0
selected
-
1.
Automated Deformation-Based Analysis of 3D Optical Coherence Tomography in Diabetic Retinopathy.
Khansari, MM, Zhang, J, Qiao, Y, Gahm, JK, Sarabi, MS, Kashani, AH, Shi, Y
IEEE transactions on medical imaging. 2020;(1):236-245
-
-
Free full text
-
Abstract
Diabetic retinopathy (DR) is a significant microvascular complication of diabetes mellitus and a leading cause of vision impairment in working age adults. Optical coherence tomography (OCT) is a routinely used clinical tool to observe retinal structural and thickness alterations in DR. Pathological changes that alter the normal anatomy of the retina, such as intraretinal edema, pose great challenges for conventional layer-based analysis of OCT images. We present an alternative approach for the automated analysis of OCT volumes in DR research based on nonlinear registration. In this paper, we first obtain an anatomically consistent volume of interest (VOI) in different OCT images via carefully designed masking and affine registration. After that, efficient B-spline transformations are computed using stochastic gradient descent optimization. Using the OCT volumes of normal controls, for which layer-based segmentation works well, we demonstrate the accuracy of our registration-based analysis in aligning layer boundaries. By nonlinearly registering the OCT volumes of DR subjects to an atlas constructed from normal controls and measuring the Jacobian determinant of the deformation, we can simultaneously visualize tissue contraction and expansion due to DR pathology. Tensor-based morphometry (TBM) can also be performed for quantitative analysis of local structural changes. In our experimental results, we apply our method to a dataset of 105 subjects and demonstrate that volumetric OCT registration and TBM analysis can successfully detect local retinal structural alterations due to DR.
-
2.
Platelet distribution width, platelet count, and plateletcrit in diabetic retinopathy: A systematic review and meta-analysis of PRISMA guidelines.
Ji, S, Ning, X, Zhang, B, Shi, H, Liu, Z, Zhang, J
Medicine. 2019;(29):e16510
-
-
Free full text
-
Abstract
BACKGROUND Screening and diagnosis of diabetic retinopathy (DR) mainly depends on fundus examination, which is not an intuitive and simple screening or diagnostic method. Recently, the relationship between platelet parameters and DR has become a hot topic. Whether platelet parameters have clinical value in DR is controversial. METHODS Literature was retrieved by formal search of electronic databases (PubMed, Embase, Cochrane library, Scopus, and CNKI) and by hand searching of reference lists of related articles from the beginning of building database to December 2017. Review manager 5.3 was utilized to deal with statistical data. This study was registered at International Prospective Register of Systematic Reviews (number: CRD42018093773). RESULTS This study included 1720 DR patients, 1477 type 2 diabetic mellitus (T2DM) without DR patients and 1456 health controls in 21 eligible studies. We found there was significant increase of platelet distribution width (PDW) level in the comparison of DR versus Control group (standard mean difference [SMD] [95% confidence interval [CI]] = 1.04 [0.68, 1.40]) and DR versus T2DM without DR group (SMD [95% CI] = 0.68 [0.40, 0.95]). For platelet count (PLT), it showed obvious decrease in the comparison of DR versus T2DM without DR group (SMD [95% CI] = -0.26 [-0.49, -0.03]) and no difference in comparison of DR versus Control (SMD [95% CI] = -0.26 [-0.51, -0.00]). Subgroup analysis showed that significant result of PDW level appeared in China and Turkey in all comparisons, while similar results of PLT only in China. In addition, PDW level was different in various DR-subtypes, obvious high level in proliferation DR. CONCLUSIONS We concluded that the guiding significance of PDW and PLT in diagnosis and monitor of DR, and especially, application of PDW to PDR management may have potential sense.
-
3.
Retinal Microaneurysms Detection Using Local Convergence Index Features.
Dashtbozorg, B, Zhang, J, Huang, F, Ter Haar Romeny, BM
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2018;(7):3300-3315
Abstract
Retinal microaneurysms (MAs) are the earliest clinical sign of diabetic retinopathy disease. Detection of MAs is crucial for the early diagnosis of diabetic retinopathy and prevention of blindness. In this paper, a novel and reliable method for automatic detection of MAs in retinal images is proposed. In the first stage of the proposed method, several preliminary microaneurysm candidates are extracted using a gradient weighting technique and an iterative thresholding approach. In the next stage, in addition to intensity and shape descriptors, a new set of features based on local convergence index filters is extracted for each candidate. Finally, the collective set of features is fed to a hybrid sampling/boosting classifier to discriminate the MAs from non-MAs candidates. The method is evaluated on images with different resolutions and modalities (color and scanning laser ophthalmoscope) using six publicly available data sets including the retinopathy online challenges (ROC) data set. The proposed method achieves an average sensitivity score of 0.471 on the ROC data set outperforming state-of-the-art approaches in an extensive comparison. The experimental results on the other five data sets demonstrate the effectiveness and robustness of the proposed MAs detection method regardless of different image resolutions and modalities.
-
4.
Relationship between vitamin D deficiency and diabetic retinopathy: a meta-analysis.
Zhang, J, Upala, S, Sanguankeo, A
Canadian journal of ophthalmology. Journal canadien d'ophtalmologie. 2017;:S39-S44
Abstract
OBJECTIVE The purpose of this study was to evaluate the evidence for an association between diabetic retinopathy (DR) and vitamin D deficiency. DESIGN Meta-analysis. METHODS We included 14 observational studies with 10 007 participants who had undergone assessment for both DR and vitamin D deficiency. Pooled odds ratios (ORs) and 95% CIs were calculated using a random-effect, Mantel-Haenszel analysis. RESULTS There was a statistically significant association between DR and vitamin D deficiency with an overall pooled OR of 1.27 (95% CI, 1.17-1.37; P = 0.001; I2 = 80%; Pheterogeneity = 0.01). There was also a statistically significant lower serum vitamin D level in patient subgroups with DR versus control groups, with an overall mean difference of -1.32 ng/mL (95% CI, -2.50 to -0.15; P = 0.001; I2 = 89%; Pheterogeneity = 0.01). CONCLUSION There is a statistically significant association between vitamin D deficiency and DR.
-
5.
Meta-analysis and review on the changes of tear function and corneal sensitivity in diabetic patients.
Lv, H, Li, A, Zhang, X, Xu, M, Qiao, Y, Zhang, J, Yu, L
Acta ophthalmologica. 2014;(2):e96-e104
-
-
Free full text
-
Abstract
To perform a comprehensive evaluation and comparison of tear function in diabetic and non-diabetic patients. Research related to tear function in diabetic and non-diabetic patients was gathered using PubMed, EBSCO, OVID. Two reviewers independently conducted the literature search. The quality assessment and the data extraction were performed in accordance with exclusion criteria and cross-checking. RevMan 5.1.7 software was used for the meta-analysis. The tear film break-up time was studied in eight articles with a total of 1449 samples. Through a random-effects model analysis, the combined weighted mean difference (WMD) was -4.44 [-5.87, -3.01]. The time in diabetic patients was shorter than that in the non-diabetic group (p < 0.00001). The basal tear secretion test was studied in seven articles with a total of 949 samples. The combined WMD was -3.96 [-5.70, -2.23], and the difference between the diabetic group and control group was statistically significant (p < 0.00001). The total tear secretion test was studied in five articles with a total of 921 samples. The combined WMD was -3.96 [-7.43, -0.50]. The difference between the diabetic and control groups was statistically significant (p = 0.03). The corneal sensitivity was compared in eight studies with a total of 976 samples. Through a random-effects model analysis, the standardized mean difference (SMD) was -5.14 [-6.99, -3.29]. The corneal sensitivity was lower in diabetic patients than the control group (p < 0.00001). Our study suggests that the tear functions are worse in diabetic patients compared with the control group. Moreover, patients with PDR are more predisposed to impaired tear functions.