. As for pterygium localization, an additional step of box proposal based on edges information is used to generate possible regions of the pterygium infected tissues. Hanning window is also applied to the generated regions to give more weightage to the center area. Experimental results show that Pterygium-Net produces high average detection sensitivity and specificity of 0.95 and 0.983, respectively. As for pterygium tissues localization, the algorithm achieves 0.811 accuracy with a very low failure rate of 0.053. In the future, deeper networks can be implemented to further improve pterygium localization.",
keywords = "Machine learning, Pterygium detection, Pterygium localization",
author = "Zulkifley, {Mohd Asyraf} and Abdani, {Siti Raihanah} and Zulkifley, {Nuraisyah Hani}",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s11042-019-08130-x",
language = "English",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Pterygium-Net

T2 - a deep learning approach to pterygium detection and localization

AU - Zulkifley, Mohd Asyraf

AU - Abdani, Siti Raihanah

AU - Zulkifley, Nuraisyah Hani

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Automatic pterygium detection is an essential screening tool for health community service groups. It allows non-expert to perform screening process without the needs of big and expensive equipment, especially for the application in rural areas. Thence, patients who have been screened as positive pterygium will be referred to the certified medical personnel for further diagnosis and treatment. Current state-of-the-art algorithms for pterygium detection rely on basic machine learning approach such as artificial neural network and support vector machine, which have not yet achieved high detection sensitivity and specificity as required in standard medical practice. Hence, a deep learning approach based on fully convolutional neural networks is proposed to detect and localize the pterygium infected tissues automatically. The input image requirement for the developed system is low as any commercial mobile phone camera is sufficient. Moreover, the developed algorithm, which we refer as Pterygium-Net works well even if the eye image is captured under low lighting condition with pupil position is not at the center location. Pterygium-Net utilizes three layers of convolutional neural networks (CNN) and three layers of fully connected networks. Two steps are implemented to overcome lacks of training data by generating synthetic images and pre-training the CNN weights and biases in a different public dataset. As for pterygium localization, an additional step of box proposal based on edges information is used to generate possible regions of the pterygium infected tissues. Hanning window is also applied to the generated regions to give more weightage to the center area. Experimental results show that Pterygium-Net produces high average detection sensitivity and specificity of 0.95 and 0.983, respectively. As for pterygium tissues localization, the algorithm achieves 0.811 accuracy with a very low failure rate of 0.053. In the future, deeper networks can be implemented to further improve pterygium localization.

AB - Automatic pterygium detection is an essential screening tool for health community service groups. It allows non-expert to perform screening process without the needs of big and expensive equipment, especially for the application in rural areas. Thence, patients who have been screened as positive pterygium will be referred to the certified medical personnel for further diagnosis and treatment. Current state-of-the-art algorithms for pterygium detection rely on basic machine learning approach such as artificial neural network and support vector machine, which have not yet achieved high detection sensitivity and specificity as required in standard medical practice. Hence, a deep learning approach based on fully convolutional neural networks is proposed to detect and localize the pterygium infected tissues automatically. The input image requirement for the developed system is low as any commercial mobile phone camera is sufficient. Moreover, the developed algorithm, which we refer as Pterygium-Net works well even if the eye image is captured under low lighting condition with pupil position is not at the center location. Pterygium-Net utilizes three layers of convolutional neural networks (CNN) and three layers of fully connected networks. Two steps are implemented to overcome lacks of training data by generating synthetic images and pre-training the CNN weights and biases in a different public dataset. As for pterygium localization, an additional step of box proposal based on edges information is used to generate possible regions of the pterygium infected tissues. Hanning window is also applied to the generated regions to give more weightage to the center area. Experimental results show that Pterygium-Net produces high average detection sensitivity and specificity of 0.95 and 0.983, respectively. As for pterygium tissues localization, the algorithm achieves 0.811 accuracy with a very low failure rate of 0.053. In the future, deeper networks can be implemented to further improve pterygium localization.

KW - Machine learning

KW - Pterygium detection

KW - Pterygium localization

UR - http://www.scopus.com/inward/record.url?scp=85071307629&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071307629&partnerID=8YFLogxK

U2 - 10.1007/s11042-019-08130-x

DO - 10.1007/s11042-019-08130-x

M3 - Article

AN - SCOPUS:85071307629

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

ER -