MyMedR

Displaying all 4 publications

Abstract:

Sort:

Application of higher-order spectra for automated grading of diabetic maculopathy

Mookiah MR, Acharya UR, Chandran V, Martis RJ, Tan JH, Koh JE, et al.

Med Biol Eng Comput, 2015 Dec;53(12):1319-31.
PMID: 25894464 DOI: 10.1007/s11517-015-1278-7

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.

Matched MeSH terms: Macular Edema/diagnosis*
Fulltext Spectral-domain optical coherence tomography evaluation of postoperative cystoid macular oedema following phacoemulsification with intraoperative complication

Khaw KW, Lam HH, Khang TF, Wan Ab Kadir AJ, Subrayan V

BMC Ophthalmol, 2014;14:16.
PMID: 24533465 DOI: 10.1186/1471-2415-14-16

To report the rate of cystoid macular oedema (CMO) as detected by spectral-domain optical coherence tomography (SD-OCT) after intraoperative complication during phacoemulsification. The secondary objectives include comparing mean macular thickness and best-corrected visual acuity (BCVA) between those who developed postoperative CMO against those who did not.

Matched MeSH terms: Macular Edema/diagnosis*
Fulltext Diabetic Macular Edema Management in Asian Population: Expert Panel Consensus Guidelines

Chhablani J, Wong K, Tan GS, Sudhalkar A, Laude A, Cheung CMG, et al.

Asia Pac J Ophthalmol (Phila), 2020;9(5):426-434.
PMID: 32956188 DOI: 10.1097/APO.0000000000000312

PURPOSE: The aim of this consensus article was to provide comprehensive recommendations in the management of diabetic macular edema (DME) by reviewing recent clinical evidence.
DESIGN: A questionnaire containing 47 questions was developed which encompassed clinical scenarios such as treatment response to anti-vascular endothelial growth factor and steroid, treatment side effects, as well as cost and compliance/reimbursement in the management of DME using a Dephi questionnaire as guide.
METHODS: An expert panel of 12 retinal specialists from Singapore, Malaysia, Philippines, India and Vietnam responded to this questionnaire on two separate occasions. The first round responses were compiled, analyzed and discussed in a round table discussion where a consensus was sought through voting. Consensus was considered achieved, when 9 of the 12 panellists (75%) agreed on a recommendation.
RESULTS: The DME patients were initially profiled based on their response to treatment, and the terms target response, adequate response, nonresponse, and inadequate response were defined. The panellists arrived at a consensus on various aspects of DME treatment such as need for classification of patients before treatment, first-line treatment options, appropriate time to switch between treatment modalities, and steroid-related side effects based on which recommendations were derived, and a treatment algorithm was developed.
CONCLUSIONS: This consensus article provides comprehensive, evidence-based treatment guidelines in the management of DME in Asian population. In addition, it also provides recommendations on other aspects of DME management such as steroid treatment for stable glaucoma patients, management of intraocular pressure rise, and recommendations for cataract development.

Matched MeSH terms: Macular Edema/diagnosis
Scanning laser edema index: a reliable tool to correlate with diabetic retinopathy and systemic risk factors?

Peyman M, Tajunisah I, Loo A, Chuah KC, Subrayan V

J Diabetes Complications, 2012 May-Jun;26(3):210-3.
PMID: 22520399 DOI: 10.1016/j.jdiacomp.2012.03.019

To correlate Heidelberg Retina Tomograph (HRT) derived macular edema (DME) index with severity of diabetic retinopathy and systemic factors. A total of 300 diabetic patients were recruited for the study for each of them a value for the macular edema index was obtained using the HRT II. Patients' age, gender, duration and type of diabetes mellitus, latest HbA1c result and presence or absence of co-morbid factors (hypertension, ischemic heart disease, nephropathy) were recorded together with the stage of diabetic retinopathy. These were correlated with DME. Out of 300 patients, HRT defined macula edema was seen in 68 patients (22.6%). There is a wider and higher range (95% percentile) of macula edema index in the severe non proliferative diabetic retinopathy (NPDR) group. Independent samples t test showed significant difference between the severe NPDR group and no DR group (p<0.001), mild NPDR group (p<0.05) and moderate NPDR group (p<0.05). A higher macula edema index was also found to have a low degree of correlation with more advanced stages of retinopathy (r=0.310; p<0.001). Also nephropathy showed a strong and significant correlation with DME. Hypertension had moderately significant correlation with DME. This study found no correlation between ischemic heart disease and DME. HRT derived scanning laser edema index is a reliable objective tool to evaluate diabetic retinopathy and systemic risk factors.

Matched MeSH terms: Macular Edema/diagnosis*