Peripapillary atrophy detection by sparse biologically inspired feature manifold

Cheng, J; Tao, D; Liu, J; Wong, DWK; Tan, NM; Wong, TY; Saw, SM

Peripapillary atrophy detection by sparse biologically inspired feature manifold

Cheng, J Tao, D

Liu, J Wong, DWK Tan, NM Wong, TY Saw, SM

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Medical Imaging, 2012, 31 (12), pp. 2355 - 2365
Issue Date:: 2012-12-10

Closed Access

	Filename	Description	Size
	2012001501OK.pdf		1.67 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Cheng, J	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.contributor.author	Liu, J	en_US
dc.contributor.author	Wong, DWK	en_US
dc.contributor.author	Tan, NM	en_US
dc.contributor.author	Wong, TY	en_US
dc.contributor.author	Saw, SM	en_US
dc.date.issued	2012-12-10	en_US
dc.identifier.citation	IEEE Transactions on Medical Imaging, 2012, 31 (12), pp. 2355 - 2365	en_US
dc.identifier.issn	0278-0062	en_US
dc.identifier.uri	http://hdl.handle.net/10453/23051
dc.description.abstract	Peripapillary atrophy (PPA) is an atrophy of pre-existing retina tissue. Because of its association with eye diseases such as myopia and glaucoma, PPA is an important indicator for diagnosis of these diseases. Experienced ophthalmologists are able to determine the presence of PPA using visual information from the retinal images. However, it is tedious, time consuming and subjective to examine all images especially in a screening program. This paper presents biologically inspired feature (BIF) for the automatic detection of PPA. BIF mimics the process of cortex for visual perception. In the proposed method, a focal region is segmented from the retinal image and the BIF is extracted. As BIF is an intrinsically low dimensional feature embedded in a high dimensional space, it is not suitable to measure the similarity between two BIFs directly based on the Euclidean distance. Therefore, it is necessary to obtain a suitable mapping to reduce the dimensionality. In this paper, we explore sparse transfer learning to transfer the label information from ophthalmologists to the sample distribution knowledge contained in all samples. Selective pair-wise discriminant analysis is used to define two strategies of sparse transfer learning: negative and positive sparse transfer learning. Experimental results show that negative sparse transfer learning is superior to the positive one for this task. The proposed BIF based approach achieves an accuracy of more than 90% in detecting PPA, much better than previous methods. It can be used to save the workload of ophthalmologists and thus reduce the diagnosis costs. © 2012 IEEE.	en_US
dc.relation.ispartof	IEEE Transactions on Medical Imaging	en_US
dc.relation.isbasedon	10.1109/TMI.2012.2218118	en_US
dc.subject.classification	Nuclear Medicine & Medical Imaging	en_US
dc.subject.mesh	Optic Disk	en_US
dc.subject.mesh	Retina	en_US
dc.subject.mesh	Humans	en_US
dc.subject.mesh	Optic Atrophy	en_US
dc.subject.mesh	Retinal Diseases	en_US
dc.subject.mesh	Diagnostic Techniques, Ophthalmological	en_US
dc.subject.mesh	Algorithms	en_US
dc.subject.mesh	Image Processing, Computer-Assisted	en_US
dc.subject.mesh	Databases, Factual	en_US
dc.subject.mesh	Child	en_US
dc.title	Peripapillary atrophy detection by sparse biologically inspired feature manifold	en_US
dc.type	Journal Article
utslib.citation.volume	12	en_US
utslib.citation.volume	31	en_US
utslib.for	0903 Biomedical Engineering	en_US
utslib.for	08 Information and Computing Sciences	en_US
utslib.for	09 Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.issue	12	en_US
pubs.publication-status	Published	en_US
pubs.volume	31	en_US

Abstract:

Peripapillary atrophy (PPA) is an atrophy of pre-existing retina tissue. Because of its association with eye diseases such as myopia and glaucoma, PPA is an important indicator for diagnosis of these diseases. Experienced ophthalmologists are able to determine the presence of PPA using visual information from the retinal images. However, it is tedious, time consuming and subjective to examine all images especially in a screening program. This paper presents biologically inspired feature (BIF) for the automatic detection of PPA. BIF mimics the process of cortex for visual perception. In the proposed method, a focal region is segmented from the retinal image and the BIF is extracted. As BIF is an intrinsically low dimensional feature embedded in a high dimensional space, it is not suitable to measure the similarity between two BIFs directly based on the Euclidean distance. Therefore, it is necessary to obtain a suitable mapping to reduce the dimensionality. In this paper, we explore sparse transfer learning to transfer the label information from ophthalmologists to the sample distribution knowledge contained in all samples. Selective pair-wise discriminant analysis is used to define two strategies of sparse transfer learning: negative and positive sparse transfer learning. Experimental results show that negative sparse transfer learning is superior to the positive one for this task. The proposed BIF based approach achieves an accuracy of more than 90% in detecting PPA, much better than previous methods. It can be used to save the workload of ophthalmologists and thus reduce the diagnosis costs. © 2012 IEEE.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/23051