The purpose of this study is to assess the accuracy of artificial intelligence (AI)-based screening for diabetic retinopathy (DR) and to explore the feasibility of applying AI-based technique to ...community hospital for DR screening.
Nonmydriatic fundus photos were taken for 889 diabetic patients who were screened in community hospital clinic. According to DR international classification standards, ophthalmologists and AI identified and classified these fundus photos. The sensitivity and specificity of AI automatic grading were evaluated according to ophthalmologists' grading.
DR was detected by ophthalmologists in 143 (16.1%) participants and by AI in 145 (16.3%) participants. Among them, there were 101 (11.4%) participants diagnosed with referable diabetic retinopathy (RDR) by ophthalmologists and 103 (11.6%) by AI. The sensitivity, specificity and area under the curve (AUC) of AI for detecting DR were 90.79% (95% CI 86.4-94.1), 98.5% (95% CI 97.8-99.0) and 0.946 (95% CI 0.935-0.956), respectively. For detecting RDR, the sensitivity, specificity and AUC of AI were 91.18% (95% CI 86.4-94.7), 98.79% (95% CI 98.1-99.3) and 0.950 (95% CI 0.939-0.960), respectively.
AI has high sensitivity and specificity in detecting DR and RDR, so it is feasible to carry out AI-based DR screening in outpatient clinic of community hospital.
To assess the feasibility and clinical utility of artificial intelligence (AI)-based screening for diabetic retinopathy (DR) and macular edema (ME) by combining fundus photos and optical coherence ...tomography (OCT) images in a community hospital. Fundus photos and OCT images were taken for 600 diabetic patients in a community hospital. Ophthalmologists graded these fundus photos according to the International Clinical Diabetic Retinopathy (ICDR) Severity Scale as the ground truth. Two existing trained AI models were used to automatically classify the fundus images into DR grades according to ICDR, and to detect concomitant ME from OCT images, respectively. The criteria for referral were DR grades 2-4 and/or the presence of ME. The sensitivity and specificity of AI grading were evaluated. The number of referable DR cases confirmed by ophthalmologists and AI was calculated, respectively. DR was detected in 81 (13.5%) participants by ophthalmologists and in 94 (15.6%) by AI, and 45 (7.5%) and 53 (8.8%) participants were diagnosed with referable DR by ophthalmologists and by AI, respectively. The sensitivity, specificity and area under the curve (AUC) of AI for detecting DR were 91.67%, 96.92% and 0.944, respectively. For detecting referable DR, the sensitivity, specificity and AUC of AI were 97.78%, 98.38% and 0.981, respectively. ME was detected from OCT images in 49 (8.2%) participants by ophthalmologists and in 57 (9.5%) by AI, and the sensitivity, specificity and AUC of AI were 91.30%, 97.46% and 0.944, respectively. When combining fundus photos and OCT images, the number of referrals identified by ophthalmologists increased from 45 to 75 and from 53 to 85 by AI. AI-based DR screening has high sensitivity and specificity and may feasibly improve the referral rate of community DR.
Background/aimsThis study evaluates the performance of the Airdoc retinal artificial intelligence system (ARAS) for detecting multiple fundus diseases in real-world scenarios in primary healthcare ...settings and investigates the fundus disease spectrum based on ARAS.MethodsThis real-world, multicentre, cross-sectional study was conducted in Shanghai and Xinjiang, China. Six primary healthcare settings were included in this study. Colour fundus photographs were taken and graded by ARAS and retinal specialists. The performance of ARAS is described by its accuracy, sensitivity, specificity and positive and negative predictive values. The spectrum of fundus diseases in primary healthcare settings has also been investigated.ResultsA total of 4795 participants were included. The median age was 57.0 (IQR 39.0–66.0) years, and 3175 (66.2%) participants were female. The accuracy, specificity and negative predictive value of ARAS for detecting normal fundus and 14 retinal abnormalities were high, whereas the sensitivity and positive predictive value varied in detecting different abnormalities. The proportion of retinal drusen, pathological myopia and glaucomatous optic neuropathy was significantly higher in Shanghai than in Xinjiang. Moreover, the percentages of referable diabetic retinopathy, retinal vein occlusion and macular oedema in middle-aged and elderly people in Xinjiang were significantly higher than in Shanghai.ConclusionThis study demonstrated the dependability of ARAS for detecting multiple retinal diseases in primary healthcare settings. Implementing the AI-assisted fundus disease screening system in primary healthcare settings might be beneficial in reducing regional disparities in medical resources. However, the ARAS algorithm must be improved to achieve better performance.Trial registration number NCT04592068.
Intraocular lens (IOL) opacification after cataract surgery has been widely reported, but opacification during pars-plana vitrectomy (PPV) has not been reported. In our case, a 59-year-old male ...patient underwent PPV. During the surgery, IOL was found to be cloudy, and the area accounted for half of IOL. The surgical field was not affected. At the end of surgery, the degree of opacification decreased significantly. On the first day after surgery, IOL was completely transparent. IOL opacification may be caused by condensation and does not affect retina observation during PPV. It is not necessary to remove and replace the IOL immediately.
To study the efficacy of rapamycin (RAPA)-chitosan (CS)-calcium alginate (CA) sustained-release microspheres on scar formation in a rabbit model of glaucoma filtration surgery. Eighty New Zealand ...white rabbits were randomly divided into four groups and a glaucoma filtration model was
established by scleral bite through the eyes. RAPA-CS-CA sustained-release microspheres were implanted in the right eye of 40 rabbits (Group A) and CS blank sustained-release microspheres were implanted in the left eye (Group B). Another 40 rabbits were treated with a 0.2 g·L-1
RAPA cotton sheet in the right eye (Group C) and the left eye underwent a simple sclerotomy (Group D). The intraocular pressure, filter bleb, anterior chamber inflammation, complications, and corneal endothelial cell density were observed after the operation. Rabbits were euthanized for pathological
examination 7 days, 14 days, and 21 days after the operation. The drug loading rate of RAPA-CS-CA sustainedrelease microspheres was (34.58±1.47)% and the encapsulation rate was (56.23±1.55)%. The microsphere release in vitro was relatively stable. The release rate of the
microspheres during the burst was only 16.54%. After 49 days, the cumulative release rate of the microspheres reached 94.07% and the sustained release effect was significant within 45 days. Group A maintained low-level intraocular pressure for the longest period of time, followed by Group
C, and then Group B and D. The survival time of filter vesicles in Group A was longer than that in other groups. There were no postoperative complications in each group. The conjunctival epithelium of Group A had better integrity and fewer subconjunctival fibroblasts than other groups. There
was no obvious inflammation or infiltration around the filtering mouth and there were fewer new collagen fibers. RAPA-CS-CA slow-release microspheres safely and effectively inhibited the proliferation of fibroblasts and neonatal collagen fibers in rabbit glaucoma filtration surgery and significantly
improved the success rate of glaucoma filtration surgery.
To evaluate the morphology and functional recovery of the retina after treatment of idiopathic choroidal neovascularization using intravitreal injections of bevacizumab in young adults.
For this ...interventional case series, 20 eyes of 19 patients with idiopathic choroidal neovascularization were treated with multiple intravitreal injections of bevacizumab. Changes in best-corrected visual acuity before the treatment and at follow-up visits were recorded. Structural changes were evaluated using optical coherence tomography and functional changes were assessed using microperimetry.
Twenty eyes were followed for 12 months after their first injection. The eyes underwent an average of 3.95 injections. All eyes had a stable or an improved vision. The mean logarithm of the minimum angle of resolution best-corrected visual acuity improved from 0.43 to 0.06 (Wilcoxon signed-ranks test, P < 0.005). Improvement in macular function was detected as early as 1 month after the treatment and lasted for at least 6 months. Microperimetry demonstrated that mean retinal sensitivities within the central 10° field (10.29 ± 5.12 dB) at baseline improved to 13.98 ± 3.96 dB at the last visit. Dense scotomas were found in 13 of the 20 eyes at baseline and 5 of the 20 eyes at the last visit. Stable fixation (6 of 20 at baseline) was found in 17 of the 20 eyes at the last visit. Twelve of the 14 eyes with either a predominantly eccentric or poor central fixation at baseline established central fixation at 12 months. No serious local or systemic complications were encountered.
In young adults with idiopathic choroidal neovascularization, an improvement in visual acuity and macular function was detected after intravitreal injections of bevacizumab.
Recent years, more and more multi-view data are widely used in many real-world applications. This kind of data (such as image data) is high dimensional and obtained from different feature extractors, ...which represents distinct perspectives of the data. How to cluster such data efficiently is a challenge. In this paper, we propose a novel multi-view clustering framework, called re-weighted discriminatively embedded K-means, for this task. The proposed method is a multiview least-absolute residual model, which induces robustness to efficiently mitigates the influence of outliers and realizes dimension reduction during multi-view clustering. Specifically, the proposed model is an unsupervised optimization scheme, which utilizes iterative re-weighted least squares to solve least-absolute residual and adaptively controls the distribution of multiple weights in a re-weighted manner only based on its own low-dimensional subspaces and a common clustering indicator matrix. Furthermore, theoretical analysis (including optimality and convergence analysis) and the optimization algorithm are also presented. Compared with several state-of-the-art multi-view clustering methods, the proposed method substantially improves the accuracy of the clustering results on widely used benchmark data sets, which demonstrates the superiority of the proposed work.
In this paper, we propose a new image clustering algorithm, referred to as clustering using local discriminant models and global integration (LDMGI). To deal with the data points sampled from a ...nonlinear manifold, for each data point, we construct a local clique comprising this data point and its neighboring data points. Inspired by the Fisher criterion, we use a local discriminant model for each local clique to evaluate the clustering performance of samples within the local clique. To obtain the clustering result, we further propose a unified objective function to globally integrate the local models of all the local cliques. With the unified objective function, spectral relaxation and spectral rotation are used to obtain the binary cluster indicator matrix for all the samples. We show that LDMGI shares a similar objective function with the spectral clustering (SC) algorithms, e.g., normalized cut (NCut). In contrast to NCut in which the Laplacian matrix is directly calculated based upon a Gaussian function, a new Laplacian matrix is learnt in LDMGI by exploiting both manifold structure and local discriminant information. We also prove that K-means and discriminative K-means (DisKmeans) are both special cases of LDMGI. Extensive experiments on several benchmark image datasets demonstrate the effectiveness of LDMGI. We observe in the experiments that LDMGI is more robust to algorithmic parameter, when compared with NCut. Thus, LDMGI is more appealing for the real image clustering applications in which the ground truth is generally not available for tuning algorithmic parameters.
We present a new framework for multimedia content analysis and retrieval which consists of two independent algorithms. First, we propose a new semi-supervised algorithm called ranking with Local ...Regression and Global Alignment (LRGA) to learn a robust Laplacian matrix for data ranking. In LRGA, for each data point, a local linear regression model is used to predict the ranking scores of its neighboring points. A unified objective function is then proposed to globally align the local models from all the data points so that an optimal ranking score can be assigned to each data point. Second, we propose a semi-supervised long-term Relevance Feedback (RF) algorithm to refine the multimedia data representation. The proposed long-term RF algorithm utilizes both the multimedia data distribution in multimedia feature space and the history RF information provided by users. A trace ratio optimization problem is then formulated and solved by an efficient algorithm. The algorithms have been applied to several content-based multimedia retrieval applications, including cross-media retrieval, image retrieval, and 3D motion/pose data retrieval. Comprehensive experiments on four data sets have demonstrated its advantages in precision, robustness, scalability, and computational efficiency.