The Effect of Watermarking on Automated Assessment of Diabetic Retinal Images

A D Lock, Alastair Robert Allen, Alan Duncan Fleming, Keith A Goatman

Research output: Contribution to journalArticle

Abstract

Screening programs for the detection of diabetic retinopathy are being introduced in the UK and elsewhere. The use of automated grading software for this purpose has been proposed and shown to perform with sufficient accuracy. Separately, the use of watermarking for authentication is gaining traction in medical imaging. Much work has been conducted on reducing the perceptibility of watermarking to the human visual system, though little has investigated the perceptibility to machine vision applications. This paper describes a study on the effect of watermarking of retinal images on the automated detection of image clarity and disease. Various watermarking algorithms at a range of embedding capacities are compared. Results are presented for differences in clarity and number of microaneurysms (MA) detected for watermarked images compared to the originals. Sensitivity and specificity of disease and inadequate clarity detection are presented, with a significant reduction in specificity found for generalized least significant bit embedding in both MA and clarity detection.
Original languageEnglish
JournalIEEE Transactions on Information Technology in Biomedicine
Publication statusAccepted/In press - 2012

Fingerprint

Watermarking
Traction
Diabetic Retinopathy
Diagnostic Imaging
Software
Sensitivity and Specificity
Medical imaging
Authentication
Computer vision
Screening
Microaneurysm

Keywords

  • Automated detection,
  • image processing
  • retinal imaging
  • microaneursysm
  • reversible watermarking

Cite this

The Effect of Watermarking on Automated Assessment of Diabetic Retinal Images. / Lock, A D; Allen, Alastair Robert; Fleming, Alan Duncan; Goatman, Keith A.

In: IEEE Transactions on Information Technology in Biomedicine, 2012.

Research output: Contribution to journalArticle

@article{e1cf3c4765ef45f5ac081cbdd80dc1e8,
title = "The Effect of Watermarking on Automated Assessment of Diabetic Retinal Images",
abstract = "Screening programs for the detection of diabetic retinopathy are being introduced in the UK and elsewhere. The use of automated grading software for this purpose has been proposed and shown to perform with sufficient accuracy. Separately, the use of watermarking for authentication is gaining traction in medical imaging. Much work has been conducted on reducing the perceptibility of watermarking to the human visual system, though little has investigated the perceptibility to machine vision applications. This paper describes a study on the effect of watermarking of retinal images on the automated detection of image clarity and disease. Various watermarking algorithms at a range of embedding capacities are compared. Results are presented for differences in clarity and number of microaneurysms (MA) detected for watermarked images compared to the originals. Sensitivity and specificity of disease and inadequate clarity detection are presented, with a significant reduction in specificity found for generalized least significant bit embedding in both MA and clarity detection.",
keywords = "Automated detection,, image processing, retinal imaging, microaneursysm, reversible watermarking",
author = "Lock, {A D} and Allen, {Alastair Robert} and Fleming, {Alan Duncan} and Goatman, {Keith A}",
year = "2012",
language = "English",
journal = "IEEE Transactions on Information Technology in Biomedicine",
issn = "1089-7771",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - The Effect of Watermarking on Automated Assessment of Diabetic Retinal Images

AU - Lock, A D

AU - Allen, Alastair Robert

AU - Fleming, Alan Duncan

AU - Goatman, Keith A

PY - 2012

Y1 - 2012

N2 - Screening programs for the detection of diabetic retinopathy are being introduced in the UK and elsewhere. The use of automated grading software for this purpose has been proposed and shown to perform with sufficient accuracy. Separately, the use of watermarking for authentication is gaining traction in medical imaging. Much work has been conducted on reducing the perceptibility of watermarking to the human visual system, though little has investigated the perceptibility to machine vision applications. This paper describes a study on the effect of watermarking of retinal images on the automated detection of image clarity and disease. Various watermarking algorithms at a range of embedding capacities are compared. Results are presented for differences in clarity and number of microaneurysms (MA) detected for watermarked images compared to the originals. Sensitivity and specificity of disease and inadequate clarity detection are presented, with a significant reduction in specificity found for generalized least significant bit embedding in both MA and clarity detection.

AB - Screening programs for the detection of diabetic retinopathy are being introduced in the UK and elsewhere. The use of automated grading software for this purpose has been proposed and shown to perform with sufficient accuracy. Separately, the use of watermarking for authentication is gaining traction in medical imaging. Much work has been conducted on reducing the perceptibility of watermarking to the human visual system, though little has investigated the perceptibility to machine vision applications. This paper describes a study on the effect of watermarking of retinal images on the automated detection of image clarity and disease. Various watermarking algorithms at a range of embedding capacities are compared. Results are presented for differences in clarity and number of microaneurysms (MA) detected for watermarked images compared to the originals. Sensitivity and specificity of disease and inadequate clarity detection are presented, with a significant reduction in specificity found for generalized least significant bit embedding in both MA and clarity detection.

KW - Automated detection,

KW - image processing

KW - retinal imaging

KW - microaneursysm

KW - reversible watermarking

M3 - Article

JO - IEEE Transactions on Information Technology in Biomedicine

JF - IEEE Transactions on Information Technology in Biomedicine

SN - 1089-7771

ER -