A Two Layer Sparse Autoencoder for Glaucoma Identification with Fundus Images

Raghavendra, U and Gudigar, Anjan and Bhandary, Sulatha V and Rao, Tejaswini and Ciaccio, Edward J and Acharya, Rajendra U (2019) A Two Layer Sparse Autoencoder for Glaucoma Identification with Fundus Images. Journal of Medical Systems, 43. pp. 1-9. ISSN 0148-5598

[img] PDF
7031.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy


Glaucoma is a type of eye condition which may result in partial or consummate vision loss. Higher intraocular pressure is the leading cause for this condition. Screening for glaucoma and early detection can avert vision loss. Computer aided diagnosis (CAD) is an automated process with the potential to identify glaucoma early through quantitative analysis of digital fundus images.PreparinganeffectivemodelforCADrequiresalargedatabase.ThisstudypresentsaCADtoolfortheprecisedetection of glaucoma using a machine learning approach. An autoencoder is trained to determine effective and important features from fundusimages.Thesefeaturesareusedtodevelopclassesofglaucomafortesting.ThemethodachievedanF−measurevalueof 0.95utilizing1426digitalfundusimages(589controland837glaucoma).Theefficacyofthesystemisevident,andissuggestive of its possible utility as an additional tool for verification of clinical decisions.

Item Type: Article
Uncontrolled Keywords: CAD .Cascade .Glaucoma .Sparseautoencoder
Subjects: Engineering > MIT Manipal > Instrumentation and Control
Depositing User: MIT Library
Date Deposited: 06 Aug 2019 09:22
Last Modified: 06 Aug 2019 09:22
URI: http://eprints.manipal.edu/id/eprint/154314

Actions (login required)

View Item View Item