Application of higher-order spectra for automated grading of diabetic maculopathy
Authors:
- Muthu Rama Krishnan MookiahMMMuthu Rama Krishnan Mookiah
- U. Rajendra AcharyaU. Rajendra Acharya
- Vinod ChandranVCVinod Chandran
- Roshan Joy MartisRMRoshan Joy Martis
- Jen Hong TanJTJen Hong Tan
- Joel E. W. KohJKJoel E. W. Koh
- Chua Kuang ChuaCCChua Kuang Chua
- Louis TongLTLouis Tong
- Augustinus LaudeALAugustinus Laude
- 18 April 2015
- journal article
- research article
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 53 (12) , 1319-1331
Abstract
Diabetic macular edema (DME) is one of the most common causes of visual loss among diabetes mellitus patients. Early detection and successive treatment may improve the visual acuity. DME is mainly graded into non-clinically significant macular edema (NCSME) and clinically significant macular edema according to the location of hard exudates in the macula region. DME can be identified by manual examination of fundus images. It is laborious and resource intensive. Hence, in this work, automated grading of DME is proposed using higher-order spectra (HOS) of Radon transform projections of the fundus images. We have used third-order cumulants and bispectrum magnitude, in this work, as features, and compared their performance. They can capture subtle changes in the fundus image. Spectral regression discriminant analysis (SRDA) reduces feature dimension, and minimum redundancy maximum relevance method is used to rank the significant SRDA components. Ranked features are fed to various supervised classifiers, viz. Naive Bayes, AdaBoost and support vector machine, to discriminate No DME, NCSME and clinically significant macular edema classes. The performance of our system is evaluated using the publicly available MESSIDOR dataset (300 images) and also verified with a local dataset (300 images). Our results show that HOS cumulants and bispectrum magnitude obtained an average accuracy of 95.56 and 94.39 % for MESSIDOR dataset and 95.93 and 93.33 % for local dataset, respectively.Keywords
This publication has 41 references indexed in Scilit:
- Medical management for the prevention and treatment of diabetic macular edemaSurvey of Ophthalmology, 2013
- Global Prevalence and Major Risk Factors of Diabetic RetinopathyDiabetes Care, 2012
- Exudate-based diabetic macular edema detection in fundus images using publicly available datasetsMedical Image Analysis, 2012
- Automated grading for diabetic retinopathy: a large-scale audit using arbitration by clinical expertsBritish Journal of Ophthalmology, 2010
- Automatic identification of diabetic maculopathy stages using fundus imagesJournal of Medical Engineering & Technology, 2009
- Analysis of epileptic EEG signals using higher order spectraJournal of Medical Engineering & Technology, 2009
- Cardiac state diagnosis using higher order spectra of heart rate variabilityJournal of Medical Engineering & Technology, 2008
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Pattern recognition using invariants defined from higher order spectra: 2-D image inputsIEEE Transactions on Image Processing, 1997
- Pattern Recognition Using Invariants Defined From Higher Order Spectra- One Dimensional InputsIEEE Transactions on Signal Processing, 1993