Displaying all 3 publications

Abstract:
Sort:
  1. A decision support system for automatic screening of non-proliferative diabetic retinopathy
    Reza AW, Eswaran C
    J Med Syst, 2011 Feb;35(1):17-24.
    PMID: 20703589 DOI: 10.1007/s10916-009-9337-y
    The increasing number of diabetic retinopathy (DR) cases world wide demands the development of an automated decision support system for quick and cost-effective screening of DR. We present an automatic screening system for detecting the early stage of DR, which is known as non-proliferative diabetic retinopathy (NPDR). The proposed system involves processing of fundus images for extraction of abnormal signs, such as hard exudates, cotton wool spots, and large plaque of hard exudates. A rule based classifier is used for classifying the DR into two classes, namely, normal and abnormal. The abnormal NPDR is further classified into three levels, namely, mild, moderate, and severe. To evaluate the performance of the proposed decision support framework, the algorithms have been tested on the images of STARE database. The results obtained from this study show that the proposed system can detect the bright lesions with an average accuracy of about 97%. The study further shows promising results in classifying the bright lesions correctly according to NPDR severity levels.
    Matched MeSH terms: Diabetic Retinopathy/classification*
  2. 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: Diabetic Retinopathy/classification*
  3. Total Protein Concentration and Tumor Necrosis Factor α in Tears of Nonproliferative Diabetic Retinopathy
    Amil-Bangsa NH, Mohd-Ali B, Ishak B, Abdul-Aziz CNN, Ngah NF, Hashim H, et al.
    Optom Vis Sci, 2019 12;96(12):934-939.
    PMID: 31834153 DOI: 10.1097/OPX.0000000000001456
    SIGNIFICANCE: Total protein concentration (TPC) and tumor necrosis factor α (TNF-α) concentration in tears are correlated with severity of retinopathy. However, minimal data are available in the literature for investigating tear TPC and TNF-α concentrations in Asian individuals with different severity of nonproliferative diabetic retinopathy (NPDR).

    PURPOSE: This study evaluated differences of TPC and TNF-α concentrations in tears at different severity of NPDR among participants with diabetes in comparison with normal participants.

    METHODS: A total of 75 participants were categorized based on Early Treatment for Diabetic Retinopathy Study scale, with 15 participants representing each group, namely, normal, diabetes without retinopathy, mild NPDR, moderate NPDR, and severe NPDR. All participants were screened using McMonnies questionnaire. Refraction was conducted subjectively. Visual acuity was measured using a LogMAR chart. Twenty-five microliters of basal tears was collected using glass capillary tubes. Total protein concentration and TNF-α concentrations were determined using Bradford assay and enzyme-linked immunosorbent assay, respectively.

    RESULTS: Mean ± SD age of participants (n = 75) was 57.88 ± 4.71 years, and participants scored equally in McMonnies questionnaire (P = .90). Mean visual acuity was significantly different in severe NPDR (P = .003). Mean tear TPC was significantly lower, and mean tear TNF-α concentration was significantly higher in moderate and severe NPDR (P < .001). Mean ± SD tear TPC and TNF-α concentrations for normal were 7.10 ± 1.53 and 1.39 ± 0.24 pg/mL; for diabetes without retinopathy, 6.37 ± 1.65 and 1.53 ± 0.27 pg/mL; for mild NPDR, 6.32 ± 2.05 and 1.60 ± 0.21 pg/mL; for moderate NPDR, 3.88 ± 1.38 and 1.99 ± 0.05 pg/mL; and for severe NPDR, 3.64 ± 1.26 and 2.21 ± 0.04 pg/mL, respectively. Tear TPC and TNF-α concentrations were significantly correlated (r = -0.50, P < .0001). Visual acuity was significantly correlated with tear TPC (r = -0.236, P = .04) and TNF-α concentrations (r = 0.432, P < .0001).

    CONCLUSIONS: This cross-sectional study identified differences in tear TPC and TNF-α concentrations with increasing severity of NPDR.

    Matched MeSH terms: Diabetic Retinopathy/classification
Related Terms
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links